diff --git "a/upernet_beit_adapter_large_512_80k_cocostuff10k_ss.log" "b/upernet_beit_adapter_large_512_80k_cocostuff10k_ss.log" new file mode 100644--- /dev/null +++ "b/upernet_beit_adapter_large_512_80k_cocostuff10k_ss.log" @@ -0,0 +1,6592 @@ +2022-05-05 09:13:59,620 - mmseg - INFO - Environment info: +------------------------------------------------------------ +sys.platform: linux +Python: 3.7.11 (default, Jul 27 2021, 14:32:16) [GCC 7.5.0] +CUDA available: True +GPU 0,1,2,3,4,5,6,7: A100-SXM-80GB +CUDA_HOME: /mnt/lustre/share/cuda-11.1 +NVCC: Build cuda_11.1.TC455_06.29069683_0 +GCC: gcc (GCC) 5.4.0 +PyTorch: 1.9.0+cu111 +PyTorch compiling details: PyTorch built with: + - GCC 7.3 + - C++ Version: 201402 + - Intel(R) Math Kernel Library Version 2020.0.0 Product Build 20191122 for Intel(R) 64 architecture applications + - Intel(R) MKL-DNN v2.1.2 (Git Hash 98be7e8afa711dc9b66c8ff3504129cb82013cdb) + - OpenMP 201511 (a.k.a. OpenMP 4.5) + - NNPACK is enabled + - CPU capability usage: AVX2 + - CUDA Runtime 11.1 + - NVCC architecture flags: -gencode;arch=compute_37,code=sm_37;-gencode;arch=compute_50,code=sm_50;-gencode;arch=compute_60,code=sm_60;-gencode;arch=compute_70,code=sm_70;-gencode;arch=compute_75,code=sm_75;-gencode;arch=compute_80,code=sm_80;-gencode;arch=compute_86,code=sm_86 + - CuDNN 8.0.5 + - Magma 2.5.2 + - Build settings: BLAS_INFO=mkl, BUILD_TYPE=Release, CUDA_VERSION=11.1, CUDNN_VERSION=8.0.5, CXX_COMPILER=/opt/rh/devtoolset-7/root/usr/bin/c++, CXX_FLAGS= -Wno-deprecated -fvisibility-inlines-hidden -DUSE_PTHREADPOOL -fopenmp -DNDEBUG -DUSE_KINETO -DUSE_FBGEMM -DUSE_QNNPACK -DUSE_PYTORCH_QNNPACK -DUSE_XNNPACK -DSYMBOLICATE_MOBILE_DEBUG_HANDLE -O2 -fPIC -Wno-narrowing -Wall -Wextra -Werror=return-type -Wno-missing-field-initializers -Wno-type-limits -Wno-array-bounds -Wno-unknown-pragmas -Wno-sign-compare -Wno-unused-parameter -Wno-unused-variable -Wno-unused-function -Wno-unused-result -Wno-unused-local-typedefs -Wno-strict-overflow -Wno-strict-aliasing -Wno-error=deprecated-declarations -Wno-stringop-overflow -Wno-psabi -Wno-error=pedantic -Wno-error=redundant-decls -Wno-error=old-style-cast -fdiagnostics-color=always -faligned-new -Wno-unused-but-set-variable -Wno-maybe-uninitialized -fno-math-errno -fno-trapping-math -Werror=format -Wno-stringop-overflow, LAPACK_INFO=mkl, PERF_WITH_AVX=1, PERF_WITH_AVX2=1, PERF_WITH_AVX512=1, TORCH_VERSION=1.9.0, USE_CUDA=ON, USE_CUDNN=ON, USE_EXCEPTION_PTR=1, USE_GFLAGS=OFF, USE_GLOG=OFF, USE_MKL=ON, USE_MKLDNN=ON, USE_MPI=OFF, USE_NCCL=ON, USE_NNPACK=ON, USE_OPENMP=ON, + +TorchVision: 0.10.0+cu111 +OpenCV: 4.5.5 +MMCV: 1.4.2 +MMCV Compiler: GCC 7.3 +MMCV CUDA Compiler: 11.1 +MMSegmentation: 0.20.2+ +------------------------------------------------------------ + +2022-05-05 09:13:59,620 - mmseg - INFO - Distributed training: True +2022-05-05 09:13:59,948 - mmseg - INFO - Config: +norm_cfg = dict(type='SyncBN', requires_grad=True) +model = dict( + type='EncoderDecoder', + pretrained='pretrained/beit_large_patch16_224_pt22k_ft22k.pth', + backbone=dict( + type='BEiTAdapter', + patch_size=16, + embed_dim=1024, + depth=24, + num_heads=16, + mlp_ratio=4, + qkv_bias=True, + use_abs_pos_emb=False, + use_rel_pos_bias=True, + img_size=512, + init_values=1e-06, + drop_path_rate=0.3, + conv_inplane=64, + n_points=4, + deform_num_heads=16, + interact_with_ffn=True, + interact_ffn_ratio=0.25, + interact_deform_ratio=0.5, + extract_with_ffn=True, + extract_ffn_ratio=0.25, + extract_deform_ratio=0.5, + num_extract_block=2, + add_vit_feature=True, + interact_indexes=[[0, 5], [6, 11], [12, 17], [18, 23]]), + decode_head=dict( + type='UPerHead', + in_channels=[1024, 1024, 1024, 1024], + in_index=[0, 1, 2, 3], + pool_scales=(1, 2, 3, 6), + channels=1024, + dropout_ratio=0.1, + num_classes=171, + norm_cfg=dict(type='SyncBN', requires_grad=True), + align_corners=False, + loss_decode=dict( + type='CrossEntropyLoss', use_sigmoid=False, loss_weight=1.0)), + auxiliary_head=dict( + type='FCNHead', + in_channels=1024, + in_index=2, + channels=256, + num_convs=1, + concat_input=False, + dropout_ratio=0.1, + num_classes=171, + norm_cfg=dict(type='SyncBN', requires_grad=True), + align_corners=False, + loss_decode=dict( + type='CrossEntropyLoss', use_sigmoid=False, loss_weight=0.4)), + train_cfg=dict(), + test_cfg=dict(mode='slide', crop_size=(512, 512), stride=(341, 341))) +dataset_type = 'COCOStuffDataset' +data_root = 'data/coco_stuff10k' +img_norm_cfg = dict( + mean=[123.675, 116.28, 103.53], std=[58.395, 57.12, 57.375], to_rgb=True) +crop_size = (512, 512) +train_pipeline = [ + dict(type='LoadImageFromFile'), + dict(type='LoadAnnotations', reduce_zero_label=True), + dict(type='Resize', img_scale=(2048, 512), ratio_range=(0.5, 2.0)), + dict(type='RandomCrop', crop_size=(512, 512), cat_max_ratio=0.75), + dict(type='RandomFlip', prob=0.5), + dict(type='PhotoMetricDistortion'), + dict( + type='Normalize', + mean=[123.675, 116.28, 103.53], + std=[58.395, 57.12, 57.375], + to_rgb=True), + dict(type='Pad', size=(512, 512), pad_val=0, seg_pad_val=255), + dict(type='DefaultFormatBundle'), + dict(type='Collect', keys=['img', 'gt_semantic_seg']) +] +test_pipeline = [ + dict(type='LoadImageFromFile'), + dict( + type='MultiScaleFlipAug', + img_scale=(2048, 512), + flip=False, + transforms=[ + dict(type='Resize', keep_ratio=True), + dict(type='ResizeToMultiple', size_divisor=32), + dict(type='RandomFlip'), + dict( + type='Normalize', + mean=[123.675, 116.28, 103.53], + std=[58.395, 57.12, 57.375], + to_rgb=True), + dict(type='ImageToTensor', keys=['img']), + dict(type='Collect', keys=['img']) + ]) +] +data = dict( + samples_per_gpu=2, + workers_per_gpu=4, + train=dict( + type='COCOStuffDataset', + data_root='data/coco_stuff10k', + reduce_zero_label=True, + img_dir='images/train2014', + ann_dir='annotations/train2014', + pipeline=[ + dict(type='LoadImageFromFile'), + dict(type='LoadAnnotations', reduce_zero_label=True), + dict(type='Resize', img_scale=(2048, 512), ratio_range=(0.5, 2.0)), + dict(type='RandomCrop', crop_size=(512, 512), cat_max_ratio=0.75), + dict(type='RandomFlip', prob=0.5), + dict(type='PhotoMetricDistortion'), + dict( + type='Normalize', + mean=[123.675, 116.28, 103.53], + std=[58.395, 57.12, 57.375], + to_rgb=True), + dict(type='Pad', size=(512, 512), pad_val=0, seg_pad_val=255), + dict(type='DefaultFormatBundle'), + dict(type='Collect', keys=['img', 'gt_semantic_seg']) + ]), + val=dict( + type='COCOStuffDataset', + data_root='data/coco_stuff10k', + reduce_zero_label=True, + img_dir='images/test2014', + ann_dir='annotations/test2014', + pipeline=[ + dict(type='LoadImageFromFile'), + dict( + type='MultiScaleFlipAug', + img_scale=(2048, 512), + flip=False, + transforms=[ + dict(type='Resize', keep_ratio=True), + dict(type='ResizeToMultiple', size_divisor=32), + dict(type='RandomFlip'), + dict( + type='Normalize', + mean=[123.675, 116.28, 103.53], + std=[58.395, 57.12, 57.375], + to_rgb=True), + dict(type='ImageToTensor', keys=['img']), + dict(type='Collect', keys=['img']) + ]) + ]), + test=dict( + type='COCOStuffDataset', + data_root='data/coco_stuff10k', + reduce_zero_label=True, + img_dir='images/test2014', + ann_dir='annotations/test2014', + pipeline=[ + dict(type='LoadImageFromFile'), + dict( + type='MultiScaleFlipAug', + img_scale=(2048, 512), + flip=False, + transforms=[ + dict(type='Resize', keep_ratio=True), + dict(type='ResizeToMultiple', size_divisor=32), + dict(type='RandomFlip'), + dict( + type='Normalize', + mean=[123.675, 116.28, 103.53], + std=[58.395, 57.12, 57.375], + to_rgb=True), + dict(type='ImageToTensor', keys=['img']), + dict(type='Collect', keys=['img']) + ]) + ])) +log_config = dict( + interval=50, hooks=[dict(type='TextLoggerHook', by_epoch=False)]) +dist_params = dict(backend='nccl') +log_level = 'INFO' +load_from = None +resume_from = None +workflow = [('train', 1)] +cudnn_benchmark = True +optimizer = dict( + type='AdamW', + lr=2e-05, + betas=(0.9, 0.999), + weight_decay=0.05, + constructor='LayerDecayOptimizerConstructor', + paramwise_cfg=dict(num_layers=24, layer_decay_rate=0.9)) +optimizer_config = dict() +lr_config = dict( + policy='poly', + warmup='linear', + warmup_iters=1500, + warmup_ratio=1e-06, + power=1.0, + min_lr=0.0, + by_epoch=False) +runner = dict(type='IterBasedRunner', max_iters=80000) +checkpoint_config = dict(by_epoch=False, interval=1000, max_keep_ckpts=1) +evaluation = dict( + interval=8000, metric='mIoU', pre_eval=True, save_best='mIoU') +work_dir = './work_dirs/upernet_beit_adapter_large_512_80k_cocostuff10k_ss' +gpu_ids = range(0, 8) +auto_resume = False + +2022-05-05 09:14:08,345 - mmseg - INFO - Set random seed to 1642837154, deterministic: False +2022-05-05 09:14:20,193 - mmseg - WARNING - The model and loaded state dict do not match exactly + +unexpected key in source state_dict: fc_norm.weight, fc_norm.bias, head.weight, head.bias + +missing keys in source state_dict: blocks.0.attn.relative_position_index, blocks.1.attn.relative_position_index, blocks.2.attn.relative_position_index, blocks.3.attn.relative_position_index, blocks.4.attn.relative_position_index, blocks.5.attn.relative_position_index, blocks.6.attn.relative_position_index, blocks.7.attn.relative_position_index, blocks.8.attn.relative_position_index, blocks.9.attn.relative_position_index, blocks.10.attn.relative_position_index, blocks.11.attn.relative_position_index, blocks.12.attn.relative_position_index, blocks.13.attn.relative_position_index, blocks.14.attn.relative_position_index, blocks.15.attn.relative_position_index, blocks.16.attn.relative_position_index, blocks.17.attn.relative_position_index, blocks.18.attn.relative_position_index, blocks.19.attn.relative_position_index, blocks.20.attn.relative_position_index, blocks.21.attn.relative_position_index, blocks.22.attn.relative_position_index, blocks.23.attn.relative_position_index + +2022-05-05 09:14:21,902 - mmseg - INFO - initialize UPerHead with init_cfg {'type': 'Normal', 'std': 0.01, 'override': {'name': 'conv_seg'}} +2022-05-05 09:14:22,393 - mmseg - INFO - initialize FCNHead with init_cfg {'type': 'Normal', 'std': 0.01, 'override': {'name': 'conv_seg'}} +Name of parameter - Initialization information + +backbone.cls_token - torch.Size([1, 1, 1024]): +The value is the same before and after calling `init_weights` of EncoderDecoder + +backbone.level_embed - torch.Size([3, 1024]): +The value is the same before and after calling `init_weights` of EncoderDecoder + +backbone.patch_embed.proj.weight - torch.Size([1024, 3, 16, 16]): +The value is the same before and after calling `init_weights` of EncoderDecoder + +backbone.patch_embed.proj.bias - torch.Size([1024]): +The value is the same before and after calling `init_weights` of EncoderDecoder + +backbone.blocks.0.gamma_1 - torch.Size([1024]): +The value is the same before and after calling `init_weights` of EncoderDecoder + +backbone.blocks.0.gamma_2 - torch.Size([1024]): +The value is the same before and after calling `init_weights` of EncoderDecoder + +backbone.blocks.0.norm1.weight - torch.Size([1024]): +The value is the same before and after calling `init_weights` of EncoderDecoder + +backbone.blocks.0.norm1.bias - torch.Size([1024]): +The value is the same before and after calling `init_weights` of EncoderDecoder + +backbone.blocks.0.attn.q_bias - torch.Size([1024]): +The value is the same before and after calling `init_weights` of EncoderDecoder + +backbone.blocks.0.attn.v_bias - torch.Size([1024]): +The value is the same before and after calling `init_weights` of EncoderDecoder + +backbone.blocks.0.attn.relative_position_bias_table - torch.Size([3972, 16]): +The value is the same before and after calling `init_weights` of EncoderDecoder + +backbone.blocks.0.attn.qkv.weight - torch.Size([3072, 1024]): +The value is the same before and after calling `init_weights` of EncoderDecoder + +backbone.blocks.0.attn.proj.weight - torch.Size([1024, 1024]): +The value is the same before and after calling `init_weights` of EncoderDecoder + +backbone.blocks.0.attn.proj.bias - torch.Size([1024]): +The value is the same before and after calling `init_weights` of EncoderDecoder + +backbone.blocks.0.norm2.weight - torch.Size([1024]): +The value is the same before and after calling `init_weights` of EncoderDecoder + +backbone.blocks.0.norm2.bias - torch.Size([1024]): +The value is the same before and after calling `init_weights` of EncoderDecoder + +backbone.blocks.0.mlp.fc1.weight - torch.Size([4096, 1024]): +The value is the same before and after calling `init_weights` of EncoderDecoder + +backbone.blocks.0.mlp.fc1.bias - torch.Size([4096]): +The value is the same before and after calling `init_weights` of EncoderDecoder + +backbone.blocks.0.mlp.fc2.weight - torch.Size([1024, 4096]): +The value is the same before and after calling `init_weights` of EncoderDecoder + +backbone.blocks.0.mlp.fc2.bias - torch.Size([1024]): +The value is the same before and after calling `init_weights` of EncoderDecoder + +backbone.blocks.1.gamma_1 - torch.Size([1024]): +The value is the same before and after calling `init_weights` of EncoderDecoder + +backbone.blocks.1.gamma_2 - torch.Size([1024]): +The value is the same before and after calling `init_weights` of EncoderDecoder + +backbone.blocks.1.norm1.weight - torch.Size([1024]): +The value is the same before and after calling `init_weights` of EncoderDecoder + +backbone.blocks.1.norm1.bias - torch.Size([1024]): +The value is the same before and after calling `init_weights` of EncoderDecoder + +backbone.blocks.1.attn.q_bias - torch.Size([1024]): +The value is the same before and after calling `init_weights` of EncoderDecoder + +backbone.blocks.1.attn.v_bias - torch.Size([1024]): +The value is the same before and after calling `init_weights` of EncoderDecoder + +backbone.blocks.1.attn.relative_position_bias_table - torch.Size([3972, 16]): +The value is the same before and after calling `init_weights` of EncoderDecoder + +backbone.blocks.1.attn.qkv.weight - torch.Size([3072, 1024]): +The value is the same before and after calling `init_weights` of EncoderDecoder + +backbone.blocks.1.attn.proj.weight - torch.Size([1024, 1024]): +The value is the same before and after calling `init_weights` of EncoderDecoder + +backbone.blocks.1.attn.proj.bias - torch.Size([1024]): +The value is the same before and after calling `init_weights` of EncoderDecoder + +backbone.blocks.1.norm2.weight - torch.Size([1024]): +The value is the same before and after calling `init_weights` of EncoderDecoder + +backbone.blocks.1.norm2.bias - torch.Size([1024]): +The value is the same before and after calling `init_weights` of EncoderDecoder + +backbone.blocks.1.mlp.fc1.weight - torch.Size([4096, 1024]): +The value is the same before and after calling `init_weights` of EncoderDecoder + +backbone.blocks.1.mlp.fc1.bias - torch.Size([4096]): +The value is the same before and after calling `init_weights` of EncoderDecoder + +backbone.blocks.1.mlp.fc2.weight - torch.Size([1024, 4096]): +The value is the same before and after calling `init_weights` of EncoderDecoder + +backbone.blocks.1.mlp.fc2.bias - torch.Size([1024]): +The value is the same before and after calling `init_weights` of EncoderDecoder + +backbone.blocks.2.gamma_1 - torch.Size([1024]): +The value is the same before and after calling `init_weights` of EncoderDecoder + +backbone.blocks.2.gamma_2 - torch.Size([1024]): +The value is the same before and after calling `init_weights` of EncoderDecoder + +backbone.blocks.2.norm1.weight - torch.Size([1024]): +The value is the same before and after calling `init_weights` of EncoderDecoder + +backbone.blocks.2.norm1.bias - torch.Size([1024]): +The value is the same before and after calling `init_weights` of EncoderDecoder + +backbone.blocks.2.attn.q_bias - torch.Size([1024]): +The value is the same before and after calling `init_weights` of EncoderDecoder + +backbone.blocks.2.attn.v_bias - torch.Size([1024]): +The value is the same before and after calling `init_weights` of EncoderDecoder + +backbone.blocks.2.attn.relative_position_bias_table - torch.Size([3972, 16]): +The value is the same before and after calling `init_weights` of EncoderDecoder + +backbone.blocks.2.attn.qkv.weight - torch.Size([3072, 1024]): +The value is the same before and after calling `init_weights` of EncoderDecoder + +backbone.blocks.2.attn.proj.weight - torch.Size([1024, 1024]): +The value is the same before and after calling `init_weights` of EncoderDecoder + +backbone.blocks.2.attn.proj.bias - torch.Size([1024]): +The value is the same before and after calling `init_weights` of EncoderDecoder + +backbone.blocks.2.norm2.weight - torch.Size([1024]): +The value is the same before and after calling `init_weights` of EncoderDecoder + +backbone.blocks.2.norm2.bias - torch.Size([1024]): +The value is the same before and after calling `init_weights` of EncoderDecoder + +backbone.blocks.2.mlp.fc1.weight - torch.Size([4096, 1024]): +The value is the same before and after calling `init_weights` of EncoderDecoder + +backbone.blocks.2.mlp.fc1.bias - torch.Size([4096]): +The value is the same before and after calling `init_weights` of EncoderDecoder + +backbone.blocks.2.mlp.fc2.weight - torch.Size([1024, 4096]): +The value is the same before and after calling `init_weights` of EncoderDecoder + +backbone.blocks.2.mlp.fc2.bias - torch.Size([1024]): +The value is the same before and after calling `init_weights` of EncoderDecoder + +backbone.blocks.3.gamma_1 - torch.Size([1024]): +The value is the same before and after calling `init_weights` of EncoderDecoder + +backbone.blocks.3.gamma_2 - torch.Size([1024]): +The value is the same before and after calling `init_weights` of EncoderDecoder + +backbone.blocks.3.norm1.weight - torch.Size([1024]): +The value is the same before and after calling `init_weights` of EncoderDecoder + +backbone.blocks.3.norm1.bias - torch.Size([1024]): +The value is the same before and after calling `init_weights` of EncoderDecoder + +backbone.blocks.3.attn.q_bias - torch.Size([1024]): +The value is the same before and after calling `init_weights` of EncoderDecoder + +backbone.blocks.3.attn.v_bias - torch.Size([1024]): +The value is the same before and after calling `init_weights` of EncoderDecoder + +backbone.blocks.3.attn.relative_position_bias_table - torch.Size([3972, 16]): +The value is the same before and after calling `init_weights` of EncoderDecoder + +backbone.blocks.3.attn.qkv.weight - torch.Size([3072, 1024]): +The value is the same before and after calling `init_weights` of EncoderDecoder + +backbone.blocks.3.attn.proj.weight - torch.Size([1024, 1024]): +The value is the same before and after calling `init_weights` of EncoderDecoder + +backbone.blocks.3.attn.proj.bias - torch.Size([1024]): +The value is the same before and after calling `init_weights` of EncoderDecoder + +backbone.blocks.3.norm2.weight - torch.Size([1024]): +The value is the same before and after calling `init_weights` of EncoderDecoder + +backbone.blocks.3.norm2.bias - torch.Size([1024]): +The value is the same before and after calling `init_weights` of EncoderDecoder + +backbone.blocks.3.mlp.fc1.weight - torch.Size([4096, 1024]): +The value is the same before and after calling `init_weights` of EncoderDecoder + +backbone.blocks.3.mlp.fc1.bias - torch.Size([4096]): +The value is the same before and after calling `init_weights` of EncoderDecoder + +backbone.blocks.3.mlp.fc2.weight - torch.Size([1024, 4096]): +The value is the same before and after calling `init_weights` of EncoderDecoder + +backbone.blocks.3.mlp.fc2.bias - torch.Size([1024]): +The value is the same before and after calling `init_weights` of EncoderDecoder + +backbone.blocks.4.gamma_1 - torch.Size([1024]): +The value is the same before and after calling `init_weights` of EncoderDecoder + +backbone.blocks.4.gamma_2 - torch.Size([1024]): +The value is the same before and after calling `init_weights` of EncoderDecoder + +backbone.blocks.4.norm1.weight - torch.Size([1024]): +The value is the same before and after calling `init_weights` of EncoderDecoder + +backbone.blocks.4.norm1.bias - torch.Size([1024]): +The value is the same before and after calling `init_weights` of EncoderDecoder + +backbone.blocks.4.attn.q_bias - torch.Size([1024]): +The value is the same before and after calling `init_weights` of EncoderDecoder + +backbone.blocks.4.attn.v_bias - torch.Size([1024]): +The value is the same before and after calling `init_weights` of EncoderDecoder + +backbone.blocks.4.attn.relative_position_bias_table - torch.Size([3972, 16]): +The value is the same before and after calling `init_weights` of EncoderDecoder + +backbone.blocks.4.attn.qkv.weight - torch.Size([3072, 1024]): +The value is the same before and after calling `init_weights` of EncoderDecoder + +backbone.blocks.4.attn.proj.weight - torch.Size([1024, 1024]): +The value is the same before and after calling `init_weights` of EncoderDecoder + +backbone.blocks.4.attn.proj.bias - torch.Size([1024]): +The value is the same before and after calling `init_weights` of EncoderDecoder + +backbone.blocks.4.norm2.weight - torch.Size([1024]): +The value is the same before and after calling `init_weights` of EncoderDecoder + +backbone.blocks.4.norm2.bias - torch.Size([1024]): +The value is the same before and after calling `init_weights` of EncoderDecoder + +backbone.blocks.4.mlp.fc1.weight - torch.Size([4096, 1024]): +The value is the same before and after calling `init_weights` of EncoderDecoder + +backbone.blocks.4.mlp.fc1.bias - torch.Size([4096]): +The value is the same before and after calling `init_weights` of EncoderDecoder + +backbone.blocks.4.mlp.fc2.weight - torch.Size([1024, 4096]): +The value is the same before and after calling `init_weights` of EncoderDecoder + +backbone.blocks.4.mlp.fc2.bias - torch.Size([1024]): +The value is the same before and after calling `init_weights` of EncoderDecoder + +backbone.blocks.5.gamma_1 - torch.Size([1024]): +The value is the same before and after calling `init_weights` of EncoderDecoder + +backbone.blocks.5.gamma_2 - torch.Size([1024]): +The value is the same before and after calling `init_weights` of EncoderDecoder + +backbone.blocks.5.norm1.weight - torch.Size([1024]): +The value is the same before and after calling `init_weights` of EncoderDecoder + +backbone.blocks.5.norm1.bias - torch.Size([1024]): +The value is the same before and after calling `init_weights` of EncoderDecoder + +backbone.blocks.5.attn.q_bias - torch.Size([1024]): +The value is the same before and after calling `init_weights` of EncoderDecoder + +backbone.blocks.5.attn.v_bias - torch.Size([1024]): +The value is the same before and after calling `init_weights` of EncoderDecoder + +backbone.blocks.5.attn.relative_position_bias_table - torch.Size([3972, 16]): +The value is the same before and after calling `init_weights` of EncoderDecoder + +backbone.blocks.5.attn.qkv.weight - torch.Size([3072, 1024]): +The value is the same before and after calling `init_weights` of EncoderDecoder + +backbone.blocks.5.attn.proj.weight - torch.Size([1024, 1024]): +The value is the same before and after calling `init_weights` of EncoderDecoder + +backbone.blocks.5.attn.proj.bias - torch.Size([1024]): +The value is the same before and after calling `init_weights` of EncoderDecoder + +backbone.blocks.5.norm2.weight - torch.Size([1024]): +The value is the same before and after calling `init_weights` of EncoderDecoder + +backbone.blocks.5.norm2.bias - torch.Size([1024]): +The value is the same before and after calling `init_weights` of EncoderDecoder + +backbone.blocks.5.mlp.fc1.weight - torch.Size([4096, 1024]): +The value is the same before and after calling `init_weights` of EncoderDecoder + +backbone.blocks.5.mlp.fc1.bias - torch.Size([4096]): +The value is the same before and after calling `init_weights` of EncoderDecoder + +backbone.blocks.5.mlp.fc2.weight - torch.Size([1024, 4096]): +The value is the same before and after calling `init_weights` of EncoderDecoder + +backbone.blocks.5.mlp.fc2.bias - torch.Size([1024]): +The value is the same before and after calling `init_weights` of EncoderDecoder + +backbone.blocks.6.gamma_1 - torch.Size([1024]): +The value is the same before and after calling `init_weights` of EncoderDecoder + +backbone.blocks.6.gamma_2 - torch.Size([1024]): +The value is the same before and after calling `init_weights` of EncoderDecoder + +backbone.blocks.6.norm1.weight - torch.Size([1024]): +The value is the same before and after calling `init_weights` of EncoderDecoder + +backbone.blocks.6.norm1.bias - torch.Size([1024]): +The value is the same before and after calling `init_weights` of EncoderDecoder + +backbone.blocks.6.attn.q_bias - torch.Size([1024]): +The value is the same before and after calling `init_weights` of EncoderDecoder + +backbone.blocks.6.attn.v_bias - torch.Size([1024]): +The value is the same before and after calling `init_weights` of EncoderDecoder + +backbone.blocks.6.attn.relative_position_bias_table - torch.Size([3972, 16]): +The value is the same before and after calling `init_weights` of EncoderDecoder + +backbone.blocks.6.attn.qkv.weight - torch.Size([3072, 1024]): +The value is the same before and after calling `init_weights` of EncoderDecoder + +backbone.blocks.6.attn.proj.weight - torch.Size([1024, 1024]): +The value is the same before and after calling `init_weights` of EncoderDecoder + +backbone.blocks.6.attn.proj.bias - torch.Size([1024]): +The value is the same before and after calling `init_weights` of EncoderDecoder + +backbone.blocks.6.norm2.weight - torch.Size([1024]): +The value is the same before and after calling `init_weights` of EncoderDecoder + +backbone.blocks.6.norm2.bias - torch.Size([1024]): +The value is the same before and after calling `init_weights` of EncoderDecoder + +backbone.blocks.6.mlp.fc1.weight - torch.Size([4096, 1024]): +The value is the same before and after calling `init_weights` of EncoderDecoder + +backbone.blocks.6.mlp.fc1.bias - torch.Size([4096]): +The value is the same before and after calling `init_weights` of EncoderDecoder + +backbone.blocks.6.mlp.fc2.weight - torch.Size([1024, 4096]): +The value is the same before and after calling `init_weights` of EncoderDecoder + +backbone.blocks.6.mlp.fc2.bias - torch.Size([1024]): +The value is the same before and after calling `init_weights` of EncoderDecoder + +backbone.blocks.7.gamma_1 - torch.Size([1024]): +The value is the same before and after calling `init_weights` of EncoderDecoder + +backbone.blocks.7.gamma_2 - torch.Size([1024]): +The value is the same before and after calling `init_weights` of EncoderDecoder + +backbone.blocks.7.norm1.weight - torch.Size([1024]): +The value is the same before and after calling `init_weights` of EncoderDecoder + +backbone.blocks.7.norm1.bias - torch.Size([1024]): +The value is the same before and after calling `init_weights` of EncoderDecoder + +backbone.blocks.7.attn.q_bias - torch.Size([1024]): +The value is the same before and after calling `init_weights` of EncoderDecoder + +backbone.blocks.7.attn.v_bias - torch.Size([1024]): +The value is the same before and after calling `init_weights` of EncoderDecoder + +backbone.blocks.7.attn.relative_position_bias_table - torch.Size([3972, 16]): +The value is the same before and after calling `init_weights` of EncoderDecoder + +backbone.blocks.7.attn.qkv.weight - torch.Size([3072, 1024]): +The value is the same before and after calling `init_weights` of EncoderDecoder + +backbone.blocks.7.attn.proj.weight - torch.Size([1024, 1024]): +The value is the same before and after calling `init_weights` of EncoderDecoder + +backbone.blocks.7.attn.proj.bias - torch.Size([1024]): +The value is the same before and after calling `init_weights` of EncoderDecoder + +backbone.blocks.7.norm2.weight - torch.Size([1024]): +The value is the same before and after calling `init_weights` of EncoderDecoder + +backbone.blocks.7.norm2.bias - torch.Size([1024]): +The value is the same before and after calling `init_weights` of EncoderDecoder + +backbone.blocks.7.mlp.fc1.weight - torch.Size([4096, 1024]): +The value is the same before and after calling `init_weights` of EncoderDecoder + +backbone.blocks.7.mlp.fc1.bias - torch.Size([4096]): +The value is the same before and after calling `init_weights` of EncoderDecoder + +backbone.blocks.7.mlp.fc2.weight - torch.Size([1024, 4096]): +The value is the same before and after calling `init_weights` of EncoderDecoder + +backbone.blocks.7.mlp.fc2.bias - torch.Size([1024]): +The value is the same before and after calling `init_weights` of EncoderDecoder + +backbone.blocks.8.gamma_1 - torch.Size([1024]): +The value is the same before and after calling `init_weights` of EncoderDecoder + +backbone.blocks.8.gamma_2 - torch.Size([1024]): +The value is the same before and after calling `init_weights` of EncoderDecoder + +backbone.blocks.8.norm1.weight - torch.Size([1024]): +The value is the same before and after calling `init_weights` of EncoderDecoder + +backbone.blocks.8.norm1.bias - torch.Size([1024]): +The value is the same before and after calling `init_weights` of EncoderDecoder + +backbone.blocks.8.attn.q_bias - torch.Size([1024]): +The value is the same before and after calling `init_weights` of EncoderDecoder + +backbone.blocks.8.attn.v_bias - torch.Size([1024]): +The value is the same before and after calling `init_weights` of EncoderDecoder + +backbone.blocks.8.attn.relative_position_bias_table - torch.Size([3972, 16]): +The value is the same before and after calling `init_weights` of EncoderDecoder + +backbone.blocks.8.attn.qkv.weight - torch.Size([3072, 1024]): +The value is the same before and after calling `init_weights` of EncoderDecoder + +backbone.blocks.8.attn.proj.weight - torch.Size([1024, 1024]): +The value is the same before and after calling `init_weights` of EncoderDecoder + +backbone.blocks.8.attn.proj.bias - torch.Size([1024]): +The value is the same before and after calling `init_weights` of EncoderDecoder + +backbone.blocks.8.norm2.weight - torch.Size([1024]): +The value is the same before and after calling `init_weights` of EncoderDecoder + +backbone.blocks.8.norm2.bias - torch.Size([1024]): +The value is the same before and after calling `init_weights` of EncoderDecoder + +backbone.blocks.8.mlp.fc1.weight - torch.Size([4096, 1024]): +The value is the same before and after calling `init_weights` of EncoderDecoder + +backbone.blocks.8.mlp.fc1.bias - torch.Size([4096]): +The value is the same before and after calling `init_weights` of EncoderDecoder + +backbone.blocks.8.mlp.fc2.weight - torch.Size([1024, 4096]): +The value is the same before and after calling `init_weights` of EncoderDecoder + +backbone.blocks.8.mlp.fc2.bias - torch.Size([1024]): +The value is the same before and after calling `init_weights` of EncoderDecoder + +backbone.blocks.9.gamma_1 - torch.Size([1024]): +The value is the same before and after calling `init_weights` of EncoderDecoder + +backbone.blocks.9.gamma_2 - torch.Size([1024]): +The value is the same before and after calling `init_weights` of EncoderDecoder + +backbone.blocks.9.norm1.weight - torch.Size([1024]): +The value is the same before and after calling `init_weights` of EncoderDecoder + +backbone.blocks.9.norm1.bias - torch.Size([1024]): +The value is the same before and after calling `init_weights` of EncoderDecoder + +backbone.blocks.9.attn.q_bias - torch.Size([1024]): +The value is the same before and after calling `init_weights` of EncoderDecoder + +backbone.blocks.9.attn.v_bias - torch.Size([1024]): +The value is the same before and after calling `init_weights` of EncoderDecoder + +backbone.blocks.9.attn.relative_position_bias_table - torch.Size([3972, 16]): +The value is the same before and after calling `init_weights` of EncoderDecoder + +backbone.blocks.9.attn.qkv.weight - torch.Size([3072, 1024]): +The value is the same before and after calling `init_weights` of EncoderDecoder + +backbone.blocks.9.attn.proj.weight - torch.Size([1024, 1024]): +The value is the same before and after calling `init_weights` of EncoderDecoder + +backbone.blocks.9.attn.proj.bias - torch.Size([1024]): +The value is the same before and after calling `init_weights` of EncoderDecoder + +backbone.blocks.9.norm2.weight - torch.Size([1024]): +The value is the same before and after calling `init_weights` of EncoderDecoder + +backbone.blocks.9.norm2.bias - torch.Size([1024]): +The value is the same before and after calling `init_weights` of EncoderDecoder + +backbone.blocks.9.mlp.fc1.weight - torch.Size([4096, 1024]): +The value is the same before and after calling `init_weights` of EncoderDecoder + +backbone.blocks.9.mlp.fc1.bias - torch.Size([4096]): +The value is the same before and after calling `init_weights` of EncoderDecoder + +backbone.blocks.9.mlp.fc2.weight - torch.Size([1024, 4096]): +The value is the same before and after calling `init_weights` of EncoderDecoder + +backbone.blocks.9.mlp.fc2.bias - torch.Size([1024]): +The value is the same before and after calling `init_weights` of EncoderDecoder + +backbone.blocks.10.gamma_1 - torch.Size([1024]): +The value is the same before and after calling `init_weights` of EncoderDecoder + +backbone.blocks.10.gamma_2 - torch.Size([1024]): +The value is the same before and after calling `init_weights` of EncoderDecoder + +backbone.blocks.10.norm1.weight - torch.Size([1024]): +The value is the same before and after calling `init_weights` of EncoderDecoder + +backbone.blocks.10.norm1.bias - torch.Size([1024]): +The value is the same before and after calling `init_weights` of EncoderDecoder + +backbone.blocks.10.attn.q_bias - torch.Size([1024]): +The value is the same before and after calling `init_weights` of EncoderDecoder + +backbone.blocks.10.attn.v_bias - torch.Size([1024]): +The value is the same before and after calling `init_weights` of EncoderDecoder + +backbone.blocks.10.attn.relative_position_bias_table - torch.Size([3972, 16]): +The value is the same before and after calling `init_weights` of EncoderDecoder + +backbone.blocks.10.attn.qkv.weight - torch.Size([3072, 1024]): +The value is the same before and after calling `init_weights` of EncoderDecoder + +backbone.blocks.10.attn.proj.weight - torch.Size([1024, 1024]): +The value is the same before and after calling `init_weights` of EncoderDecoder + +backbone.blocks.10.attn.proj.bias - torch.Size([1024]): +The value is the same before and after calling `init_weights` of EncoderDecoder + +backbone.blocks.10.norm2.weight - torch.Size([1024]): +The value is the same before and after calling `init_weights` of EncoderDecoder + +backbone.blocks.10.norm2.bias - torch.Size([1024]): +The value is the same before and after calling `init_weights` of EncoderDecoder + +backbone.blocks.10.mlp.fc1.weight - torch.Size([4096, 1024]): +The value is the same before and after calling `init_weights` of EncoderDecoder + +backbone.blocks.10.mlp.fc1.bias - torch.Size([4096]): +The value is the same before and after calling `init_weights` of EncoderDecoder + +backbone.blocks.10.mlp.fc2.weight - torch.Size([1024, 4096]): +The value is the same before and after calling `init_weights` of EncoderDecoder + +backbone.blocks.10.mlp.fc2.bias - torch.Size([1024]): +The value is the same before and after calling `init_weights` of EncoderDecoder + +backbone.blocks.11.gamma_1 - torch.Size([1024]): +The value is the same before and after calling `init_weights` of EncoderDecoder + +backbone.blocks.11.gamma_2 - torch.Size([1024]): +The value is the same before and after calling `init_weights` of EncoderDecoder + +backbone.blocks.11.norm1.weight - torch.Size([1024]): +The value is the same before and after calling `init_weights` of EncoderDecoder + +backbone.blocks.11.norm1.bias - torch.Size([1024]): +The value is the same before and after calling `init_weights` of EncoderDecoder + +backbone.blocks.11.attn.q_bias - torch.Size([1024]): +The value is the same before and after calling `init_weights` of EncoderDecoder + +backbone.blocks.11.attn.v_bias - torch.Size([1024]): +The value is the same before and after calling `init_weights` of EncoderDecoder + +backbone.blocks.11.attn.relative_position_bias_table - torch.Size([3972, 16]): +The value is the same before and after calling `init_weights` of EncoderDecoder + +backbone.blocks.11.attn.qkv.weight - torch.Size([3072, 1024]): +The value is the same before and after calling `init_weights` of EncoderDecoder + +backbone.blocks.11.attn.proj.weight - torch.Size([1024, 1024]): +The value is the same before and after calling `init_weights` of EncoderDecoder + +backbone.blocks.11.attn.proj.bias - torch.Size([1024]): +The value is the same before and after calling `init_weights` of EncoderDecoder + +backbone.blocks.11.norm2.weight - torch.Size([1024]): +The value is the same before and after calling `init_weights` of EncoderDecoder + +backbone.blocks.11.norm2.bias - torch.Size([1024]): +The value is the same before and after calling `init_weights` of EncoderDecoder + +backbone.blocks.11.mlp.fc1.weight - torch.Size([4096, 1024]): +The value is the same before and after calling `init_weights` of EncoderDecoder + +backbone.blocks.11.mlp.fc1.bias - torch.Size([4096]): +The value is the same before and after calling `init_weights` of EncoderDecoder + +backbone.blocks.11.mlp.fc2.weight - torch.Size([1024, 4096]): +The value is the same before and after calling `init_weights` of EncoderDecoder + +backbone.blocks.11.mlp.fc2.bias - torch.Size([1024]): +The value is the same before and after calling `init_weights` of EncoderDecoder + +backbone.blocks.12.gamma_1 - torch.Size([1024]): +The value is the same before and after calling `init_weights` of EncoderDecoder + +backbone.blocks.12.gamma_2 - torch.Size([1024]): +The value is the same before and after calling `init_weights` of EncoderDecoder + +backbone.blocks.12.norm1.weight - torch.Size([1024]): +The value is the same before and after calling `init_weights` of EncoderDecoder + +backbone.blocks.12.norm1.bias - torch.Size([1024]): +The value is the same before and after calling `init_weights` of EncoderDecoder + +backbone.blocks.12.attn.q_bias - torch.Size([1024]): +The value is the same before and after calling `init_weights` of EncoderDecoder + +backbone.blocks.12.attn.v_bias - torch.Size([1024]): +The value is the same before and after calling `init_weights` of EncoderDecoder + +backbone.blocks.12.attn.relative_position_bias_table - torch.Size([3972, 16]): +The value is the same before and after calling `init_weights` of EncoderDecoder + +backbone.blocks.12.attn.qkv.weight - torch.Size([3072, 1024]): +The value is the same before and after calling `init_weights` of EncoderDecoder + +backbone.blocks.12.attn.proj.weight - torch.Size([1024, 1024]): +The value is the same before and after calling `init_weights` of EncoderDecoder + +backbone.blocks.12.attn.proj.bias - torch.Size([1024]): +The value is the same before and after calling `init_weights` of EncoderDecoder + +backbone.blocks.12.norm2.weight - torch.Size([1024]): +The value is the same before and after calling `init_weights` of EncoderDecoder + +backbone.blocks.12.norm2.bias - torch.Size([1024]): +The value is the same before and after calling `init_weights` of EncoderDecoder + +backbone.blocks.12.mlp.fc1.weight - torch.Size([4096, 1024]): +The value is the same before and after calling `init_weights` of EncoderDecoder + +backbone.blocks.12.mlp.fc1.bias - torch.Size([4096]): +The value is the same before and after calling `init_weights` of EncoderDecoder + +backbone.blocks.12.mlp.fc2.weight - torch.Size([1024, 4096]): +The value is the same before and after calling `init_weights` of EncoderDecoder + +backbone.blocks.12.mlp.fc2.bias - torch.Size([1024]): +The value is the same before and after calling `init_weights` of EncoderDecoder + +backbone.blocks.13.gamma_1 - torch.Size([1024]): +The value is the same before and after calling `init_weights` of EncoderDecoder + +backbone.blocks.13.gamma_2 - torch.Size([1024]): +The value is the same before and after calling `init_weights` of EncoderDecoder + +backbone.blocks.13.norm1.weight - torch.Size([1024]): +The value is the same before and after calling `init_weights` of EncoderDecoder + +backbone.blocks.13.norm1.bias - torch.Size([1024]): +The value is the same before and after calling `init_weights` of EncoderDecoder + +backbone.blocks.13.attn.q_bias - torch.Size([1024]): +The value is the same before and after calling `init_weights` of EncoderDecoder + +backbone.blocks.13.attn.v_bias - torch.Size([1024]): +The value is the same before and after calling `init_weights` of EncoderDecoder + +backbone.blocks.13.attn.relative_position_bias_table - torch.Size([3972, 16]): +The value is the same before and after calling `init_weights` of EncoderDecoder + +backbone.blocks.13.attn.qkv.weight - torch.Size([3072, 1024]): +The value is the same before and after calling `init_weights` of EncoderDecoder + +backbone.blocks.13.attn.proj.weight - torch.Size([1024, 1024]): +The value is the same before and after calling `init_weights` of EncoderDecoder + +backbone.blocks.13.attn.proj.bias - torch.Size([1024]): +The value is the same before and after calling `init_weights` of EncoderDecoder + +backbone.blocks.13.norm2.weight - torch.Size([1024]): +The value is the same before and after calling `init_weights` of EncoderDecoder + +backbone.blocks.13.norm2.bias - torch.Size([1024]): +The value is the same before and after calling `init_weights` of EncoderDecoder + +backbone.blocks.13.mlp.fc1.weight - torch.Size([4096, 1024]): +The value is the same before and after calling `init_weights` of EncoderDecoder + +backbone.blocks.13.mlp.fc1.bias - torch.Size([4096]): +The value is the same before and after calling `init_weights` of EncoderDecoder + +backbone.blocks.13.mlp.fc2.weight - torch.Size([1024, 4096]): +The value is the same before and after calling `init_weights` of EncoderDecoder + +backbone.blocks.13.mlp.fc2.bias - torch.Size([1024]): +The value is the same before and after calling `init_weights` of EncoderDecoder + +backbone.blocks.14.gamma_1 - torch.Size([1024]): +The value is the same before and after calling `init_weights` of EncoderDecoder + +backbone.blocks.14.gamma_2 - torch.Size([1024]): +The value is the same before and after calling `init_weights` of EncoderDecoder + +backbone.blocks.14.norm1.weight - torch.Size([1024]): +The value is the same before and after calling `init_weights` of EncoderDecoder + +backbone.blocks.14.norm1.bias - torch.Size([1024]): +The value is the same before and after calling `init_weights` of EncoderDecoder + +backbone.blocks.14.attn.q_bias - torch.Size([1024]): +The value is the same before and after calling `init_weights` of EncoderDecoder + +backbone.blocks.14.attn.v_bias - torch.Size([1024]): +The value is the same before and after calling `init_weights` of EncoderDecoder + +backbone.blocks.14.attn.relative_position_bias_table - torch.Size([3972, 16]): +The value is the same before and after calling `init_weights` of EncoderDecoder + +backbone.blocks.14.attn.qkv.weight - torch.Size([3072, 1024]): +The value is the same before and after calling `init_weights` of EncoderDecoder + +backbone.blocks.14.attn.proj.weight - torch.Size([1024, 1024]): +The value is the same before and after calling `init_weights` of EncoderDecoder + +backbone.blocks.14.attn.proj.bias - torch.Size([1024]): +The value is the same before and after calling `init_weights` of EncoderDecoder + +backbone.blocks.14.norm2.weight - torch.Size([1024]): +The value is the same before and after calling `init_weights` of EncoderDecoder + +backbone.blocks.14.norm2.bias - torch.Size([1024]): +The value is the same before and after calling `init_weights` of EncoderDecoder + +backbone.blocks.14.mlp.fc1.weight - torch.Size([4096, 1024]): +The value is the same before and after calling `init_weights` of EncoderDecoder + +backbone.blocks.14.mlp.fc1.bias - torch.Size([4096]): +The value is the same before and after calling `init_weights` of EncoderDecoder + +backbone.blocks.14.mlp.fc2.weight - torch.Size([1024, 4096]): +The value is the same before and after calling `init_weights` of EncoderDecoder + +backbone.blocks.14.mlp.fc2.bias - torch.Size([1024]): +The value is the same before and after calling `init_weights` of EncoderDecoder + +backbone.blocks.15.gamma_1 - torch.Size([1024]): +The value is the same before and after calling `init_weights` of EncoderDecoder + +backbone.blocks.15.gamma_2 - torch.Size([1024]): +The value is the same before and after calling `init_weights` of EncoderDecoder + +backbone.blocks.15.norm1.weight - torch.Size([1024]): +The value is the same before and after calling `init_weights` of EncoderDecoder + +backbone.blocks.15.norm1.bias - torch.Size([1024]): +The value is the same before and after calling `init_weights` of EncoderDecoder + +backbone.blocks.15.attn.q_bias - torch.Size([1024]): +The value is the same before and after calling `init_weights` of EncoderDecoder + +backbone.blocks.15.attn.v_bias - torch.Size([1024]): +The value is the same before and after calling `init_weights` of EncoderDecoder + +backbone.blocks.15.attn.relative_position_bias_table - torch.Size([3972, 16]): +The value is the same before and after calling `init_weights` of EncoderDecoder + +backbone.blocks.15.attn.qkv.weight - torch.Size([3072, 1024]): +The value is the same before and after calling `init_weights` of EncoderDecoder + +backbone.blocks.15.attn.proj.weight - torch.Size([1024, 1024]): +The value is the same before and after calling `init_weights` of EncoderDecoder + +backbone.blocks.15.attn.proj.bias - torch.Size([1024]): +The value is the same before and after calling `init_weights` of EncoderDecoder + +backbone.blocks.15.norm2.weight - torch.Size([1024]): +The value is the same before and after calling `init_weights` of EncoderDecoder + +backbone.blocks.15.norm2.bias - torch.Size([1024]): +The value is the same before and after calling `init_weights` of EncoderDecoder + +backbone.blocks.15.mlp.fc1.weight - torch.Size([4096, 1024]): +The value is the same before and after calling `init_weights` of EncoderDecoder + +backbone.blocks.15.mlp.fc1.bias - torch.Size([4096]): +The value is the same before and after calling `init_weights` of EncoderDecoder + +backbone.blocks.15.mlp.fc2.weight - torch.Size([1024, 4096]): +The value is the same before and after calling `init_weights` of EncoderDecoder + +backbone.blocks.15.mlp.fc2.bias - torch.Size([1024]): +The value is the same before and after calling `init_weights` of EncoderDecoder + +backbone.blocks.16.gamma_1 - torch.Size([1024]): +The value is the same before and after calling `init_weights` of EncoderDecoder + +backbone.blocks.16.gamma_2 - torch.Size([1024]): +The value is the same before and after calling `init_weights` of EncoderDecoder + +backbone.blocks.16.norm1.weight - torch.Size([1024]): +The value is the same before and after calling `init_weights` of EncoderDecoder + +backbone.blocks.16.norm1.bias - torch.Size([1024]): +The value is the same before and after calling `init_weights` of EncoderDecoder + +backbone.blocks.16.attn.q_bias - torch.Size([1024]): +The value is the same before and after calling `init_weights` of EncoderDecoder + +backbone.blocks.16.attn.v_bias - torch.Size([1024]): +The value is the same before and after calling `init_weights` of EncoderDecoder + +backbone.blocks.16.attn.relative_position_bias_table - torch.Size([3972, 16]): +The value is the same before and after calling `init_weights` of EncoderDecoder + +backbone.blocks.16.attn.qkv.weight - torch.Size([3072, 1024]): +The value is the same before and after calling `init_weights` of EncoderDecoder + +backbone.blocks.16.attn.proj.weight - torch.Size([1024, 1024]): +The value is the same before and after calling `init_weights` of EncoderDecoder + +backbone.blocks.16.attn.proj.bias - torch.Size([1024]): +The value is the same before and after calling `init_weights` of EncoderDecoder + +backbone.blocks.16.norm2.weight - torch.Size([1024]): +The value is the same before and after calling `init_weights` of EncoderDecoder + +backbone.blocks.16.norm2.bias - torch.Size([1024]): +The value is the same before and after calling `init_weights` of EncoderDecoder + +backbone.blocks.16.mlp.fc1.weight - torch.Size([4096, 1024]): +The value is the same before and after calling `init_weights` of EncoderDecoder + +backbone.blocks.16.mlp.fc1.bias - torch.Size([4096]): +The value is the same before and after calling `init_weights` of EncoderDecoder + +backbone.blocks.16.mlp.fc2.weight - torch.Size([1024, 4096]): +The value is the same before and after calling `init_weights` of EncoderDecoder + +backbone.blocks.16.mlp.fc2.bias - torch.Size([1024]): +The value is the same before and after calling `init_weights` of EncoderDecoder + +backbone.blocks.17.gamma_1 - torch.Size([1024]): +The value is the same before and after calling `init_weights` of EncoderDecoder + +backbone.blocks.17.gamma_2 - torch.Size([1024]): +The value is the same before and after calling `init_weights` of EncoderDecoder + +backbone.blocks.17.norm1.weight - torch.Size([1024]): +The value is the same before and after calling `init_weights` of EncoderDecoder + +backbone.blocks.17.norm1.bias - torch.Size([1024]): +The value is the same before and after calling `init_weights` of EncoderDecoder + +backbone.blocks.17.attn.q_bias - torch.Size([1024]): +The value is the same before and after calling `init_weights` of EncoderDecoder + +backbone.blocks.17.attn.v_bias - torch.Size([1024]): +The value is the same before and after calling `init_weights` of EncoderDecoder + +backbone.blocks.17.attn.relative_position_bias_table - torch.Size([3972, 16]): +The value is the same before and after calling `init_weights` of EncoderDecoder + +backbone.blocks.17.attn.qkv.weight - torch.Size([3072, 1024]): +The value is the same before and after calling `init_weights` of EncoderDecoder + +backbone.blocks.17.attn.proj.weight - torch.Size([1024, 1024]): +The value is the same before and after calling `init_weights` of EncoderDecoder + +backbone.blocks.17.attn.proj.bias - torch.Size([1024]): +The value is the same before and after calling `init_weights` of EncoderDecoder + +backbone.blocks.17.norm2.weight - torch.Size([1024]): +The value is the same before and after calling `init_weights` of EncoderDecoder + +backbone.blocks.17.norm2.bias - torch.Size([1024]): +The value is the same before and after calling `init_weights` of EncoderDecoder + +backbone.blocks.17.mlp.fc1.weight - torch.Size([4096, 1024]): +The value is the same before and after calling `init_weights` of EncoderDecoder + +backbone.blocks.17.mlp.fc1.bias - torch.Size([4096]): +The value is the same before and after calling `init_weights` of EncoderDecoder + +backbone.blocks.17.mlp.fc2.weight - torch.Size([1024, 4096]): +The value is the same before and after calling `init_weights` of EncoderDecoder + +backbone.blocks.17.mlp.fc2.bias - torch.Size([1024]): +The value is the same before and after calling `init_weights` of EncoderDecoder + +backbone.blocks.18.gamma_1 - torch.Size([1024]): +The value is the same before and after calling `init_weights` of EncoderDecoder + +backbone.blocks.18.gamma_2 - torch.Size([1024]): +The value is the same before and after calling `init_weights` of EncoderDecoder + +backbone.blocks.18.norm1.weight - torch.Size([1024]): +The value is the same before and after calling `init_weights` of EncoderDecoder + +backbone.blocks.18.norm1.bias - torch.Size([1024]): +The value is the same before and after calling `init_weights` of EncoderDecoder + +backbone.blocks.18.attn.q_bias - torch.Size([1024]): +The value is the same before and after calling `init_weights` of EncoderDecoder + +backbone.blocks.18.attn.v_bias - torch.Size([1024]): +The value is the same before and after calling `init_weights` of EncoderDecoder + +backbone.blocks.18.attn.relative_position_bias_table - torch.Size([3972, 16]): +The value is the same before and after calling `init_weights` of EncoderDecoder + +backbone.blocks.18.attn.qkv.weight - torch.Size([3072, 1024]): +The value is the same before and after calling `init_weights` of EncoderDecoder + +backbone.blocks.18.attn.proj.weight - torch.Size([1024, 1024]): +The value is the same before and after calling `init_weights` of EncoderDecoder + +backbone.blocks.18.attn.proj.bias - torch.Size([1024]): +The value is the same before and after calling `init_weights` of EncoderDecoder + +backbone.blocks.18.norm2.weight - torch.Size([1024]): +The value is the same before and after calling `init_weights` of EncoderDecoder + +backbone.blocks.18.norm2.bias - torch.Size([1024]): +The value is the same before and after calling `init_weights` of EncoderDecoder + +backbone.blocks.18.mlp.fc1.weight - torch.Size([4096, 1024]): +The value is the same before and after calling `init_weights` of EncoderDecoder + +backbone.blocks.18.mlp.fc1.bias - torch.Size([4096]): +The value is the same before and after calling `init_weights` of EncoderDecoder + +backbone.blocks.18.mlp.fc2.weight - torch.Size([1024, 4096]): +The value is the same before and after calling `init_weights` of EncoderDecoder + +backbone.blocks.18.mlp.fc2.bias - torch.Size([1024]): +The value is the same before and after calling `init_weights` of EncoderDecoder + +backbone.blocks.19.gamma_1 - torch.Size([1024]): +The value is the same before and after calling `init_weights` of EncoderDecoder + +backbone.blocks.19.gamma_2 - torch.Size([1024]): +The value is the same before and after calling `init_weights` of EncoderDecoder + +backbone.blocks.19.norm1.weight - torch.Size([1024]): +The value is the same before and after calling `init_weights` of EncoderDecoder + +backbone.blocks.19.norm1.bias - torch.Size([1024]): +The value is the same before and after calling `init_weights` of EncoderDecoder + +backbone.blocks.19.attn.q_bias - torch.Size([1024]): +The value is the same before and after calling `init_weights` of EncoderDecoder + +backbone.blocks.19.attn.v_bias - torch.Size([1024]): +The value is the same before and after calling `init_weights` of EncoderDecoder + +backbone.blocks.19.attn.relative_position_bias_table - torch.Size([3972, 16]): +The value is the same before and after calling `init_weights` of EncoderDecoder + +backbone.blocks.19.attn.qkv.weight - torch.Size([3072, 1024]): +The value is the same before and after calling `init_weights` of EncoderDecoder + +backbone.blocks.19.attn.proj.weight - torch.Size([1024, 1024]): +The value is the same before and after calling `init_weights` of EncoderDecoder + +backbone.blocks.19.attn.proj.bias - torch.Size([1024]): +The value is the same before and after calling `init_weights` of EncoderDecoder + +backbone.blocks.19.norm2.weight - torch.Size([1024]): +The value is the same before and after calling `init_weights` of EncoderDecoder + +backbone.blocks.19.norm2.bias - torch.Size([1024]): +The value is the same before and after calling `init_weights` of EncoderDecoder + +backbone.blocks.19.mlp.fc1.weight - torch.Size([4096, 1024]): +The value is the same before and after calling `init_weights` of EncoderDecoder + +backbone.blocks.19.mlp.fc1.bias - torch.Size([4096]): +The value is the same before and after calling `init_weights` of EncoderDecoder + +backbone.blocks.19.mlp.fc2.weight - torch.Size([1024, 4096]): +The value is the same before and after calling `init_weights` of EncoderDecoder + +backbone.blocks.19.mlp.fc2.bias - torch.Size([1024]): +The value is the same before and after calling `init_weights` of EncoderDecoder + +backbone.blocks.20.gamma_1 - torch.Size([1024]): +The value is the same before and after calling `init_weights` of EncoderDecoder + +backbone.blocks.20.gamma_2 - torch.Size([1024]): +The value is the same before and after calling `init_weights` of EncoderDecoder + +backbone.blocks.20.norm1.weight - torch.Size([1024]): +The value is the same before and after calling `init_weights` of EncoderDecoder + +backbone.blocks.20.norm1.bias - torch.Size([1024]): +The value is the same before and after calling `init_weights` of EncoderDecoder + +backbone.blocks.20.attn.q_bias - torch.Size([1024]): +The value is the same before and after calling `init_weights` of EncoderDecoder + +backbone.blocks.20.attn.v_bias - torch.Size([1024]): +The value is the same before and after calling `init_weights` of EncoderDecoder + +backbone.blocks.20.attn.relative_position_bias_table - torch.Size([3972, 16]): +The value is the same before and after calling `init_weights` of EncoderDecoder + +backbone.blocks.20.attn.qkv.weight - torch.Size([3072, 1024]): +The value is the same before and after calling `init_weights` of EncoderDecoder + +backbone.blocks.20.attn.proj.weight - torch.Size([1024, 1024]): +The value is the same before and after calling `init_weights` of EncoderDecoder + +backbone.blocks.20.attn.proj.bias - torch.Size([1024]): +The value is the same before and after calling `init_weights` of EncoderDecoder + +backbone.blocks.20.norm2.weight - torch.Size([1024]): +The value is the same before and after calling `init_weights` of EncoderDecoder + +backbone.blocks.20.norm2.bias - torch.Size([1024]): +The value is the same before and after calling `init_weights` of EncoderDecoder + +backbone.blocks.20.mlp.fc1.weight - torch.Size([4096, 1024]): +The value is the same before and after calling `init_weights` of EncoderDecoder + +backbone.blocks.20.mlp.fc1.bias - torch.Size([4096]): +The value is the same before and after calling `init_weights` of EncoderDecoder + +backbone.blocks.20.mlp.fc2.weight - torch.Size([1024, 4096]): +The value is the same before and after calling `init_weights` of EncoderDecoder + +backbone.blocks.20.mlp.fc2.bias - torch.Size([1024]): +The value is the same before and after calling `init_weights` of EncoderDecoder + +backbone.blocks.21.gamma_1 - torch.Size([1024]): +The value is the same before and after calling `init_weights` of EncoderDecoder + +backbone.blocks.21.gamma_2 - torch.Size([1024]): +The value is the same before and after calling `init_weights` of EncoderDecoder + +backbone.blocks.21.norm1.weight - torch.Size([1024]): +The value is the same before and after calling `init_weights` of EncoderDecoder + +backbone.blocks.21.norm1.bias - torch.Size([1024]): +The value is the same before and after calling `init_weights` of EncoderDecoder + +backbone.blocks.21.attn.q_bias - torch.Size([1024]): +The value is the same before and after calling `init_weights` of EncoderDecoder + +backbone.blocks.21.attn.v_bias - torch.Size([1024]): +The value is the same before and after calling `init_weights` of EncoderDecoder + +backbone.blocks.21.attn.relative_position_bias_table - torch.Size([3972, 16]): +The value is the same before and after calling `init_weights` of EncoderDecoder + +backbone.blocks.21.attn.qkv.weight - torch.Size([3072, 1024]): +The value is the same before and after calling `init_weights` of EncoderDecoder + +backbone.blocks.21.attn.proj.weight - torch.Size([1024, 1024]): +The value is the same before and after calling `init_weights` of EncoderDecoder + +backbone.blocks.21.attn.proj.bias - torch.Size([1024]): +The value is the same before and after calling `init_weights` of EncoderDecoder + +backbone.blocks.21.norm2.weight - torch.Size([1024]): +The value is the same before and after calling `init_weights` of EncoderDecoder + +backbone.blocks.21.norm2.bias - torch.Size([1024]): +The value is the same before and after calling `init_weights` of EncoderDecoder + +backbone.blocks.21.mlp.fc1.weight - torch.Size([4096, 1024]): +The value is the same before and after calling `init_weights` of EncoderDecoder + +backbone.blocks.21.mlp.fc1.bias - torch.Size([4096]): +The value is the same before and after calling `init_weights` of EncoderDecoder + +backbone.blocks.21.mlp.fc2.weight - torch.Size([1024, 4096]): +The value is the same before and after calling `init_weights` of EncoderDecoder + +backbone.blocks.21.mlp.fc2.bias - torch.Size([1024]): +The value is the same before and after calling `init_weights` of EncoderDecoder + +backbone.blocks.22.gamma_1 - torch.Size([1024]): +The value is the same before and after calling `init_weights` of EncoderDecoder + +backbone.blocks.22.gamma_2 - torch.Size([1024]): +The value is the same before and after calling `init_weights` of EncoderDecoder + +backbone.blocks.22.norm1.weight - torch.Size([1024]): +The value is the same before and after calling `init_weights` of EncoderDecoder + +backbone.blocks.22.norm1.bias - torch.Size([1024]): +The value is the same before and after calling `init_weights` of EncoderDecoder + +backbone.blocks.22.attn.q_bias - torch.Size([1024]): +The value is the same before and after calling `init_weights` of EncoderDecoder + +backbone.blocks.22.attn.v_bias - torch.Size([1024]): +The value is the same before and after calling `init_weights` of EncoderDecoder + +backbone.blocks.22.attn.relative_position_bias_table - torch.Size([3972, 16]): +The value is the same before and after calling `init_weights` of EncoderDecoder + +backbone.blocks.22.attn.qkv.weight - torch.Size([3072, 1024]): +The value is the same before and after calling `init_weights` of EncoderDecoder + +backbone.blocks.22.attn.proj.weight - torch.Size([1024, 1024]): +The value is the same before and after calling `init_weights` of EncoderDecoder + +backbone.blocks.22.attn.proj.bias - torch.Size([1024]): +The value is the same before and after calling `init_weights` of EncoderDecoder + +backbone.blocks.22.norm2.weight - torch.Size([1024]): +The value is the same before and after calling `init_weights` of EncoderDecoder + +backbone.blocks.22.norm2.bias - torch.Size([1024]): +The value is the same before and after calling `init_weights` of EncoderDecoder + +backbone.blocks.22.mlp.fc1.weight - torch.Size([4096, 1024]): +The value is the same before and after calling `init_weights` of EncoderDecoder + +backbone.blocks.22.mlp.fc1.bias - torch.Size([4096]): +The value is the same before and after calling `init_weights` of EncoderDecoder + +backbone.blocks.22.mlp.fc2.weight - torch.Size([1024, 4096]): +The value is the same before and after calling `init_weights` of EncoderDecoder + +backbone.blocks.22.mlp.fc2.bias - torch.Size([1024]): +The value is the same before and after calling `init_weights` of EncoderDecoder + +backbone.blocks.23.gamma_1 - torch.Size([1024]): +The value is the same before and after calling `init_weights` of EncoderDecoder + +backbone.blocks.23.gamma_2 - torch.Size([1024]): +The value is the same before and after calling `init_weights` of EncoderDecoder + +backbone.blocks.23.norm1.weight - torch.Size([1024]): +The value is the same before and after calling `init_weights` of EncoderDecoder + +backbone.blocks.23.norm1.bias - torch.Size([1024]): +The value is the same before and after calling `init_weights` of EncoderDecoder + +backbone.blocks.23.attn.q_bias - torch.Size([1024]): +The value is the same before and after calling `init_weights` of EncoderDecoder + +backbone.blocks.23.attn.v_bias - torch.Size([1024]): +The value is the same before and after calling `init_weights` of EncoderDecoder + +backbone.blocks.23.attn.relative_position_bias_table - torch.Size([3972, 16]): +The value is the same before and after calling `init_weights` of EncoderDecoder + +backbone.blocks.23.attn.qkv.weight - torch.Size([3072, 1024]): +The value is the same before and after calling `init_weights` of EncoderDecoder + +backbone.blocks.23.attn.proj.weight - torch.Size([1024, 1024]): +The value is the same before and after calling `init_weights` of EncoderDecoder + +backbone.blocks.23.attn.proj.bias - torch.Size([1024]): +The value is the same before and after calling `init_weights` of EncoderDecoder + +backbone.blocks.23.norm2.weight - torch.Size([1024]): +The value is the same before and after calling `init_weights` of EncoderDecoder + +backbone.blocks.23.norm2.bias - torch.Size([1024]): +The value is the same before and after calling `init_weights` of EncoderDecoder + +backbone.blocks.23.mlp.fc1.weight - torch.Size([4096, 1024]): +The value is the same before and after calling `init_weights` of EncoderDecoder + +backbone.blocks.23.mlp.fc1.bias - torch.Size([4096]): +The value is the same before and after calling `init_weights` of EncoderDecoder + +backbone.blocks.23.mlp.fc2.weight - torch.Size([1024, 4096]): +The value is the same before and after calling `init_weights` of EncoderDecoder + +backbone.blocks.23.mlp.fc2.bias - torch.Size([1024]): +The value is the same before and after calling `init_weights` of EncoderDecoder + +backbone.conv_branch.stem.0.weight - torch.Size([64, 3, 3, 3]): +The value is the same before and after calling `init_weights` of EncoderDecoder + +backbone.conv_branch.stem.1.weight - torch.Size([64]): +The value is the same before and after calling `init_weights` of EncoderDecoder + +backbone.conv_branch.stem.1.bias - torch.Size([64]): +The value is the same before and after calling `init_weights` of EncoderDecoder + +backbone.conv_branch.stem.3.weight - torch.Size([64, 64, 3, 3]): +The value is the same before and after calling `init_weights` of EncoderDecoder + +backbone.conv_branch.stem.4.weight - torch.Size([64]): +The value is the same before and after calling `init_weights` of EncoderDecoder + +backbone.conv_branch.stem.4.bias - torch.Size([64]): +The value is the same before and after calling `init_weights` of EncoderDecoder + +backbone.conv_branch.stem.6.weight - torch.Size([64, 64, 3, 3]): +The value is the same before and after calling `init_weights` of EncoderDecoder + +backbone.conv_branch.stem.7.weight - torch.Size([64]): +The value is the same before and after calling `init_weights` of EncoderDecoder + +backbone.conv_branch.stem.7.bias - torch.Size([64]): +The value is the same before and after calling `init_weights` of EncoderDecoder + +backbone.conv_branch.conv2.0.weight - torch.Size([128, 64, 3, 3]): +The value is the same before and after calling `init_weights` of EncoderDecoder + +backbone.conv_branch.conv2.1.weight - torch.Size([128]): +The value is the same before and after calling `init_weights` of EncoderDecoder + +backbone.conv_branch.conv2.1.bias - torch.Size([128]): +The value is the same before and after calling `init_weights` of EncoderDecoder + +backbone.conv_branch.conv3.0.weight - torch.Size([256, 128, 3, 3]): +The value is the same before and after calling `init_weights` of EncoderDecoder + +backbone.conv_branch.conv3.1.weight - torch.Size([256]): +The value is the same before and after calling `init_weights` of EncoderDecoder + +backbone.conv_branch.conv3.1.bias - torch.Size([256]): +The value is the same before and after calling `init_weights` of EncoderDecoder + +backbone.conv_branch.conv4.0.weight - torch.Size([256, 256, 3, 3]): +The value is the same before and after calling `init_weights` of EncoderDecoder + +backbone.conv_branch.conv4.1.weight - torch.Size([256]): +The value is the same before and after calling `init_weights` of EncoderDecoder + +backbone.conv_branch.conv4.1.bias - torch.Size([256]): +The value is the same before and after calling `init_weights` of EncoderDecoder + +backbone.conv_branch.fc1.weight - torch.Size([1024, 64, 1, 1]): +The value is the same before and after calling `init_weights` of EncoderDecoder + +backbone.conv_branch.fc1.bias - torch.Size([1024]): +The value is the same before and after calling `init_weights` of EncoderDecoder + +backbone.conv_branch.fc2.weight - torch.Size([1024, 128, 1, 1]): +The value is the same before and after calling `init_weights` of EncoderDecoder + +backbone.conv_branch.fc2.bias - torch.Size([1024]): +The value is the same before and after calling `init_weights` of EncoderDecoder + +backbone.conv_branch.fc3.weight - torch.Size([1024, 256, 1, 1]): +The value is the same before and after calling `init_weights` of EncoderDecoder + +backbone.conv_branch.fc3.bias - torch.Size([1024]): +The value is the same before and after calling `init_weights` of EncoderDecoder + +backbone.conv_branch.fc4.weight - torch.Size([1024, 256, 1, 1]): +The value is the same before and after calling `init_weights` of EncoderDecoder + +backbone.conv_branch.fc4.bias - torch.Size([1024]): +The value is the same before and after calling `init_weights` of EncoderDecoder + +backbone.interact_blocks.0.extract.query_norm.weight - torch.Size([1024]): +The value is the same before and after calling `init_weights` of EncoderDecoder + +backbone.interact_blocks.0.extract.query_norm.bias - torch.Size([1024]): +The value is the same before and after calling `init_weights` of EncoderDecoder + +backbone.interact_blocks.0.extract.feat_norm.weight - torch.Size([1024]): +The value is the same before and after calling `init_weights` of EncoderDecoder + +backbone.interact_blocks.0.extract.feat_norm.bias - torch.Size([1024]): +The value is the same before and after calling `init_weights` of EncoderDecoder + +backbone.interact_blocks.0.extract.attn.sampling_offsets.weight - torch.Size([128, 1024]): +The value is the same before and after calling `init_weights` of EncoderDecoder + +backbone.interact_blocks.0.extract.attn.sampling_offsets.bias - torch.Size([128]): +The value is the same before and after calling `init_weights` of EncoderDecoder + +backbone.interact_blocks.0.extract.attn.attention_weights.weight - torch.Size([64, 1024]): +The value is the same before and after calling `init_weights` of EncoderDecoder + +backbone.interact_blocks.0.extract.attn.attention_weights.bias - torch.Size([64]): +The value is the same before and after calling `init_weights` of EncoderDecoder + +backbone.interact_blocks.0.extract.attn.value_proj.weight - torch.Size([512, 1024]): +The value is the same before and after calling `init_weights` of EncoderDecoder + +backbone.interact_blocks.0.extract.attn.value_proj.bias - torch.Size([512]): +The value is the same before and after calling `init_weights` of EncoderDecoder + +backbone.interact_blocks.0.extract.attn.output_proj.weight - torch.Size([1024, 512]): +The value is the same before and after calling `init_weights` of EncoderDecoder + +backbone.interact_blocks.0.extract.attn.output_proj.bias - torch.Size([1024]): +The value is the same before and after calling `init_weights` of EncoderDecoder + +backbone.interact_blocks.0.insert.gamma - torch.Size([1024]): +The value is the same before and after calling `init_weights` of EncoderDecoder + +backbone.interact_blocks.0.insert.query_norm.weight - torch.Size([1024]): +The value is the same before and after calling `init_weights` of EncoderDecoder + +backbone.interact_blocks.0.insert.query_norm.bias - torch.Size([1024]): +The value is the same before and after calling `init_weights` of EncoderDecoder + +backbone.interact_blocks.0.insert.feat_norm.weight - torch.Size([1024]): +The value is the same before and after calling `init_weights` of EncoderDecoder + +backbone.interact_blocks.0.insert.feat_norm.bias - torch.Size([1024]): +The value is the same before and after calling `init_weights` of EncoderDecoder + +backbone.interact_blocks.0.insert.attn.sampling_offsets.weight - torch.Size([384, 1024]): +The value is the same before and after calling `init_weights` of EncoderDecoder + +backbone.interact_blocks.0.insert.attn.sampling_offsets.bias - torch.Size([384]): +The value is the same before and after calling `init_weights` of EncoderDecoder + +backbone.interact_blocks.0.insert.attn.attention_weights.weight - torch.Size([192, 1024]): +The value is the same before and after calling `init_weights` of EncoderDecoder + +backbone.interact_blocks.0.insert.attn.attention_weights.bias - torch.Size([192]): +The value is the same before and after calling `init_weights` of EncoderDecoder + +backbone.interact_blocks.0.insert.attn.value_proj.weight - torch.Size([512, 1024]): +The value is the same before and after calling `init_weights` of EncoderDecoder + +backbone.interact_blocks.0.insert.attn.value_proj.bias - torch.Size([512]): +The value is the same before and after calling `init_weights` of EncoderDecoder + +backbone.interact_blocks.0.insert.attn.output_proj.weight - torch.Size([1024, 512]): +The value is the same before and after calling `init_weights` of EncoderDecoder + +backbone.interact_blocks.0.insert.attn.output_proj.bias - torch.Size([1024]): +The value is the same before and after calling `init_weights` of EncoderDecoder + +backbone.interact_blocks.0.ffn.fc1.weight - torch.Size([256, 1024]): +The value is the same before and after calling `init_weights` of EncoderDecoder + +backbone.interact_blocks.0.ffn.fc1.bias - torch.Size([256]): +The value is the same before and after calling `init_weights` of EncoderDecoder + +backbone.interact_blocks.0.ffn.dwconv.dwconv.weight - torch.Size([256, 1, 3, 3]): +The value is the same before and after calling `init_weights` of EncoderDecoder + +backbone.interact_blocks.0.ffn.dwconv.dwconv.bias - torch.Size([256]): +The value is the same before and after calling `init_weights` of EncoderDecoder + +backbone.interact_blocks.0.ffn.fc2.weight - torch.Size([1024, 256]): +The value is the same before and after calling `init_weights` of EncoderDecoder + +backbone.interact_blocks.0.ffn.fc2.bias - torch.Size([1024]): +The value is the same before and after calling `init_weights` of EncoderDecoder + +backbone.interact_blocks.0.ffn_norm.weight - torch.Size([1024]): +The value is the same before and after calling `init_weights` of EncoderDecoder + +backbone.interact_blocks.0.ffn_norm.bias - torch.Size([1024]): +The value is the same before and after calling `init_weights` of EncoderDecoder + +backbone.interact_blocks.1.extract.query_norm.weight - torch.Size([1024]): +The value is the same before and after calling `init_weights` of EncoderDecoder + +backbone.interact_blocks.1.extract.query_norm.bias - torch.Size([1024]): +The value is the same before and after calling `init_weights` of EncoderDecoder + +backbone.interact_blocks.1.extract.feat_norm.weight - torch.Size([1024]): +The value is the same before and after calling `init_weights` of EncoderDecoder + +backbone.interact_blocks.1.extract.feat_norm.bias - torch.Size([1024]): +The value is the same before and after calling `init_weights` of EncoderDecoder + +backbone.interact_blocks.1.extract.attn.sampling_offsets.weight - torch.Size([128, 1024]): +The value is the same before and after calling `init_weights` of EncoderDecoder + +backbone.interact_blocks.1.extract.attn.sampling_offsets.bias - torch.Size([128]): +The value is the same before and after calling `init_weights` of EncoderDecoder + +backbone.interact_blocks.1.extract.attn.attention_weights.weight - torch.Size([64, 1024]): +The value is the same before and after calling `init_weights` of EncoderDecoder + +backbone.interact_blocks.1.extract.attn.attention_weights.bias - torch.Size([64]): +The value is the same before and after calling `init_weights` of EncoderDecoder + +backbone.interact_blocks.1.extract.attn.value_proj.weight - torch.Size([512, 1024]): +The value is the same before and after calling `init_weights` of EncoderDecoder + +backbone.interact_blocks.1.extract.attn.value_proj.bias - torch.Size([512]): +The value is the same before and after calling `init_weights` of EncoderDecoder + +backbone.interact_blocks.1.extract.attn.output_proj.weight - torch.Size([1024, 512]): +The value is the same before and after calling `init_weights` of EncoderDecoder + +backbone.interact_blocks.1.extract.attn.output_proj.bias - torch.Size([1024]): +The value is the same before and after calling `init_weights` of EncoderDecoder + +backbone.interact_blocks.1.insert.gamma - torch.Size([1024]): +The value is the same before and after calling `init_weights` of EncoderDecoder + +backbone.interact_blocks.1.insert.query_norm.weight - torch.Size([1024]): +The value is the same before and after calling `init_weights` of EncoderDecoder + +backbone.interact_blocks.1.insert.query_norm.bias - torch.Size([1024]): +The value is the same before and after calling `init_weights` of EncoderDecoder + +backbone.interact_blocks.1.insert.feat_norm.weight - torch.Size([1024]): +The value is the same before and after calling `init_weights` of EncoderDecoder + +backbone.interact_blocks.1.insert.feat_norm.bias - torch.Size([1024]): +The value is the same before and after calling `init_weights` of EncoderDecoder + +backbone.interact_blocks.1.insert.attn.sampling_offsets.weight - torch.Size([384, 1024]): +The value is the same before and after calling `init_weights` of EncoderDecoder + +backbone.interact_blocks.1.insert.attn.sampling_offsets.bias - torch.Size([384]): +The value is the same before and after calling `init_weights` of EncoderDecoder + +backbone.interact_blocks.1.insert.attn.attention_weights.weight - torch.Size([192, 1024]): +The value is the same before and after calling `init_weights` of EncoderDecoder + +backbone.interact_blocks.1.insert.attn.attention_weights.bias - torch.Size([192]): +The value is the same before and after calling `init_weights` of EncoderDecoder + +backbone.interact_blocks.1.insert.attn.value_proj.weight - torch.Size([512, 1024]): +The value is the same before and after calling `init_weights` of EncoderDecoder + +backbone.interact_blocks.1.insert.attn.value_proj.bias - torch.Size([512]): +The value is the same before and after calling `init_weights` of EncoderDecoder + +backbone.interact_blocks.1.insert.attn.output_proj.weight - torch.Size([1024, 512]): +The value is the same before and after calling `init_weights` of EncoderDecoder + +backbone.interact_blocks.1.insert.attn.output_proj.bias - torch.Size([1024]): +The value is the same before and after calling `init_weights` of EncoderDecoder + +backbone.interact_blocks.1.ffn.fc1.weight - torch.Size([256, 1024]): +The value is the same before and after calling `init_weights` of EncoderDecoder + +backbone.interact_blocks.1.ffn.fc1.bias - torch.Size([256]): +The value is the same before and after calling `init_weights` of EncoderDecoder + +backbone.interact_blocks.1.ffn.dwconv.dwconv.weight - torch.Size([256, 1, 3, 3]): +The value is the same before and after calling `init_weights` of EncoderDecoder + +backbone.interact_blocks.1.ffn.dwconv.dwconv.bias - torch.Size([256]): +The value is the same before and after calling `init_weights` of EncoderDecoder + +backbone.interact_blocks.1.ffn.fc2.weight - torch.Size([1024, 256]): +The value is the same before and after calling `init_weights` of EncoderDecoder + +backbone.interact_blocks.1.ffn.fc2.bias - torch.Size([1024]): +The value is the same before and after calling `init_weights` of EncoderDecoder + +backbone.interact_blocks.1.ffn_norm.weight - torch.Size([1024]): +The value is the same before and after calling `init_weights` of EncoderDecoder + +backbone.interact_blocks.1.ffn_norm.bias - torch.Size([1024]): +The value is the same before and after calling `init_weights` of EncoderDecoder + +backbone.interact_blocks.2.extract.query_norm.weight - torch.Size([1024]): +The value is the same before and after calling `init_weights` of EncoderDecoder + +backbone.interact_blocks.2.extract.query_norm.bias - torch.Size([1024]): +The value is the same before and after calling `init_weights` of EncoderDecoder + +backbone.interact_blocks.2.extract.feat_norm.weight - torch.Size([1024]): +The value is the same before and after calling `init_weights` of EncoderDecoder + +backbone.interact_blocks.2.extract.feat_norm.bias - torch.Size([1024]): +The value is the same before and after calling `init_weights` of EncoderDecoder + +backbone.interact_blocks.2.extract.attn.sampling_offsets.weight - torch.Size([128, 1024]): +The value is the same before and after calling `init_weights` of EncoderDecoder + +backbone.interact_blocks.2.extract.attn.sampling_offsets.bias - torch.Size([128]): +The value is the same before and after calling `init_weights` of EncoderDecoder + +backbone.interact_blocks.2.extract.attn.attention_weights.weight - torch.Size([64, 1024]): +The value is the same before and after calling `init_weights` of EncoderDecoder + +backbone.interact_blocks.2.extract.attn.attention_weights.bias - torch.Size([64]): +The value is the same before and after calling `init_weights` of EncoderDecoder + +backbone.interact_blocks.2.extract.attn.value_proj.weight - torch.Size([512, 1024]): +The value is the same before and after calling `init_weights` of EncoderDecoder + +backbone.interact_blocks.2.extract.attn.value_proj.bias - torch.Size([512]): +The value is the same before and after calling `init_weights` of EncoderDecoder + +backbone.interact_blocks.2.extract.attn.output_proj.weight - torch.Size([1024, 512]): +The value is the same before and after calling `init_weights` of EncoderDecoder + +backbone.interact_blocks.2.extract.attn.output_proj.bias - torch.Size([1024]): +The value is the same before and after calling `init_weights` of EncoderDecoder + +backbone.interact_blocks.2.insert.gamma - torch.Size([1024]): +The value is the same before and after calling `init_weights` of EncoderDecoder + +backbone.interact_blocks.2.insert.query_norm.weight - torch.Size([1024]): +The value is the same before and after calling `init_weights` of EncoderDecoder + +backbone.interact_blocks.2.insert.query_norm.bias - torch.Size([1024]): +The value is the same before and after calling `init_weights` of EncoderDecoder + +backbone.interact_blocks.2.insert.feat_norm.weight - torch.Size([1024]): +The value is the same before and after calling `init_weights` of EncoderDecoder + +backbone.interact_blocks.2.insert.feat_norm.bias - torch.Size([1024]): +The value is the same before and after calling `init_weights` of EncoderDecoder + +backbone.interact_blocks.2.insert.attn.sampling_offsets.weight - torch.Size([384, 1024]): +The value is the same before and after calling `init_weights` of EncoderDecoder + +backbone.interact_blocks.2.insert.attn.sampling_offsets.bias - torch.Size([384]): +The value is the same before and after calling `init_weights` of EncoderDecoder + +backbone.interact_blocks.2.insert.attn.attention_weights.weight - torch.Size([192, 1024]): +The value is the same before and after calling `init_weights` of EncoderDecoder + +backbone.interact_blocks.2.insert.attn.attention_weights.bias - torch.Size([192]): +The value is the same before and after calling `init_weights` of EncoderDecoder + +backbone.interact_blocks.2.insert.attn.value_proj.weight - torch.Size([512, 1024]): +The value is the same before and after calling `init_weights` of EncoderDecoder + +backbone.interact_blocks.2.insert.attn.value_proj.bias - torch.Size([512]): +The value is the same before and after calling `init_weights` of EncoderDecoder + +backbone.interact_blocks.2.insert.attn.output_proj.weight - torch.Size([1024, 512]): +The value is the same before and after calling `init_weights` of EncoderDecoder + +backbone.interact_blocks.2.insert.attn.output_proj.bias - torch.Size([1024]): +The value is the same before and after calling `init_weights` of EncoderDecoder + +backbone.interact_blocks.2.ffn.fc1.weight - torch.Size([256, 1024]): +The value is the same before and after calling `init_weights` of EncoderDecoder + +backbone.interact_blocks.2.ffn.fc1.bias - torch.Size([256]): +The value is the same before and after calling `init_weights` of EncoderDecoder + +backbone.interact_blocks.2.ffn.dwconv.dwconv.weight - torch.Size([256, 1, 3, 3]): +The value is the same before and after calling `init_weights` of EncoderDecoder + +backbone.interact_blocks.2.ffn.dwconv.dwconv.bias - torch.Size([256]): +The value is the same before and after calling `init_weights` of EncoderDecoder + +backbone.interact_blocks.2.ffn.fc2.weight - torch.Size([1024, 256]): +The value is the same before and after calling `init_weights` of EncoderDecoder + +backbone.interact_blocks.2.ffn.fc2.bias - torch.Size([1024]): +The value is the same before and after calling `init_weights` of EncoderDecoder + +backbone.interact_blocks.2.ffn_norm.weight - torch.Size([1024]): +The value is the same before and after calling `init_weights` of EncoderDecoder + +backbone.interact_blocks.2.ffn_norm.bias - torch.Size([1024]): +The value is the same before and after calling `init_weights` of EncoderDecoder + +backbone.interact_blocks.3.extract.query_norm.weight - torch.Size([1024]): +The value is the same before and after calling `init_weights` of EncoderDecoder + +backbone.interact_blocks.3.extract.query_norm.bias - torch.Size([1024]): +The value is the same before and after calling `init_weights` of EncoderDecoder + +backbone.interact_blocks.3.extract.feat_norm.weight - torch.Size([1024]): +The value is the same before and after calling `init_weights` of EncoderDecoder + +backbone.interact_blocks.3.extract.feat_norm.bias - torch.Size([1024]): +The value is the same before and after calling `init_weights` of EncoderDecoder + +backbone.interact_blocks.3.extract.attn.sampling_offsets.weight - torch.Size([128, 1024]): +The value is the same before and after calling `init_weights` of EncoderDecoder + +backbone.interact_blocks.3.extract.attn.sampling_offsets.bias - torch.Size([128]): +The value is the same before and after calling `init_weights` of EncoderDecoder + +backbone.interact_blocks.3.extract.attn.attention_weights.weight - torch.Size([64, 1024]): +The value is the same before and after calling `init_weights` of EncoderDecoder + +backbone.interact_blocks.3.extract.attn.attention_weights.bias - torch.Size([64]): +The value is the same before and after calling `init_weights` of EncoderDecoder + +backbone.interact_blocks.3.extract.attn.value_proj.weight - torch.Size([512, 1024]): +The value is the same before and after calling `init_weights` of EncoderDecoder + +backbone.interact_blocks.3.extract.attn.value_proj.bias - torch.Size([512]): +The value is the same before and after calling `init_weights` of EncoderDecoder + +backbone.interact_blocks.3.extract.attn.output_proj.weight - torch.Size([1024, 512]): +The value is the same before and after calling `init_weights` of EncoderDecoder + +backbone.interact_blocks.3.extract.attn.output_proj.bias - torch.Size([1024]): +The value is the same before and after calling `init_weights` of EncoderDecoder + +backbone.interact_blocks.3.insert.gamma - torch.Size([1024]): +The value is the same before and after calling `init_weights` of EncoderDecoder + +backbone.interact_blocks.3.insert.query_norm.weight - torch.Size([1024]): +The value is the same before and after calling `init_weights` of EncoderDecoder + +backbone.interact_blocks.3.insert.query_norm.bias - torch.Size([1024]): +The value is the same before and after calling `init_weights` of EncoderDecoder + +backbone.interact_blocks.3.insert.feat_norm.weight - torch.Size([1024]): +The value is the same before and after calling `init_weights` of EncoderDecoder + +backbone.interact_blocks.3.insert.feat_norm.bias - torch.Size([1024]): +The value is the same before and after calling `init_weights` of EncoderDecoder + +backbone.interact_blocks.3.insert.attn.sampling_offsets.weight - torch.Size([384, 1024]): +The value is the same before and after calling `init_weights` of EncoderDecoder + +backbone.interact_blocks.3.insert.attn.sampling_offsets.bias - torch.Size([384]): +The value is the same before and after calling `init_weights` of EncoderDecoder + +backbone.interact_blocks.3.insert.attn.attention_weights.weight - torch.Size([192, 1024]): +The value is the same before and after calling `init_weights` of EncoderDecoder + +backbone.interact_blocks.3.insert.attn.attention_weights.bias - torch.Size([192]): +The value is the same before and after calling `init_weights` of EncoderDecoder + +backbone.interact_blocks.3.insert.attn.value_proj.weight - torch.Size([512, 1024]): +The value is the same before and after calling `init_weights` of EncoderDecoder + +backbone.interact_blocks.3.insert.attn.value_proj.bias - torch.Size([512]): +The value is the same before and after calling `init_weights` of EncoderDecoder + +backbone.interact_blocks.3.insert.attn.output_proj.weight - torch.Size([1024, 512]): +The value is the same before and after calling `init_weights` of EncoderDecoder + +backbone.interact_blocks.3.insert.attn.output_proj.bias - torch.Size([1024]): +The value is the same before and after calling `init_weights` of EncoderDecoder + +backbone.interact_blocks.3.ffn.fc1.weight - torch.Size([256, 1024]): +The value is the same before and after calling `init_weights` of EncoderDecoder + +backbone.interact_blocks.3.ffn.fc1.bias - torch.Size([256]): +The value is the same before and after calling `init_weights` of EncoderDecoder + +backbone.interact_blocks.3.ffn.dwconv.dwconv.weight - torch.Size([256, 1, 3, 3]): +The value is the same before and after calling `init_weights` of EncoderDecoder + +backbone.interact_blocks.3.ffn.dwconv.dwconv.bias - torch.Size([256]): +The value is the same before and after calling `init_weights` of EncoderDecoder + +backbone.interact_blocks.3.ffn.fc2.weight - torch.Size([1024, 256]): +The value is the same before and after calling `init_weights` of EncoderDecoder + +backbone.interact_blocks.3.ffn.fc2.bias - torch.Size([1024]): +The value is the same before and after calling `init_weights` of EncoderDecoder + +backbone.interact_blocks.3.ffn_norm.weight - torch.Size([1024]): +The value is the same before and after calling `init_weights` of EncoderDecoder + +backbone.interact_blocks.3.ffn_norm.bias - torch.Size([1024]): +The value is the same before and after calling `init_weights` of EncoderDecoder + +backbone.extract_blocks.0.extract.query_norm.weight - torch.Size([1024]): +The value is the same before and after calling `init_weights` of EncoderDecoder + +backbone.extract_blocks.0.extract.query_norm.bias - torch.Size([1024]): +The value is the same before and after calling `init_weights` of EncoderDecoder + +backbone.extract_blocks.0.extract.feat_norm.weight - torch.Size([1024]): +The value is the same before and after calling `init_weights` of EncoderDecoder + +backbone.extract_blocks.0.extract.feat_norm.bias - torch.Size([1024]): +The value is the same before and after calling `init_weights` of EncoderDecoder + +backbone.extract_blocks.0.extract.attn.sampling_offsets.weight - torch.Size([128, 1024]): +The value is the same before and after calling `init_weights` of EncoderDecoder + +backbone.extract_blocks.0.extract.attn.sampling_offsets.bias - torch.Size([128]): +The value is the same before and after calling `init_weights` of EncoderDecoder + +backbone.extract_blocks.0.extract.attn.attention_weights.weight - torch.Size([64, 1024]): +The value is the same before and after calling `init_weights` of EncoderDecoder + +backbone.extract_blocks.0.extract.attn.attention_weights.bias - torch.Size([64]): +The value is the same before and after calling `init_weights` of EncoderDecoder + +backbone.extract_blocks.0.extract.attn.value_proj.weight - torch.Size([512, 1024]): +The value is the same before and after calling `init_weights` of EncoderDecoder + +backbone.extract_blocks.0.extract.attn.value_proj.bias - torch.Size([512]): +The value is the same before and after calling `init_weights` of EncoderDecoder + +backbone.extract_blocks.0.extract.attn.output_proj.weight - torch.Size([1024, 512]): +The value is the same before and after calling `init_weights` of EncoderDecoder + +backbone.extract_blocks.0.extract.attn.output_proj.bias - torch.Size([1024]): +The value is the same before and after calling `init_weights` of EncoderDecoder + +backbone.extract_blocks.0.ffn.fc1.weight - torch.Size([256, 1024]): +The value is the same before and after calling `init_weights` of EncoderDecoder + +backbone.extract_blocks.0.ffn.fc1.bias - torch.Size([256]): +The value is the same before and after calling `init_weights` of EncoderDecoder + +backbone.extract_blocks.0.ffn.dwconv.dwconv.weight - torch.Size([256, 1, 3, 3]): +The value is the same before and after calling `init_weights` of EncoderDecoder + +backbone.extract_blocks.0.ffn.dwconv.dwconv.bias - torch.Size([256]): +The value is the same before and after calling `init_weights` of EncoderDecoder + +backbone.extract_blocks.0.ffn.fc2.weight - torch.Size([1024, 256]): +The value is the same before and after calling `init_weights` of EncoderDecoder + +backbone.extract_blocks.0.ffn.fc2.bias - torch.Size([1024]): +The value is the same before and after calling `init_weights` of EncoderDecoder + +backbone.extract_blocks.0.ffn_norm.weight - torch.Size([1024]): +The value is the same before and after calling `init_weights` of EncoderDecoder + +backbone.extract_blocks.0.ffn_norm.bias - torch.Size([1024]): +The value is the same before and after calling `init_weights` of EncoderDecoder + +backbone.extract_blocks.1.extract.query_norm.weight - torch.Size([1024]): +The value is the same before and after calling `init_weights` of EncoderDecoder + +backbone.extract_blocks.1.extract.query_norm.bias - torch.Size([1024]): +The value is the same before and after calling `init_weights` of EncoderDecoder + +backbone.extract_blocks.1.extract.feat_norm.weight - torch.Size([1024]): +The value is the same before and after calling `init_weights` of EncoderDecoder + +backbone.extract_blocks.1.extract.feat_norm.bias - torch.Size([1024]): +The value is the same before and after calling `init_weights` of EncoderDecoder + +backbone.extract_blocks.1.extract.attn.sampling_offsets.weight - torch.Size([128, 1024]): +The value is the same before and after calling `init_weights` of EncoderDecoder + +backbone.extract_blocks.1.extract.attn.sampling_offsets.bias - torch.Size([128]): +The value is the same before and after calling `init_weights` of EncoderDecoder + +backbone.extract_blocks.1.extract.attn.attention_weights.weight - torch.Size([64, 1024]): +The value is the same before and after calling `init_weights` of EncoderDecoder + +backbone.extract_blocks.1.extract.attn.attention_weights.bias - torch.Size([64]): +The value is the same before and after calling `init_weights` of EncoderDecoder + +backbone.extract_blocks.1.extract.attn.value_proj.weight - torch.Size([512, 1024]): +The value is the same before and after calling `init_weights` of EncoderDecoder + +backbone.extract_blocks.1.extract.attn.value_proj.bias - torch.Size([512]): +The value is the same before and after calling `init_weights` of EncoderDecoder + +backbone.extract_blocks.1.extract.attn.output_proj.weight - torch.Size([1024, 512]): +The value is the same before and after calling `init_weights` of EncoderDecoder + +backbone.extract_blocks.1.extract.attn.output_proj.bias - torch.Size([1024]): +The value is the same before and after calling `init_weights` of EncoderDecoder + +backbone.extract_blocks.1.ffn.fc1.weight - torch.Size([256, 1024]): +The value is the same before and after calling `init_weights` of EncoderDecoder + +backbone.extract_blocks.1.ffn.fc1.bias - torch.Size([256]): +The value is the same before and after calling `init_weights` of EncoderDecoder + +backbone.extract_blocks.1.ffn.dwconv.dwconv.weight - torch.Size([256, 1, 3, 3]): +The value is the same before and after calling `init_weights` of EncoderDecoder + +backbone.extract_blocks.1.ffn.dwconv.dwconv.bias - torch.Size([256]): +The value is the same before and after calling `init_weights` of EncoderDecoder + +backbone.extract_blocks.1.ffn.fc2.weight - torch.Size([1024, 256]): +The value is the same before and after calling `init_weights` of EncoderDecoder + +backbone.extract_blocks.1.ffn.fc2.bias - torch.Size([1024]): +The value is the same before and after calling `init_weights` of EncoderDecoder + +backbone.extract_blocks.1.ffn_norm.weight - torch.Size([1024]): +The value is the same before and after calling `init_weights` of EncoderDecoder + +backbone.extract_blocks.1.ffn_norm.bias - torch.Size([1024]): +The value is the same before and after calling `init_weights` of EncoderDecoder + +backbone.up.weight - torch.Size([1024, 1024, 2, 2]): +The value is the same before and after calling `init_weights` of EncoderDecoder + +backbone.up.bias - torch.Size([1024]): +The value is the same before and after calling `init_weights` of EncoderDecoder + +backbone.norm1.weight - torch.Size([1024]): +The value is the same before and after calling `init_weights` of EncoderDecoder + +backbone.norm1.bias - torch.Size([1024]): +The value is the same before and after calling `init_weights` of EncoderDecoder + +backbone.norm2.weight - torch.Size([1024]): +The value is the same before and after calling `init_weights` of EncoderDecoder + +backbone.norm2.bias - torch.Size([1024]): +The value is the same before and after calling `init_weights` of EncoderDecoder + +backbone.norm3.weight - torch.Size([1024]): +The value is the same before and after calling `init_weights` of EncoderDecoder + +backbone.norm3.bias - torch.Size([1024]): +The value is the same before and after calling `init_weights` of EncoderDecoder + +backbone.norm4.weight - torch.Size([1024]): +The value is the same before and after calling `init_weights` of EncoderDecoder + +backbone.norm4.bias - torch.Size([1024]): +The value is the same before and after calling `init_weights` of EncoderDecoder + +decode_head.conv_seg.weight - torch.Size([171, 1024, 1, 1]): +NormalInit: mean=0, std=0.01, bias=0 + +decode_head.conv_seg.bias - torch.Size([171]): +NormalInit: mean=0, std=0.01, bias=0 + +decode_head.psp_modules.0.1.conv.weight - torch.Size([1024, 1024, 1, 1]): +The value is the same before and after calling `init_weights` of EncoderDecoder + +decode_head.psp_modules.0.1.bn.weight - torch.Size([1024]): +The value is the same before and after calling `init_weights` of EncoderDecoder + +decode_head.psp_modules.0.1.bn.bias - torch.Size([1024]): +The value is the same before and after calling `init_weights` of EncoderDecoder + +decode_head.psp_modules.1.1.conv.weight - torch.Size([1024, 1024, 1, 1]): +The value is the same before and after calling `init_weights` of EncoderDecoder + +decode_head.psp_modules.1.1.bn.weight - torch.Size([1024]): +The value is the same before and after calling `init_weights` of EncoderDecoder + +decode_head.psp_modules.1.1.bn.bias - torch.Size([1024]): +The value is the same before and after calling `init_weights` of EncoderDecoder + +decode_head.psp_modules.2.1.conv.weight - torch.Size([1024, 1024, 1, 1]): +The value is the same before and after calling `init_weights` of EncoderDecoder + +decode_head.psp_modules.2.1.bn.weight - torch.Size([1024]): +The value is the same before and after calling `init_weights` of EncoderDecoder + +decode_head.psp_modules.2.1.bn.bias - torch.Size([1024]): +The value is the same before and after calling `init_weights` of EncoderDecoder + +decode_head.psp_modules.3.1.conv.weight - torch.Size([1024, 1024, 1, 1]): +The value is the same before and after calling `init_weights` of EncoderDecoder + +decode_head.psp_modules.3.1.bn.weight - torch.Size([1024]): +The value is the same before and after calling `init_weights` of EncoderDecoder + +decode_head.psp_modules.3.1.bn.bias - torch.Size([1024]): +The value is the same before and after calling `init_weights` of EncoderDecoder + +decode_head.bottleneck.conv.weight - torch.Size([1024, 5120, 3, 3]): +Initialized by user-defined `init_weights` in ConvModule + +decode_head.bottleneck.bn.weight - torch.Size([1024]): +The value is the same before and after calling `init_weights` of EncoderDecoder + +decode_head.bottleneck.bn.bias - torch.Size([1024]): +The value is the same before and after calling `init_weights` of EncoderDecoder + +decode_head.lateral_convs.0.conv.weight - torch.Size([1024, 1024, 1, 1]): +The value is the same before and after calling `init_weights` of EncoderDecoder + +decode_head.lateral_convs.0.bn.weight - torch.Size([1024]): +The value is the same before and after calling `init_weights` of EncoderDecoder + +decode_head.lateral_convs.0.bn.bias - torch.Size([1024]): +The value is the same before and after calling `init_weights` of EncoderDecoder + +decode_head.lateral_convs.1.conv.weight - torch.Size([1024, 1024, 1, 1]): +The value is the same before and after calling `init_weights` of EncoderDecoder + +decode_head.lateral_convs.1.bn.weight - torch.Size([1024]): +The value is the same before and after calling `init_weights` of EncoderDecoder + +decode_head.lateral_convs.1.bn.bias - torch.Size([1024]): +The value is the same before and after calling `init_weights` of EncoderDecoder + +decode_head.lateral_convs.2.conv.weight - torch.Size([1024, 1024, 1, 1]): +The value is the same before and after calling `init_weights` of EncoderDecoder + +decode_head.lateral_convs.2.bn.weight - torch.Size([1024]): +The value is the same before and after calling `init_weights` of EncoderDecoder + +decode_head.lateral_convs.2.bn.bias - torch.Size([1024]): +The value is the same before and after calling `init_weights` of EncoderDecoder + +decode_head.fpn_convs.0.conv.weight - torch.Size([1024, 1024, 3, 3]): +The value is the same before and after calling `init_weights` of EncoderDecoder + +decode_head.fpn_convs.0.bn.weight - torch.Size([1024]): +The value is the same before and after calling `init_weights` of EncoderDecoder + +decode_head.fpn_convs.0.bn.bias - torch.Size([1024]): +The value is the same before and after calling `init_weights` of EncoderDecoder + +decode_head.fpn_convs.1.conv.weight - torch.Size([1024, 1024, 3, 3]): +The value is the same before and after calling `init_weights` of EncoderDecoder + +decode_head.fpn_convs.1.bn.weight - torch.Size([1024]): +The value is the same before and after calling `init_weights` of EncoderDecoder + +decode_head.fpn_convs.1.bn.bias - torch.Size([1024]): +The value is the same before and after calling `init_weights` of EncoderDecoder + +decode_head.fpn_convs.2.conv.weight - torch.Size([1024, 1024, 3, 3]): +The value is the same before and after calling `init_weights` of EncoderDecoder + +decode_head.fpn_convs.2.bn.weight - torch.Size([1024]): +The value is the same before and after calling `init_weights` of EncoderDecoder + +decode_head.fpn_convs.2.bn.bias - torch.Size([1024]): +The value is the same before and after calling `init_weights` of EncoderDecoder + +decode_head.fpn_bottleneck.conv.weight - torch.Size([1024, 4096, 3, 3]): +Initialized by user-defined `init_weights` in ConvModule + +decode_head.fpn_bottleneck.bn.weight - torch.Size([1024]): +The value is the same before and after calling `init_weights` of EncoderDecoder + +decode_head.fpn_bottleneck.bn.bias - torch.Size([1024]): +The value is the same before and after calling `init_weights` of EncoderDecoder + +auxiliary_head.conv_seg.weight - torch.Size([171, 256, 1, 1]): +NormalInit: mean=0, std=0.01, bias=0 + +auxiliary_head.conv_seg.bias - torch.Size([171]): +NormalInit: mean=0, std=0.01, bias=0 + +auxiliary_head.convs.0.conv.weight - torch.Size([256, 1024, 3, 3]): +The value is the same before and after calling `init_weights` of EncoderDecoder + +auxiliary_head.convs.0.bn.weight - torch.Size([256]): +The value is the same before and after calling `init_weights` of EncoderDecoder + +auxiliary_head.convs.0.bn.bias - torch.Size([256]): +The value is the same before and after calling `init_weights` of EncoderDecoder +2022-05-05 09:14:22,399 - mmseg - INFO - EncoderDecoder( + (backbone): BEiTAdapter( + (patch_embed): PatchEmbed( + (proj): Conv2d(3, 1024, kernel_size=(16, 16), stride=(16, 16)) + ) + (pos_drop): Dropout(p=0.0, inplace=False) + (blocks): ModuleList( + (0): Block( + (norm1): LayerNorm((1024,), eps=1e-06, elementwise_affine=True) + (attn): Attention( + (qkv): Linear(in_features=1024, out_features=3072, bias=False) + (attn_drop): Dropout(p=0.0, inplace=False) + (proj): Linear(in_features=1024, out_features=1024, bias=True) + (proj_drop): Dropout(p=0.0, inplace=False) + ) + (drop_path): Identity() + (norm2): LayerNorm((1024,), eps=1e-06, elementwise_affine=True) + (mlp): Mlp( + (fc1): Linear(in_features=1024, out_features=4096, bias=True) + (act): GELU() + (fc2): Linear(in_features=4096, out_features=1024, bias=True) + (drop): Dropout(p=0.0, inplace=False) + ) + ) + (1): Block( + (norm1): LayerNorm((1024,), eps=1e-06, elementwise_affine=True) + (attn): Attention( + (qkv): Linear(in_features=1024, out_features=3072, bias=False) + (attn_drop): Dropout(p=0.0, inplace=False) + (proj): Linear(in_features=1024, out_features=1024, bias=True) + (proj_drop): Dropout(p=0.0, inplace=False) + ) + (drop_path): DropPath(p=0.013043479062616825) + (norm2): LayerNorm((1024,), eps=1e-06, elementwise_affine=True) + (mlp): Mlp( + (fc1): Linear(in_features=1024, out_features=4096, bias=True) + (act): GELU() + (fc2): Linear(in_features=4096, out_features=1024, bias=True) + (drop): Dropout(p=0.0, inplace=False) + ) + ) + (2): Block( + (norm1): LayerNorm((1024,), eps=1e-06, elementwise_affine=True) + (attn): Attention( + (qkv): Linear(in_features=1024, out_features=3072, bias=False) + (attn_drop): Dropout(p=0.0, inplace=False) + (proj): Linear(in_features=1024, out_features=1024, bias=True) + (proj_drop): Dropout(p=0.0, inplace=False) + ) + (drop_path): DropPath(p=0.02608695812523365) + (norm2): LayerNorm((1024,), eps=1e-06, elementwise_affine=True) + (mlp): Mlp( + (fc1): Linear(in_features=1024, out_features=4096, bias=True) + (act): GELU() + (fc2): Linear(in_features=4096, out_features=1024, bias=True) + (drop): Dropout(p=0.0, inplace=False) + ) + ) + (3): Block( + (norm1): LayerNorm((1024,), eps=1e-06, elementwise_affine=True) + (attn): Attention( + (qkv): Linear(in_features=1024, out_features=3072, bias=False) + (attn_drop): Dropout(p=0.0, inplace=False) + (proj): Linear(in_features=1024, out_features=1024, bias=True) + (proj_drop): Dropout(p=0.0, inplace=False) + ) + (drop_path): DropPath(p=0.03913043811917305) + (norm2): LayerNorm((1024,), eps=1e-06, elementwise_affine=True) + (mlp): Mlp( + (fc1): Linear(in_features=1024, out_features=4096, bias=True) + (act): GELU() + (fc2): Linear(in_features=4096, out_features=1024, bias=True) + (drop): Dropout(p=0.0, inplace=False) + ) + ) + (4): Block( + (norm1): LayerNorm((1024,), eps=1e-06, elementwise_affine=True) + (attn): Attention( + (qkv): Linear(in_features=1024, out_features=3072, bias=False) + (attn_drop): Dropout(p=0.0, inplace=False) + (proj): Linear(in_features=1024, out_features=1024, bias=True) + (proj_drop): Dropout(p=0.0, inplace=False) + ) + (drop_path): DropPath(p=0.0521739162504673) + (norm2): LayerNorm((1024,), eps=1e-06, elementwise_affine=True) + (mlp): Mlp( + (fc1): Linear(in_features=1024, out_features=4096, bias=True) + (act): GELU() + (fc2): Linear(in_features=4096, out_features=1024, bias=True) + (drop): Dropout(p=0.0, inplace=False) + ) + ) + (5): Block( + (norm1): LayerNorm((1024,), eps=1e-06, elementwise_affine=True) + (attn): Attention( + (qkv): Linear(in_features=1024, out_features=3072, bias=False) + (attn_drop): Dropout(p=0.0, inplace=False) + (proj): Linear(in_features=1024, out_features=1024, bias=True) + (proj_drop): Dropout(p=0.0, inplace=False) + ) + (drop_path): DropPath(p=0.06521739810705185) + (norm2): LayerNorm((1024,), eps=1e-06, elementwise_affine=True) + (mlp): Mlp( + (fc1): Linear(in_features=1024, out_features=4096, bias=True) + (act): GELU() + (fc2): Linear(in_features=4096, out_features=1024, bias=True) + (drop): Dropout(p=0.0, inplace=False) + ) + ) + (6): Block( + (norm1): LayerNorm((1024,), eps=1e-06, elementwise_affine=True) + (attn): Attention( + (qkv): Linear(in_features=1024, out_features=3072, bias=False) + (attn_drop): Dropout(p=0.0, inplace=False) + (proj): Linear(in_features=1024, out_features=1024, bias=True) + (proj_drop): Dropout(p=0.0, inplace=False) + ) + (drop_path): DropPath(p=0.0782608762383461) + (norm2): LayerNorm((1024,), eps=1e-06, elementwise_affine=True) + (mlp): Mlp( + (fc1): Linear(in_features=1024, out_features=4096, bias=True) + (act): GELU() + (fc2): Linear(in_features=4096, out_features=1024, bias=True) + (drop): Dropout(p=0.0, inplace=False) + ) + ) + (7): Block( + (norm1): LayerNorm((1024,), eps=1e-06, elementwise_affine=True) + (attn): Attention( + (qkv): Linear(in_features=1024, out_features=3072, bias=False) + (attn_drop): Dropout(p=0.0, inplace=False) + (proj): Linear(in_features=1024, out_features=1024, bias=True) + (proj_drop): Dropout(p=0.0, inplace=False) + ) + (drop_path): DropPath(p=0.09130435436964035) + (norm2): LayerNorm((1024,), eps=1e-06, elementwise_affine=True) + (mlp): Mlp( + (fc1): Linear(in_features=1024, out_features=4096, bias=True) + (act): GELU() + (fc2): Linear(in_features=4096, out_features=1024, bias=True) + (drop): Dropout(p=0.0, inplace=False) + ) + ) + (8): Block( + (norm1): LayerNorm((1024,), eps=1e-06, elementwise_affine=True) + (attn): Attention( + (qkv): Linear(in_features=1024, out_features=3072, bias=False) + (attn_drop): Dropout(p=0.0, inplace=False) + (proj): Linear(in_features=1024, out_features=1024, bias=True) + (proj_drop): Dropout(p=0.0, inplace=False) + ) + (drop_path): DropPath(p=0.1043478325009346) + (norm2): LayerNorm((1024,), eps=1e-06, elementwise_affine=True) + (mlp): Mlp( + (fc1): Linear(in_features=1024, out_features=4096, bias=True) + (act): GELU() + (fc2): Linear(in_features=4096, out_features=1024, bias=True) + (drop): Dropout(p=0.0, inplace=False) + ) + ) + (9): Block( + (norm1): LayerNorm((1024,), eps=1e-06, elementwise_affine=True) + (attn): Attention( + (qkv): Linear(in_features=1024, out_features=3072, bias=False) + (attn_drop): Dropout(p=0.0, inplace=False) + (proj): Linear(in_features=1024, out_features=1024, bias=True) + (proj_drop): Dropout(p=0.0, inplace=False) + ) + (drop_path): DropPath(p=0.11739131063222885) + (norm2): LayerNorm((1024,), eps=1e-06, elementwise_affine=True) + (mlp): Mlp( + (fc1): Linear(in_features=1024, out_features=4096, bias=True) + (act): GELU() + (fc2): Linear(in_features=4096, out_features=1024, bias=True) + (drop): Dropout(p=0.0, inplace=False) + ) + ) + (10): Block( + (norm1): LayerNorm((1024,), eps=1e-06, elementwise_affine=True) + (attn): Attention( + (qkv): Linear(in_features=1024, out_features=3072, bias=False) + (attn_drop): Dropout(p=0.0, inplace=False) + (proj): Linear(in_features=1024, out_features=1024, bias=True) + (proj_drop): Dropout(p=0.0, inplace=False) + ) + (drop_path): DropPath(p=0.1304347962141037) + (norm2): LayerNorm((1024,), eps=1e-06, elementwise_affine=True) + (mlp): Mlp( + (fc1): Linear(in_features=1024, out_features=4096, bias=True) + (act): GELU() + (fc2): Linear(in_features=4096, out_features=1024, bias=True) + (drop): Dropout(p=0.0, inplace=False) + ) + ) + (11): Block( + (norm1): LayerNorm((1024,), eps=1e-06, elementwise_affine=True) + (attn): Attention( + (qkv): Linear(in_features=1024, out_features=3072, bias=False) + (attn_drop): Dropout(p=0.0, inplace=False) + (proj): Linear(in_features=1024, out_features=1024, bias=True) + (proj_drop): Dropout(p=0.0, inplace=False) + ) + (drop_path): DropPath(p=0.14347827434539795) + (norm2): LayerNorm((1024,), eps=1e-06, elementwise_affine=True) + (mlp): Mlp( + (fc1): Linear(in_features=1024, out_features=4096, bias=True) + (act): GELU() + (fc2): Linear(in_features=4096, out_features=1024, bias=True) + (drop): Dropout(p=0.0, inplace=False) + ) + ) + (12): Block( + (norm1): LayerNorm((1024,), eps=1e-06, elementwise_affine=True) + (attn): Attention( + (qkv): Linear(in_features=1024, out_features=3072, bias=False) + (attn_drop): Dropout(p=0.0, inplace=False) + (proj): Linear(in_features=1024, out_features=1024, bias=True) + (proj_drop): Dropout(p=0.0, inplace=False) + ) + (drop_path): DropPath(p=0.1565217524766922) + (norm2): LayerNorm((1024,), eps=1e-06, elementwise_affine=True) + (mlp): Mlp( + (fc1): Linear(in_features=1024, out_features=4096, bias=True) + (act): GELU() + (fc2): Linear(in_features=4096, out_features=1024, bias=True) + (drop): Dropout(p=0.0, inplace=False) + ) + ) + (13): Block( + (norm1): LayerNorm((1024,), eps=1e-06, elementwise_affine=True) + (attn): Attention( + (qkv): Linear(in_features=1024, out_features=3072, bias=False) + (attn_drop): Dropout(p=0.0, inplace=False) + (proj): Linear(in_features=1024, out_features=1024, bias=True) + (proj_drop): Dropout(p=0.0, inplace=False) + ) + (drop_path): DropPath(p=0.16956523060798645) + (norm2): LayerNorm((1024,), eps=1e-06, elementwise_affine=True) + (mlp): Mlp( + (fc1): Linear(in_features=1024, out_features=4096, bias=True) + (act): GELU() + (fc2): Linear(in_features=4096, out_features=1024, bias=True) + (drop): Dropout(p=0.0, inplace=False) + ) + ) + (14): Block( + (norm1): LayerNorm((1024,), eps=1e-06, elementwise_affine=True) + (attn): Attention( + (qkv): Linear(in_features=1024, out_features=3072, bias=False) + (attn_drop): Dropout(p=0.0, inplace=False) + (proj): Linear(in_features=1024, out_features=1024, bias=True) + (proj_drop): Dropout(p=0.0, inplace=False) + ) + (drop_path): DropPath(p=0.1826087087392807) + (norm2): LayerNorm((1024,), eps=1e-06, elementwise_affine=True) + (mlp): Mlp( + (fc1): Linear(in_features=1024, out_features=4096, bias=True) + (act): GELU() + (fc2): Linear(in_features=4096, out_features=1024, bias=True) + (drop): Dropout(p=0.0, inplace=False) + ) + ) + (15): Block( + (norm1): LayerNorm((1024,), eps=1e-06, elementwise_affine=True) + (attn): Attention( + (qkv): Linear(in_features=1024, out_features=3072, bias=False) + (attn_drop): Dropout(p=0.0, inplace=False) + (proj): Linear(in_features=1024, out_features=1024, bias=True) + (proj_drop): Dropout(p=0.0, inplace=False) + ) + (drop_path): DropPath(p=0.19565218687057495) + (norm2): LayerNorm((1024,), eps=1e-06, elementwise_affine=True) + (mlp): Mlp( + (fc1): Linear(in_features=1024, out_features=4096, bias=True) + (act): GELU() + (fc2): Linear(in_features=4096, out_features=1024, bias=True) + (drop): Dropout(p=0.0, inplace=False) + ) + ) + (16): Block( + (norm1): LayerNorm((1024,), eps=1e-06, elementwise_affine=True) + (attn): Attention( + (qkv): Linear(in_features=1024, out_features=3072, bias=False) + (attn_drop): Dropout(p=0.0, inplace=False) + (proj): Linear(in_features=1024, out_features=1024, bias=True) + (proj_drop): Dropout(p=0.0, inplace=False) + ) + (drop_path): DropPath(p=0.2086956650018692) + (norm2): LayerNorm((1024,), eps=1e-06, elementwise_affine=True) + (mlp): Mlp( + (fc1): Linear(in_features=1024, out_features=4096, bias=True) + (act): GELU() + (fc2): Linear(in_features=4096, out_features=1024, bias=True) + (drop): Dropout(p=0.0, inplace=False) + ) + ) + (17): Block( + (norm1): LayerNorm((1024,), eps=1e-06, elementwise_affine=True) + (attn): Attention( + (qkv): Linear(in_features=1024, out_features=3072, bias=False) + (attn_drop): Dropout(p=0.0, inplace=False) + (proj): Linear(in_features=1024, out_features=1024, bias=True) + (proj_drop): Dropout(p=0.0, inplace=False) + ) + (drop_path): DropPath(p=0.22173914313316345) + (norm2): LayerNorm((1024,), eps=1e-06, elementwise_affine=True) + (mlp): Mlp( + (fc1): Linear(in_features=1024, out_features=4096, bias=True) + (act): GELU() + (fc2): Linear(in_features=4096, out_features=1024, bias=True) + (drop): Dropout(p=0.0, inplace=False) + ) + ) + (18): Block( + (norm1): LayerNorm((1024,), eps=1e-06, elementwise_affine=True) + (attn): Attention( + (qkv): Linear(in_features=1024, out_features=3072, bias=False) + (attn_drop): Dropout(p=0.0, inplace=False) + (proj): Linear(in_features=1024, out_features=1024, bias=True) + (proj_drop): Dropout(p=0.0, inplace=False) + ) + (drop_path): DropPath(p=0.2347826212644577) + (norm2): LayerNorm((1024,), eps=1e-06, elementwise_affine=True) + (mlp): Mlp( + (fc1): Linear(in_features=1024, out_features=4096, bias=True) + (act): GELU() + (fc2): Linear(in_features=4096, out_features=1024, bias=True) + (drop): Dropout(p=0.0, inplace=False) + ) + ) + (19): Block( + (norm1): LayerNorm((1024,), eps=1e-06, elementwise_affine=True) + (attn): Attention( + (qkv): Linear(in_features=1024, out_features=3072, bias=False) + (attn_drop): Dropout(p=0.0, inplace=False) + (proj): Linear(in_features=1024, out_features=1024, bias=True) + (proj_drop): Dropout(p=0.0, inplace=False) + ) + (drop_path): DropPath(p=0.24782609939575195) + (norm2): LayerNorm((1024,), eps=1e-06, elementwise_affine=True) + (mlp): Mlp( + (fc1): Linear(in_features=1024, out_features=4096, bias=True) + (act): GELU() + (fc2): Linear(in_features=4096, out_features=1024, bias=True) + (drop): Dropout(p=0.0, inplace=False) + ) + ) + (20): Block( + (norm1): LayerNorm((1024,), eps=1e-06, elementwise_affine=True) + (attn): Attention( + (qkv): Linear(in_features=1024, out_features=3072, bias=False) + (attn_drop): Dropout(p=0.0, inplace=False) + (proj): Linear(in_features=1024, out_features=1024, bias=True) + (proj_drop): Dropout(p=0.0, inplace=False) + ) + (drop_path): DropPath(p=0.260869562625885) + (norm2): LayerNorm((1024,), eps=1e-06, elementwise_affine=True) + (mlp): Mlp( + (fc1): Linear(in_features=1024, out_features=4096, bias=True) + (act): GELU() + (fc2): Linear(in_features=4096, out_features=1024, bias=True) + (drop): Dropout(p=0.0, inplace=False) + ) + ) + (21): Block( + (norm1): LayerNorm((1024,), eps=1e-06, elementwise_affine=True) + (attn): Attention( + (qkv): Linear(in_features=1024, out_features=3072, bias=False) + (attn_drop): Dropout(p=0.0, inplace=False) + (proj): Linear(in_features=1024, out_features=1024, bias=True) + (proj_drop): Dropout(p=0.0, inplace=False) + ) + (drop_path): DropPath(p=0.27391305565834045) + (norm2): LayerNorm((1024,), eps=1e-06, elementwise_affine=True) + (mlp): Mlp( + (fc1): Linear(in_features=1024, out_features=4096, bias=True) + (act): GELU() + (fc2): Linear(in_features=4096, out_features=1024, bias=True) + (drop): Dropout(p=0.0, inplace=False) + ) + ) + (22): Block( + (norm1): LayerNorm((1024,), eps=1e-06, elementwise_affine=True) + (attn): Attention( + (qkv): Linear(in_features=1024, out_features=3072, bias=False) + (attn_drop): Dropout(p=0.0, inplace=False) + (proj): Linear(in_features=1024, out_features=1024, bias=True) + (proj_drop): Dropout(p=0.0, inplace=False) + ) + (drop_path): DropPath(p=0.2869565188884735) + (norm2): LayerNorm((1024,), eps=1e-06, elementwise_affine=True) + (mlp): Mlp( + (fc1): Linear(in_features=1024, out_features=4096, bias=True) + (act): GELU() + (fc2): Linear(in_features=4096, out_features=1024, bias=True) + (drop): Dropout(p=0.0, inplace=False) + ) + ) + (23): Block( + (norm1): LayerNorm((1024,), eps=1e-06, elementwise_affine=True) + (attn): Attention( + (qkv): Linear(in_features=1024, out_features=3072, bias=False) + (attn_drop): Dropout(p=0.0, inplace=False) + (proj): Linear(in_features=1024, out_features=1024, bias=True) + (proj_drop): Dropout(p=0.0, inplace=False) + ) + (drop_path): DropPath(p=0.30000001192092896) + (norm2): LayerNorm((1024,), eps=1e-06, elementwise_affine=True) + (mlp): Mlp( + (fc1): Linear(in_features=1024, out_features=4096, bias=True) + (act): GELU() + (fc2): Linear(in_features=4096, out_features=1024, bias=True) + (drop): Dropout(p=0.0, inplace=False) + ) + ) + ) + (conv_branch): ConvBranch( + (stem): Sequential( + (0): Conv2d(3, 64, kernel_size=(3, 3), stride=(2, 2), padding=(1, 1), bias=False) + (1): SyncBatchNorm(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) + (2): ReLU(inplace=True) + (3): Conv2d(64, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False) + (4): SyncBatchNorm(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) + (5): ReLU(inplace=True) + (6): Conv2d(64, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False) + (7): SyncBatchNorm(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) + (8): ReLU(inplace=True) + (9): MaxPool2d(kernel_size=3, stride=2, padding=1, dilation=1, ceil_mode=False) + ) + (conv2): Sequential( + (0): Conv2d(64, 128, kernel_size=(3, 3), stride=(2, 2), padding=(1, 1), bias=False) + (1): SyncBatchNorm(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) + (2): ReLU(inplace=True) + ) + (conv3): Sequential( + (0): Conv2d(128, 256, kernel_size=(3, 3), stride=(2, 2), padding=(1, 1), bias=False) + (1): SyncBatchNorm(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) + (2): ReLU(inplace=True) + ) + (conv4): Sequential( + (0): Conv2d(256, 256, kernel_size=(3, 3), stride=(2, 2), padding=(1, 1), bias=False) + (1): SyncBatchNorm(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) + (2): ReLU(inplace=True) + ) + (fc1): Conv2d(64, 1024, kernel_size=(1, 1), stride=(1, 1)) + (fc2): Conv2d(128, 1024, kernel_size=(1, 1), stride=(1, 1)) + (fc3): Conv2d(256, 1024, kernel_size=(1, 1), stride=(1, 1)) + (fc4): Conv2d(256, 1024, kernel_size=(1, 1), stride=(1, 1)) + ) + (interact_blocks): Sequential( + (0): InteractBlock( + (extract): ExtractLayer( + (query_norm): LayerNorm((1024,), eps=1e-06, elementwise_affine=True) + (feat_norm): LayerNorm((1024,), eps=1e-06, elementwise_affine=True) + (attn): MSDeformAttn( + (sampling_offsets): Linear(in_features=1024, out_features=128, bias=True) + (attention_weights): Linear(in_features=1024, out_features=64, bias=True) + (value_proj): Linear(in_features=1024, out_features=512, bias=True) + (output_proj): Linear(in_features=512, out_features=1024, bias=True) + ) + ) + (insert): InsertLayer( + (query_norm): LayerNorm((1024,), eps=1e-06, elementwise_affine=True) + (feat_norm): LayerNorm((1024,), eps=1e-06, elementwise_affine=True) + (attn): MSDeformAttn( + (sampling_offsets): Linear(in_features=1024, out_features=384, bias=True) + (attention_weights): Linear(in_features=1024, out_features=192, bias=True) + (value_proj): Linear(in_features=1024, out_features=512, bias=True) + (output_proj): Linear(in_features=512, out_features=1024, bias=True) + ) + ) + (ffn): ConvFFN( + (fc1): Linear(in_features=1024, out_features=256, bias=True) + (dwconv): DWConv( + (dwconv): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), groups=256) + ) + (act): GELU() + (fc2): Linear(in_features=256, out_features=1024, bias=True) + (drop): Dropout(p=0.0, inplace=False) + ) + (ffn_norm): LayerNorm((1024,), eps=1e-06, elementwise_affine=True) + (drop_path): DropPath() + ) + (1): InteractBlock( + (extract): ExtractLayer( + (query_norm): LayerNorm((1024,), eps=1e-06, elementwise_affine=True) + (feat_norm): LayerNorm((1024,), eps=1e-06, elementwise_affine=True) + (attn): MSDeformAttn( + (sampling_offsets): Linear(in_features=1024, out_features=128, bias=True) + (attention_weights): Linear(in_features=1024, out_features=64, bias=True) + (value_proj): Linear(in_features=1024, out_features=512, bias=True) + (output_proj): Linear(in_features=512, out_features=1024, bias=True) + ) + ) + (insert): InsertLayer( + (query_norm): LayerNorm((1024,), eps=1e-06, elementwise_affine=True) + (feat_norm): LayerNorm((1024,), eps=1e-06, elementwise_affine=True) + (attn): MSDeformAttn( + (sampling_offsets): Linear(in_features=1024, out_features=384, bias=True) + (attention_weights): Linear(in_features=1024, out_features=192, bias=True) + (value_proj): Linear(in_features=1024, out_features=512, bias=True) + (output_proj): Linear(in_features=512, out_features=1024, bias=True) + ) + ) + (ffn): ConvFFN( + (fc1): Linear(in_features=1024, out_features=256, bias=True) + (dwconv): DWConv( + (dwconv): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), groups=256) + ) + (act): GELU() + (fc2): Linear(in_features=256, out_features=1024, bias=True) + (drop): Dropout(p=0.0, inplace=False) + ) + (ffn_norm): LayerNorm((1024,), eps=1e-06, elementwise_affine=True) + (drop_path): DropPath() + ) + (2): InteractBlock( + (extract): ExtractLayer( + (query_norm): LayerNorm((1024,), eps=1e-06, elementwise_affine=True) + (feat_norm): LayerNorm((1024,), eps=1e-06, elementwise_affine=True) + (attn): MSDeformAttn( + (sampling_offsets): Linear(in_features=1024, out_features=128, bias=True) + (attention_weights): Linear(in_features=1024, out_features=64, bias=True) + (value_proj): Linear(in_features=1024, out_features=512, bias=True) + (output_proj): Linear(in_features=512, out_features=1024, bias=True) + ) + ) + (insert): InsertLayer( + (query_norm): LayerNorm((1024,), eps=1e-06, elementwise_affine=True) + (feat_norm): LayerNorm((1024,), eps=1e-06, elementwise_affine=True) + (attn): MSDeformAttn( + (sampling_offsets): Linear(in_features=1024, out_features=384, bias=True) + (attention_weights): Linear(in_features=1024, out_features=192, bias=True) + (value_proj): Linear(in_features=1024, out_features=512, bias=True) + (output_proj): Linear(in_features=512, out_features=1024, bias=True) + ) + ) + (ffn): ConvFFN( + (fc1): Linear(in_features=1024, out_features=256, bias=True) + (dwconv): DWConv( + (dwconv): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), groups=256) + ) + (act): GELU() + (fc2): Linear(in_features=256, out_features=1024, bias=True) + (drop): Dropout(p=0.0, inplace=False) + ) + (ffn_norm): LayerNorm((1024,), eps=1e-06, elementwise_affine=True) + (drop_path): DropPath() + ) + (3): InteractBlock( + (extract): ExtractLayer( + (query_norm): LayerNorm((1024,), eps=1e-06, elementwise_affine=True) + (feat_norm): LayerNorm((1024,), eps=1e-06, elementwise_affine=True) + (attn): MSDeformAttn( + (sampling_offsets): Linear(in_features=1024, out_features=128, bias=True) + (attention_weights): Linear(in_features=1024, out_features=64, bias=True) + (value_proj): Linear(in_features=1024, out_features=512, bias=True) + (output_proj): Linear(in_features=512, out_features=1024, bias=True) + ) + ) + (insert): InsertLayer( + (query_norm): LayerNorm((1024,), eps=1e-06, elementwise_affine=True) + (feat_norm): LayerNorm((1024,), eps=1e-06, elementwise_affine=True) + (attn): MSDeformAttn( + (sampling_offsets): Linear(in_features=1024, out_features=384, bias=True) + (attention_weights): Linear(in_features=1024, out_features=192, bias=True) + (value_proj): Linear(in_features=1024, out_features=512, bias=True) + (output_proj): Linear(in_features=512, out_features=1024, bias=True) + ) + ) + (ffn): ConvFFN( + (fc1): Linear(in_features=1024, out_features=256, bias=True) + (dwconv): DWConv( + (dwconv): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), groups=256) + ) + (act): GELU() + (fc2): Linear(in_features=256, out_features=1024, bias=True) + (drop): Dropout(p=0.0, inplace=False) + ) + (ffn_norm): LayerNorm((1024,), eps=1e-06, elementwise_affine=True) + (drop_path): DropPath() + ) + ) + (extract_blocks): Sequential( + (0): ExtractBlock( + (extract): ExtractLayer( + (query_norm): LayerNorm((1024,), eps=1e-06, elementwise_affine=True) + (feat_norm): LayerNorm((1024,), eps=1e-06, elementwise_affine=True) + (attn): MSDeformAttn( + (sampling_offsets): Linear(in_features=1024, out_features=128, bias=True) + (attention_weights): Linear(in_features=1024, out_features=64, bias=True) + (value_proj): Linear(in_features=1024, out_features=512, bias=True) + (output_proj): Linear(in_features=512, out_features=1024, bias=True) + ) + ) + (ffn): ConvFFN( + (fc1): Linear(in_features=1024, out_features=256, bias=True) + (dwconv): DWConv( + (dwconv): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), groups=256) + ) + (act): GELU() + (fc2): Linear(in_features=256, out_features=1024, bias=True) + (drop): Dropout(p=0.0, inplace=False) + ) + (ffn_norm): LayerNorm((1024,), eps=1e-06, elementwise_affine=True) + (drop_path): Identity() + ) + (1): ExtractBlock( + (extract): ExtractLayer( + (query_norm): LayerNorm((1024,), eps=1e-06, elementwise_affine=True) + (feat_norm): LayerNorm((1024,), eps=1e-06, elementwise_affine=True) + (attn): MSDeformAttn( + (sampling_offsets): Linear(in_features=1024, out_features=128, bias=True) + (attention_weights): Linear(in_features=1024, out_features=64, bias=True) + (value_proj): Linear(in_features=1024, out_features=512, bias=True) + (output_proj): Linear(in_features=512, out_features=1024, bias=True) + ) + ) + (ffn): ConvFFN( + (fc1): Linear(in_features=1024, out_features=256, bias=True) + (dwconv): DWConv( + (dwconv): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), groups=256) + ) + (act): GELU() + (fc2): Linear(in_features=256, out_features=1024, bias=True) + (drop): Dropout(p=0.0, inplace=False) + ) + (ffn_norm): LayerNorm((1024,), eps=1e-06, elementwise_affine=True) + (drop_path): Identity() + ) + ) + (up): ConvTranspose2d(1024, 1024, kernel_size=(2, 2), stride=(2, 2)) + (norm1): SyncBatchNorm(1024, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) + (norm2): SyncBatchNorm(1024, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) + (norm3): SyncBatchNorm(1024, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) + (norm4): SyncBatchNorm(1024, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) + ) + (decode_head): UPerHead( + input_transform=multiple_select, ignore_index=255, align_corners=False + (loss_decode): CrossEntropyLoss(avg_non_ignore=False) + (conv_seg): Conv2d(1024, 171, kernel_size=(1, 1), stride=(1, 1)) + (dropout): Dropout2d(p=0.1, inplace=False) + (psp_modules): PPM( + (0): Sequential( + (0): AdaptiveAvgPool2d(output_size=1) + (1): ConvModule( + (conv): Conv2d(1024, 1024, kernel_size=(1, 1), stride=(1, 1), bias=False) + (bn): SyncBatchNorm(1024, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) + (activate): ReLU(inplace=True) + ) + ) + (1): Sequential( + (0): AdaptiveAvgPool2d(output_size=2) + (1): ConvModule( + (conv): Conv2d(1024, 1024, kernel_size=(1, 1), stride=(1, 1), bias=False) + (bn): SyncBatchNorm(1024, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) + (activate): ReLU(inplace=True) + ) + ) + (2): Sequential( + (0): AdaptiveAvgPool2d(output_size=3) + (1): ConvModule( + (conv): Conv2d(1024, 1024, kernel_size=(1, 1), stride=(1, 1), bias=False) + (bn): SyncBatchNorm(1024, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) + (activate): ReLU(inplace=True) + ) + ) + (3): Sequential( + (0): AdaptiveAvgPool2d(output_size=6) + (1): ConvModule( + (conv): Conv2d(1024, 1024, kernel_size=(1, 1), stride=(1, 1), bias=False) + (bn): SyncBatchNorm(1024, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) + (activate): ReLU(inplace=True) + ) + ) + ) + (bottleneck): ConvModule( + (conv): Conv2d(5120, 1024, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False) + (bn): SyncBatchNorm(1024, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) + (activate): ReLU(inplace=True) + ) + (lateral_convs): ModuleList( + (0): ConvModule( + (conv): Conv2d(1024, 1024, kernel_size=(1, 1), stride=(1, 1), bias=False) + (bn): SyncBatchNorm(1024, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) + (activate): ReLU() + ) + (1): ConvModule( + (conv): Conv2d(1024, 1024, kernel_size=(1, 1), stride=(1, 1), bias=False) + (bn): SyncBatchNorm(1024, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) + (activate): ReLU() + ) + (2): ConvModule( + (conv): Conv2d(1024, 1024, kernel_size=(1, 1), stride=(1, 1), bias=False) + (bn): SyncBatchNorm(1024, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) + (activate): ReLU() + ) + ) + (fpn_convs): ModuleList( + (0): ConvModule( + (conv): Conv2d(1024, 1024, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False) + (bn): SyncBatchNorm(1024, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) + (activate): ReLU() + ) + (1): ConvModule( + (conv): Conv2d(1024, 1024, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False) + (bn): SyncBatchNorm(1024, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) + (activate): ReLU() + ) + (2): ConvModule( + (conv): Conv2d(1024, 1024, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False) + (bn): SyncBatchNorm(1024, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) + (activate): ReLU() + ) + ) + (fpn_bottleneck): ConvModule( + (conv): Conv2d(4096, 1024, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False) + (bn): SyncBatchNorm(1024, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) + (activate): ReLU(inplace=True) + ) + ) + init_cfg={'type': 'Normal', 'std': 0.01, 'override': {'name': 'conv_seg'}} + (auxiliary_head): FCNHead( + input_transform=None, ignore_index=255, align_corners=False + (loss_decode): CrossEntropyLoss(avg_non_ignore=False) + (conv_seg): Conv2d(256, 171, kernel_size=(1, 1), stride=(1, 1)) + (dropout): Dropout2d(p=0.1, inplace=False) + (convs): Sequential( + (0): ConvModule( + (conv): Conv2d(1024, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False) + (bn): SyncBatchNorm(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) + (activate): ReLU(inplace=True) + ) + ) + ) + init_cfg={'type': 'Normal', 'std': 0.01, 'override': {'name': 'conv_seg'}} +) +2022-05-05 09:14:22,768 - mmseg - INFO - Loaded 9000 images +2022-05-05 09:14:23,699 - mmseg - INFO - Loaded 1000 images +2022-05-05 09:14:23,700 - mmseg - INFO - Start running, host: chenzhe.vendor@SH-IDC1-10-140-0-234, work_dir: /mnt/lustre/chenzhe.vendor/workspace/ViT-Adapter/segmentation/work_dirs/upernet_beit_adapter_large_512_80k_cocostuff10k_ss +2022-05-05 09:14:23,701 - mmseg - INFO - Hooks will be executed in the following order: +before_run: +(VERY_HIGH ) PolyLrUpdaterHook +(NORMAL ) CheckpointHook +(LOW ) DistEvalHook +(VERY_LOW ) TextLoggerHook + -------------------- +before_train_epoch: +(VERY_HIGH ) PolyLrUpdaterHook +(LOW ) IterTimerHook +(LOW ) DistEvalHook +(VERY_LOW ) TextLoggerHook + -------------------- +before_train_iter: +(VERY_HIGH ) PolyLrUpdaterHook +(LOW ) IterTimerHook +(LOW ) DistEvalHook + -------------------- +after_train_iter: +(ABOVE_NORMAL) OptimizerHook +(NORMAL ) CheckpointHook +(LOW ) IterTimerHook +(LOW ) DistEvalHook +(VERY_LOW ) TextLoggerHook + -------------------- +after_train_epoch: +(NORMAL ) CheckpointHook +(LOW ) DistEvalHook +(VERY_LOW ) TextLoggerHook + -------------------- +before_val_epoch: +(LOW ) IterTimerHook +(VERY_LOW ) TextLoggerHook + -------------------- +before_val_iter: +(LOW ) IterTimerHook + -------------------- +after_val_iter: +(LOW ) IterTimerHook + -------------------- +after_val_epoch: +(VERY_LOW ) TextLoggerHook + -------------------- +after_run: +(VERY_LOW ) TextLoggerHook + -------------------- +2022-05-05 09:14:23,701 - mmseg - INFO - workflow: [('train', 1)], max: 80000 iters +2022-05-05 09:14:23,701 - mmseg - INFO - Checkpoints will be saved to /mnt/lustre/chenzhe.vendor/workspace/ViT-Adapter/segmentation/work_dirs/upernet_beit_adapter_large_512_80k_cocostuff10k_ss by HardDiskBackend. +2022-05-05 09:15:39,197 - mmseg - INFO - Iter [50/80000] lr: 4.688e-08, eta: 21:23:45, time: 0.963, data_time: 0.007, memory: 60248, decode.loss_ce: 4.1114, decode.acc_seg: 0.5112, aux.loss_ce: 1.6487, aux.acc_seg: 0.6709, loss: 5.7601 +2022-05-05 09:16:09,274 - mmseg - INFO - Iter [100/80000] lr: 9.465e-08, eta: 17:22:38, time: 0.602, data_time: 0.005, memory: 60248, decode.loss_ce: 4.1119, decode.acc_seg: 1.0376, aux.loss_ce: 1.6560, aux.acc_seg: 0.7072, loss: 5.7679 +2022-05-05 09:16:39,082 - mmseg - INFO - Iter [150/80000] lr: 1.424e-07, eta: 15:59:01, time: 0.596, data_time: 0.004, memory: 60248, decode.loss_ce: 4.0715, decode.acc_seg: 4.2044, aux.loss_ce: 1.6620, aux.acc_seg: 0.8934, loss: 5.7336 +2022-05-05 09:17:09,324 - mmseg - INFO - Iter [200/80000] lr: 1.900e-07, eta: 15:19:56, time: 0.605, data_time: 0.005, memory: 60248, decode.loss_ce: 3.9202, decode.acc_seg: 8.8579, aux.loss_ce: 1.6271, aux.acc_seg: 1.2739, loss: 5.5473 +2022-05-05 09:17:39,477 - mmseg - INFO - Iter [250/80000] lr: 2.376e-07, eta: 14:55:52, time: 0.603, data_time: 0.005, memory: 60248, decode.loss_ce: 3.8115, decode.acc_seg: 13.4773, aux.loss_ce: 1.6150, aux.acc_seg: 2.1886, loss: 5.4265 +2022-05-05 09:18:09,316 - mmseg - INFO - Iter [300/80000] lr: 2.851e-07, eta: 14:38:12, time: 0.597, data_time: 0.004, memory: 60248, decode.loss_ce: 3.7883, decode.acc_seg: 16.5744, aux.loss_ce: 1.6470, aux.acc_seg: 4.2338, loss: 5.4354 +2022-05-05 09:18:38,854 - mmseg - INFO - Iter [350/80000] lr: 3.326e-07, eta: 14:24:17, time: 0.591, data_time: 0.004, memory: 60248, decode.loss_ce: 3.6446, decode.acc_seg: 19.0427, aux.loss_ce: 1.6434, aux.acc_seg: 7.5670, loss: 5.2880 +2022-05-05 09:19:08,583 - mmseg - INFO - Iter [400/80000] lr: 3.800e-07, eta: 14:14:22, time: 0.595, data_time: 0.004, memory: 60248, decode.loss_ce: 3.4946, decode.acc_seg: 20.2119, aux.loss_ce: 1.6361, aux.acc_seg: 10.0878, loss: 5.1307 +2022-05-05 09:19:38,428 - mmseg - INFO - Iter [450/80000] lr: 4.274e-07, eta: 14:06:54, time: 0.597, data_time: 0.004, memory: 60248, decode.loss_ce: 3.2654, decode.acc_seg: 22.6359, aux.loss_ce: 1.6058, aux.acc_seg: 13.0389, loss: 4.8712 +2022-05-05 09:20:08,271 - mmseg - INFO - Iter [500/80000] lr: 4.747e-07, eta: 14:00:49, time: 0.597, data_time: 0.004, memory: 60248, decode.loss_ce: 3.1657, decode.acc_seg: 21.3304, aux.loss_ce: 1.5826, aux.acc_seg: 14.2034, loss: 4.7483 +2022-05-05 09:20:37,966 - mmseg - INFO - Iter [550/80000] lr: 5.219e-07, eta: 13:55:23, time: 0.594, data_time: 0.004, memory: 60248, decode.loss_ce: 3.0111, decode.acc_seg: 23.9947, aux.loss_ce: 1.5773, aux.acc_seg: 16.7793, loss: 4.5884 +2022-05-05 09:21:10,422 - mmseg - INFO - Iter [600/80000] lr: 5.691e-07, eta: 13:56:52, time: 0.649, data_time: 0.053, memory: 60248, decode.loss_ce: 2.9157, decode.acc_seg: 26.6779, aux.loss_ce: 1.5791, aux.acc_seg: 19.7130, loss: 4.4948 +2022-05-05 09:21:40,124 - mmseg - INFO - Iter [650/80000] lr: 6.162e-07, eta: 13:52:27, time: 0.594, data_time: 0.004, memory: 60248, decode.loss_ce: 2.7469, decode.acc_seg: 26.6587, aux.loss_ce: 1.5176, aux.acc_seg: 19.5652, loss: 4.2645 +2022-05-05 09:22:10,285 - mmseg - INFO - Iter [700/80000] lr: 6.632e-07, eta: 13:49:25, time: 0.603, data_time: 0.004, memory: 60248, decode.loss_ce: 2.7883, decode.acc_seg: 26.4524, aux.loss_ce: 1.5426, aux.acc_seg: 19.7960, loss: 4.3309 +2022-05-05 09:22:39,941 - mmseg - INFO - Iter [750/80000] lr: 7.102e-07, eta: 13:45:52, time: 0.593, data_time: 0.005, memory: 60248, decode.loss_ce: 2.7393, decode.acc_seg: 28.0557, aux.loss_ce: 1.5463, aux.acc_seg: 19.8619, loss: 4.2856 +2022-05-05 09:23:09,757 - mmseg - INFO - Iter [800/80000] lr: 7.572e-07, eta: 13:42:58, time: 0.596, data_time: 0.004, memory: 60248, decode.loss_ce: 2.5970, decode.acc_seg: 29.5265, aux.loss_ce: 1.4949, aux.acc_seg: 23.1082, loss: 4.0919 +2022-05-05 09:23:39,510 - mmseg - INFO - Iter [850/80000] lr: 8.040e-07, eta: 13:40:14, time: 0.595, data_time: 0.007, memory: 60248, decode.loss_ce: 2.4788, decode.acc_seg: 29.9691, aux.loss_ce: 1.4553, aux.acc_seg: 23.7153, loss: 3.9341 +2022-05-05 09:24:09,419 - mmseg - INFO - Iter [900/80000] lr: 8.509e-07, eta: 13:37:57, time: 0.598, data_time: 0.005, memory: 60248, decode.loss_ce: 2.4911, decode.acc_seg: 29.7736, aux.loss_ce: 1.4357, aux.acc_seg: 21.8151, loss: 3.9268 +2022-05-05 09:24:39,547 - mmseg - INFO - Iter [950/80000] lr: 8.976e-07, eta: 13:36:14, time: 0.603, data_time: 0.006, memory: 60248, decode.loss_ce: 2.3804, decode.acc_seg: 32.7889, aux.loss_ce: 1.4182, aux.acc_seg: 23.4310, loss: 3.7987 +2022-05-05 09:25:09,376 - mmseg - INFO - Saving checkpoint at 1000 iterations +2022-05-05 09:25:29,868 - mmseg - INFO - Exp name: upernet_beit_adapter_large_512_80k_cocostuff10k_ss.py +2022-05-05 09:25:29,876 - mmseg - INFO - Iter [1000/80000] lr: 9.443e-07, eta: 14:01:01, time: 1.004, data_time: 0.004, memory: 60248, decode.loss_ce: 2.3317, decode.acc_seg: 33.4698, aux.loss_ce: 1.3943, aux.acc_seg: 24.2526, loss: 3.7260 +2022-05-05 09:26:00,253 - mmseg - INFO - Iter [1050/80000] lr: 9.909e-07, eta: 13:58:42, time: 0.610, data_time: 0.007, memory: 60248, decode.loss_ce: 2.2139, decode.acc_seg: 35.6863, aux.loss_ce: 1.3555, aux.acc_seg: 25.0364, loss: 3.5694 +2022-05-05 09:26:30,594 - mmseg - INFO - Iter [1100/80000] lr: 1.038e-06, eta: 13:56:18, time: 0.606, data_time: 0.005, memory: 60248, decode.loss_ce: 2.1386, decode.acc_seg: 34.8838, aux.loss_ce: 1.3136, aux.acc_seg: 26.5266, loss: 3.4522 +2022-05-05 09:27:03,098 - mmseg - INFO - Iter [1150/80000] lr: 1.084e-06, eta: 13:56:37, time: 0.651, data_time: 0.054, memory: 60248, decode.loss_ce: 2.0752, decode.acc_seg: 39.0494, aux.loss_ce: 1.3222, aux.acc_seg: 28.4926, loss: 3.3975 +2022-05-05 09:27:33,005 - mmseg - INFO - Iter [1200/80000] lr: 1.130e-06, eta: 13:53:54, time: 0.597, data_time: 0.005, memory: 60248, decode.loss_ce: 2.0364, decode.acc_seg: 36.2042, aux.loss_ce: 1.2700, aux.acc_seg: 26.8817, loss: 3.3064 +2022-05-05 09:28:02,831 - mmseg - INFO - Iter [1250/80000] lr: 1.177e-06, eta: 13:51:25, time: 0.598, data_time: 0.006, memory: 60248, decode.loss_ce: 2.0123, decode.acc_seg: 38.1258, aux.loss_ce: 1.2721, aux.acc_seg: 26.7831, loss: 3.2845 +2022-05-05 09:28:33,028 - mmseg - INFO - Iter [1300/80000] lr: 1.223e-06, eta: 13:49:24, time: 0.604, data_time: 0.005, memory: 60248, decode.loss_ce: 1.9399, decode.acc_seg: 37.9603, aux.loss_ce: 1.2322, aux.acc_seg: 27.0885, loss: 3.1720 +2022-05-05 09:29:02,714 - mmseg - INFO - Iter [1350/80000] lr: 1.269e-06, eta: 13:47:00, time: 0.594, data_time: 0.004, memory: 60248, decode.loss_ce: 1.8687, decode.acc_seg: 42.9611, aux.loss_ce: 1.2233, aux.acc_seg: 31.2070, loss: 3.0919 +2022-05-05 09:29:33,167 - mmseg - INFO - Iter [1400/80000] lr: 1.316e-06, eta: 13:45:24, time: 0.608, data_time: 0.006, memory: 60248, decode.loss_ce: 1.8132, decode.acc_seg: 41.1862, aux.loss_ce: 1.1743, aux.acc_seg: 29.1008, loss: 2.9874 +2022-05-05 09:30:03,150 - mmseg - INFO - Iter [1450/80000] lr: 1.362e-06, eta: 13:43:33, time: 0.601, data_time: 0.006, memory: 60248, decode.loss_ce: 1.7317, decode.acc_seg: 43.6751, aux.loss_ce: 1.1699, aux.acc_seg: 30.0608, loss: 2.9016 +2022-05-05 09:30:33,284 - mmseg - INFO - Iter [1500/80000] lr: 1.408e-06, eta: 13:41:52, time: 0.603, data_time: 0.005, memory: 60248, decode.loss_ce: 1.6548, decode.acc_seg: 44.5283, aux.loss_ce: 1.1286, aux.acc_seg: 29.8065, loss: 2.7834 +2022-05-05 09:31:03,267 - mmseg - INFO - Iter [1550/80000] lr: 1.408e-06, eta: 13:40:09, time: 0.600, data_time: 0.005, memory: 60248, decode.loss_ce: 1.5587, decode.acc_seg: 44.1280, aux.loss_ce: 1.0838, aux.acc_seg: 30.7306, loss: 2.6425 +2022-05-05 09:31:33,216 - mmseg - INFO - Iter [1600/80000] lr: 1.407e-06, eta: 13:38:28, time: 0.599, data_time: 0.005, memory: 60248, decode.loss_ce: 1.5720, decode.acc_seg: 44.3014, aux.loss_ce: 1.0924, aux.acc_seg: 29.2574, loss: 2.6644 +2022-05-05 09:32:03,397 - mmseg - INFO - Iter [1650/80000] lr: 1.406e-06, eta: 13:37:03, time: 0.603, data_time: 0.004, memory: 60248, decode.loss_ce: 1.5951, decode.acc_seg: 44.7262, aux.loss_ce: 1.0865, aux.acc_seg: 30.2762, loss: 2.6816 +2022-05-05 09:32:35,928 - mmseg - INFO - Iter [1700/80000] lr: 1.405e-06, eta: 13:37:28, time: 0.650, data_time: 0.054, memory: 60248, decode.loss_ce: 1.5051, decode.acc_seg: 47.0288, aux.loss_ce: 1.0609, aux.acc_seg: 32.4477, loss: 2.5660 +2022-05-05 09:33:06,039 - mmseg - INFO - Iter [1750/80000] lr: 1.404e-06, eta: 13:36:04, time: 0.603, data_time: 0.005, memory: 60248, decode.loss_ce: 1.4231, decode.acc_seg: 48.4848, aux.loss_ce: 1.0415, aux.acc_seg: 32.7987, loss: 2.4646 +2022-05-05 09:33:35,752 - mmseg - INFO - Iter [1800/80000] lr: 1.404e-06, eta: 13:34:23, time: 0.594, data_time: 0.004, memory: 60248, decode.loss_ce: 1.3951, decode.acc_seg: 48.0681, aux.loss_ce: 1.0254, aux.acc_seg: 31.5921, loss: 2.4205 +2022-05-05 09:34:05,904 - mmseg - INFO - Iter [1850/80000] lr: 1.403e-06, eta: 13:33:07, time: 0.603, data_time: 0.005, memory: 60248, decode.loss_ce: 1.3589, decode.acc_seg: 50.0738, aux.loss_ce: 1.0123, aux.acc_seg: 34.3032, loss: 2.3712 +2022-05-05 09:34:35,874 - mmseg - INFO - Iter [1900/80000] lr: 1.402e-06, eta: 13:31:44, time: 0.599, data_time: 0.004, memory: 60248, decode.loss_ce: 1.3058, decode.acc_seg: 51.7202, aux.loss_ce: 1.0100, aux.acc_seg: 34.3050, loss: 2.3158 +2022-05-05 09:35:05,813 - mmseg - INFO - Iter [1950/80000] lr: 1.401e-06, eta: 13:30:23, time: 0.599, data_time: 0.006, memory: 60248, decode.loss_ce: 1.4076, decode.acc_seg: 48.0328, aux.loss_ce: 1.0272, aux.acc_seg: 31.5794, loss: 2.4347 +2022-05-05 09:35:35,770 - mmseg - INFO - Saving checkpoint at 2000 iterations +2022-05-05 09:35:56,929 - mmseg - INFO - Exp name: upernet_beit_adapter_large_512_80k_cocostuff10k_ss.py +2022-05-05 09:35:56,932 - mmseg - INFO - Iter [2000/80000] lr: 1.400e-06, eta: 13:42:47, time: 1.020, data_time: 0.004, memory: 60248, decode.loss_ce: 1.2507, decode.acc_seg: 53.0022, aux.loss_ce: 1.0022, aux.acc_seg: 33.5045, loss: 2.2529 +2022-05-05 09:36:26,861 - mmseg - INFO - Iter [2050/80000] lr: 1.399e-06, eta: 13:41:14, time: 0.601, data_time: 0.006, memory: 60248, decode.loss_ce: 1.2330, decode.acc_seg: 52.1712, aux.loss_ce: 0.9666, aux.acc_seg: 34.9713, loss: 2.1996 +2022-05-05 09:36:56,469 - mmseg - INFO - Iter [2100/80000] lr: 1.398e-06, eta: 13:39:28, time: 0.592, data_time: 0.005, memory: 60248, decode.loss_ce: 1.1219, decode.acc_seg: 52.3238, aux.loss_ce: 0.9033, aux.acc_seg: 35.8886, loss: 2.0252 +2022-05-05 09:37:25,954 - mmseg - INFO - Iter [2150/80000] lr: 1.397e-06, eta: 13:37:41, time: 0.590, data_time: 0.005, memory: 60248, decode.loss_ce: 1.1949, decode.acc_seg: 51.5942, aux.loss_ce: 0.9212, aux.acc_seg: 34.5833, loss: 2.1162 +2022-05-05 09:37:55,508 - mmseg - INFO - Iter [2200/80000] lr: 1.396e-06, eta: 13:36:01, time: 0.591, data_time: 0.005, memory: 60248, decode.loss_ce: 1.1700, decode.acc_seg: 54.3285, aux.loss_ce: 0.9409, aux.acc_seg: 35.7731, loss: 2.1109 +2022-05-05 09:38:28,191 - mmseg - INFO - Iter [2250/80000] lr: 1.395e-06, eta: 13:36:09, time: 0.652, data_time: 0.050, memory: 60248, decode.loss_ce: 1.1450, decode.acc_seg: 53.3866, aux.loss_ce: 0.9169, aux.acc_seg: 34.7412, loss: 2.0619 +2022-05-05 09:38:58,346 - mmseg - INFO - Iter [2300/80000] lr: 1.395e-06, eta: 13:34:54, time: 0.604, data_time: 0.005, memory: 60248, decode.loss_ce: 1.0787, decode.acc_seg: 54.3537, aux.loss_ce: 0.8875, aux.acc_seg: 37.0128, loss: 1.9662 +2022-05-05 09:39:28,405 - mmseg - INFO - Iter [2350/80000] lr: 1.394e-06, eta: 13:33:32, time: 0.598, data_time: 0.005, memory: 60248, decode.loss_ce: 1.0620, decode.acc_seg: 55.3207, aux.loss_ce: 0.8790, aux.acc_seg: 37.0840, loss: 1.9410 +2022-05-05 09:39:58,564 - mmseg - INFO - Iter [2400/80000] lr: 1.393e-06, eta: 13:32:23, time: 0.606, data_time: 0.007, memory: 60248, decode.loss_ce: 1.0433, decode.acc_seg: 56.2460, aux.loss_ce: 0.8744, aux.acc_seg: 37.5174, loss: 1.9177 +2022-05-05 09:40:28,501 - mmseg - INFO - Iter [2450/80000] lr: 1.392e-06, eta: 13:31:05, time: 0.598, data_time: 0.005, memory: 60248, decode.loss_ce: 1.0275, decode.acc_seg: 54.9251, aux.loss_ce: 0.8487, aux.acc_seg: 37.4236, loss: 1.8762 +2022-05-05 09:40:58,193 - mmseg - INFO - Iter [2500/80000] lr: 1.391e-06, eta: 13:29:42, time: 0.594, data_time: 0.005, memory: 60248, decode.loss_ce: 1.1086, decode.acc_seg: 54.2148, aux.loss_ce: 0.8744, aux.acc_seg: 37.6267, loss: 1.9830 +2022-05-05 09:41:28,127 - mmseg - INFO - Iter [2550/80000] lr: 1.390e-06, eta: 13:28:28, time: 0.598, data_time: 0.005, memory: 60248, decode.loss_ce: 1.0172, decode.acc_seg: 55.2399, aux.loss_ce: 0.8403, aux.acc_seg: 38.3199, loss: 1.8575 +2022-05-05 09:41:58,098 - mmseg - INFO - Iter [2600/80000] lr: 1.389e-06, eta: 13:27:17, time: 0.600, data_time: 0.005, memory: 60248, decode.loss_ce: 1.0368, decode.acc_seg: 55.4428, aux.loss_ce: 0.8589, aux.acc_seg: 36.0579, loss: 1.8957 +2022-05-05 09:42:28,327 - mmseg - INFO - Iter [2650/80000] lr: 1.388e-06, eta: 13:26:14, time: 0.605, data_time: 0.006, memory: 60248, decode.loss_ce: 0.9905, decode.acc_seg: 55.8697, aux.loss_ce: 0.8335, aux.acc_seg: 37.6023, loss: 1.8240 +2022-05-05 09:42:58,312 - mmseg - INFO - Iter [2700/80000] lr: 1.387e-06, eta: 13:25:06, time: 0.600, data_time: 0.004, memory: 60248, decode.loss_ce: 0.9812, decode.acc_seg: 56.1633, aux.loss_ce: 0.8063, aux.acc_seg: 39.9049, loss: 1.7875 +2022-05-05 09:43:28,042 - mmseg - INFO - Iter [2750/80000] lr: 1.386e-06, eta: 13:23:52, time: 0.595, data_time: 0.004, memory: 60248, decode.loss_ce: 0.9785, decode.acc_seg: 56.2168, aux.loss_ce: 0.8086, aux.acc_seg: 39.1685, loss: 1.7871 +2022-05-05 09:43:57,690 - mmseg - INFO - Iter [2800/80000] lr: 1.386e-06, eta: 13:22:38, time: 0.593, data_time: 0.005, memory: 60248, decode.loss_ce: 1.0370, decode.acc_seg: 54.8704, aux.loss_ce: 0.8092, aux.acc_seg: 39.3731, loss: 1.8463 +2022-05-05 09:44:30,344 - mmseg - INFO - Iter [2850/80000] lr: 1.385e-06, eta: 13:22:46, time: 0.653, data_time: 0.057, memory: 60248, decode.loss_ce: 0.9382, decode.acc_seg: 56.9255, aux.loss_ce: 0.8041, aux.acc_seg: 39.3005, loss: 1.7424 +2022-05-05 09:45:00,404 - mmseg - INFO - Iter [2900/80000] lr: 1.384e-06, eta: 13:21:44, time: 0.601, data_time: 0.004, memory: 60248, decode.loss_ce: 0.9472, decode.acc_seg: 57.1318, aux.loss_ce: 0.7980, aux.acc_seg: 39.3108, loss: 1.7452 +2022-05-05 09:45:30,370 - mmseg - INFO - Iter [2950/80000] lr: 1.383e-06, eta: 13:20:41, time: 0.599, data_time: 0.005, memory: 60248, decode.loss_ce: 0.9132, decode.acc_seg: 56.9066, aux.loss_ce: 0.7627, aux.acc_seg: 40.1038, loss: 1.6759 +2022-05-05 09:46:00,117 - mmseg - INFO - Saving checkpoint at 3000 iterations +2022-05-05 09:46:21,041 - mmseg - INFO - Exp name: upernet_beit_adapter_large_512_80k_cocostuff10k_ss.py +2022-05-05 09:46:21,044 - mmseg - INFO - Iter [3000/80000] lr: 1.382e-06, eta: 13:28:27, time: 1.011, data_time: 0.004, memory: 60248, decode.loss_ce: 0.8772, decode.acc_seg: 57.4407, aux.loss_ce: 0.7541, aux.acc_seg: 40.9824, loss: 1.6313 +2022-05-05 09:46:52,010 - mmseg - INFO - Iter [3050/80000] lr: 1.381e-06, eta: 13:27:43, time: 0.620, data_time: 0.007, memory: 60248, decode.loss_ce: 0.9214, decode.acc_seg: 58.9477, aux.loss_ce: 0.7708, aux.acc_seg: 42.2507, loss: 1.6923 +2022-05-05 09:47:21,983 - mmseg - INFO - Iter [3100/80000] lr: 1.380e-06, eta: 13:26:36, time: 0.601, data_time: 0.006, memory: 60248, decode.loss_ce: 0.9203, decode.acc_seg: 57.4693, aux.loss_ce: 0.7694, aux.acc_seg: 39.5533, loss: 1.6897 +2022-05-05 09:47:51,678 - mmseg - INFO - Iter [3150/80000] lr: 1.379e-06, eta: 13:25:21, time: 0.594, data_time: 0.005, memory: 60248, decode.loss_ce: 0.8916, decode.acc_seg: 58.2383, aux.loss_ce: 0.7577, aux.acc_seg: 41.0401, loss: 1.6493 +2022-05-05 09:48:21,800 - mmseg - INFO - Iter [3200/80000] lr: 1.378e-06, eta: 13:24:18, time: 0.602, data_time: 0.006, memory: 60248, decode.loss_ce: 0.8938, decode.acc_seg: 58.6899, aux.loss_ce: 0.7293, aux.acc_seg: 43.4574, loss: 1.6230 +2022-05-05 09:48:51,619 - mmseg - INFO - Iter [3250/80000] lr: 1.377e-06, eta: 13:23:09, time: 0.596, data_time: 0.004, memory: 60248, decode.loss_ce: 0.8860, decode.acc_seg: 58.3198, aux.loss_ce: 0.7472, aux.acc_seg: 41.1026, loss: 1.6332 +2022-05-05 09:49:21,615 - mmseg - INFO - Iter [3300/80000] lr: 1.377e-06, eta: 13:22:05, time: 0.600, data_time: 0.004, memory: 60248, decode.loss_ce: 0.8570, decode.acc_seg: 58.8813, aux.loss_ce: 0.7212, aux.acc_seg: 42.9267, loss: 1.5782 +2022-05-05 09:49:51,565 - mmseg - INFO - Iter [3350/80000] lr: 1.376e-06, eta: 13:21:01, time: 0.599, data_time: 0.005, memory: 60248, decode.loss_ce: 0.9097, decode.acc_seg: 58.2815, aux.loss_ce: 0.7333, aux.acc_seg: 43.1186, loss: 1.6430 +2022-05-05 09:50:24,175 - mmseg - INFO - Iter [3400/80000] lr: 1.375e-06, eta: 13:20:58, time: 0.652, data_time: 0.059, memory: 60248, decode.loss_ce: 0.8426, decode.acc_seg: 60.5774, aux.loss_ce: 0.7075, aux.acc_seg: 45.3948, loss: 1.5500 +2022-05-05 09:50:53,848 - mmseg - INFO - Iter [3450/80000] lr: 1.374e-06, eta: 13:19:49, time: 0.593, data_time: 0.004, memory: 60248, decode.loss_ce: 0.8179, decode.acc_seg: 58.7019, aux.loss_ce: 0.6940, aux.acc_seg: 42.8568, loss: 1.5118 +2022-05-05 09:51:23,798 - mmseg - INFO - Iter [3500/80000] lr: 1.373e-06, eta: 13:18:47, time: 0.599, data_time: 0.005, memory: 60248, decode.loss_ce: 0.8262, decode.acc_seg: 58.7798, aux.loss_ce: 0.6871, aux.acc_seg: 44.0288, loss: 1.5134 +2022-05-05 09:51:53,337 - mmseg - INFO - Iter [3550/80000] lr: 1.372e-06, eta: 13:17:38, time: 0.591, data_time: 0.004, memory: 60248, decode.loss_ce: 0.7926, decode.acc_seg: 60.8397, aux.loss_ce: 0.7005, aux.acc_seg: 44.1159, loss: 1.4931 +2022-05-05 09:52:23,296 - mmseg - INFO - Iter [3600/80000] lr: 1.371e-06, eta: 13:16:37, time: 0.599, data_time: 0.004, memory: 60248, decode.loss_ce: 0.8409, decode.acc_seg: 60.2232, aux.loss_ce: 0.6994, aux.acc_seg: 44.5711, loss: 1.5403 +2022-05-05 09:52:53,257 - mmseg - INFO - Iter [3650/80000] lr: 1.370e-06, eta: 13:15:39, time: 0.600, data_time: 0.005, memory: 60248, decode.loss_ce: 0.7898, decode.acc_seg: 60.3568, aux.loss_ce: 0.6851, aux.acc_seg: 43.9811, loss: 1.4749 +2022-05-05 09:53:23,354 - mmseg - INFO - Iter [3700/80000] lr: 1.369e-06, eta: 13:14:44, time: 0.602, data_time: 0.005, memory: 60248, decode.loss_ce: 0.7943, decode.acc_seg: 59.2474, aux.loss_ce: 0.6736, aux.acc_seg: 42.9978, loss: 1.4679 +2022-05-05 09:53:53,511 - mmseg - INFO - Iter [3750/80000] lr: 1.369e-06, eta: 13:13:50, time: 0.603, data_time: 0.005, memory: 60248, decode.loss_ce: 0.7685, decode.acc_seg: 59.2360, aux.loss_ce: 0.6514, aux.acc_seg: 43.9296, loss: 1.4199 +2022-05-05 09:54:23,312 - mmseg - INFO - Iter [3800/80000] lr: 1.368e-06, eta: 13:12:50, time: 0.596, data_time: 0.005, memory: 60248, decode.loss_ce: 0.7840, decode.acc_seg: 59.9339, aux.loss_ce: 0.6524, aux.acc_seg: 45.4624, loss: 1.4363 +2022-05-05 09:54:53,165 - mmseg - INFO - Iter [3850/80000] lr: 1.367e-06, eta: 13:11:52, time: 0.597, data_time: 0.004, memory: 60248, decode.loss_ce: 0.8245, decode.acc_seg: 59.4533, aux.loss_ce: 0.6714, aux.acc_seg: 45.0513, loss: 1.4959 +2022-05-05 09:55:23,277 - mmseg - INFO - Iter [3900/80000] lr: 1.366e-06, eta: 13:10:59, time: 0.602, data_time: 0.005, memory: 60248, decode.loss_ce: 0.8133, decode.acc_seg: 59.6041, aux.loss_ce: 0.6667, aux.acc_seg: 44.7971, loss: 1.4800 +2022-05-05 09:55:55,967 - mmseg - INFO - Iter [3950/80000] lr: 1.365e-06, eta: 13:10:56, time: 0.653, data_time: 0.056, memory: 60248, decode.loss_ce: 0.7578, decode.acc_seg: 59.0947, aux.loss_ce: 0.6212, aux.acc_seg: 45.2886, loss: 1.3790 +2022-05-05 09:56:25,984 - mmseg - INFO - Saving checkpoint at 4000 iterations +2022-05-05 09:56:47,720 - mmseg - INFO - Exp name: upernet_beit_adapter_large_512_80k_cocostuff10k_ss.py +2022-05-05 09:56:47,723 - mmseg - INFO - Iter [4000/80000] lr: 1.364e-06, eta: 13:16:56, time: 1.035, data_time: 0.006, memory: 60248, decode.loss_ce: 0.7636, decode.acc_seg: 61.4202, aux.loss_ce: 0.6469, aux.acc_seg: 46.9667, loss: 1.4105 +2022-05-05 09:57:18,195 - mmseg - INFO - Iter [4050/80000] lr: 1.363e-06, eta: 13:16:07, time: 0.610, data_time: 0.005, memory: 60248, decode.loss_ce: 0.7136, decode.acc_seg: 61.6389, aux.loss_ce: 0.6202, aux.acc_seg: 47.1627, loss: 1.3338 +2022-05-05 09:57:48,221 - mmseg - INFO - Iter [4100/80000] lr: 1.362e-06, eta: 13:15:09, time: 0.600, data_time: 0.005, memory: 60248, decode.loss_ce: 0.7525, decode.acc_seg: 61.5762, aux.loss_ce: 0.6270, aux.acc_seg: 47.5671, loss: 1.3795 +2022-05-05 09:58:18,033 - mmseg - INFO - Iter [4150/80000] lr: 1.361e-06, eta: 13:14:08, time: 0.596, data_time: 0.005, memory: 60248, decode.loss_ce: 0.7345, decode.acc_seg: 61.8489, aux.loss_ce: 0.6312, aux.acc_seg: 47.1872, loss: 1.3657 +2022-05-05 09:58:47,675 - mmseg - INFO - Iter [4200/80000] lr: 1.360e-06, eta: 13:13:05, time: 0.593, data_time: 0.005, memory: 60248, decode.loss_ce: 0.7493, decode.acc_seg: 61.5202, aux.loss_ce: 0.6147, aux.acc_seg: 48.0418, loss: 1.3640 +2022-05-05 09:59:17,409 - mmseg - INFO - Iter [4250/80000] lr: 1.360e-06, eta: 13:12:04, time: 0.595, data_time: 0.005, memory: 60248, decode.loss_ce: 0.7559, decode.acc_seg: 60.9226, aux.loss_ce: 0.6158, aux.acc_seg: 47.5684, loss: 1.3716 +2022-05-05 09:59:47,003 - mmseg - INFO - Iter [4300/80000] lr: 1.359e-06, eta: 13:11:01, time: 0.592, data_time: 0.004, memory: 60248, decode.loss_ce: 0.7147, decode.acc_seg: 63.4489, aux.loss_ce: 0.6178, aux.acc_seg: 48.8399, loss: 1.3325 +2022-05-05 10:00:17,340 - mmseg - INFO - Iter [4350/80000] lr: 1.358e-06, eta: 13:10:12, time: 0.607, data_time: 0.005, memory: 60248, decode.loss_ce: 0.7373, decode.acc_seg: 60.8647, aux.loss_ce: 0.6026, aux.acc_seg: 47.6727, loss: 1.3399 +2022-05-05 10:00:47,429 - mmseg - INFO - Iter [4400/80000] lr: 1.357e-06, eta: 13:09:19, time: 0.602, data_time: 0.005, memory: 60248, decode.loss_ce: 0.7038, decode.acc_seg: 60.2196, aux.loss_ce: 0.5770, aux.acc_seg: 48.6402, loss: 1.2808 +2022-05-05 10:01:17,664 - mmseg - INFO - Iter [4450/80000] lr: 1.356e-06, eta: 13:08:30, time: 0.605, data_time: 0.005, memory: 60248, decode.loss_ce: 0.7080, decode.acc_seg: 62.1993, aux.loss_ce: 0.5913, aux.acc_seg: 49.3404, loss: 1.2993 +2022-05-05 10:01:50,451 - mmseg - INFO - Iter [4500/80000] lr: 1.355e-06, eta: 13:08:23, time: 0.656, data_time: 0.056, memory: 60248, decode.loss_ce: 0.7581, decode.acc_seg: 59.6167, aux.loss_ce: 0.6040, aux.acc_seg: 47.3953, loss: 1.3621 +2022-05-05 10:02:20,093 - mmseg - INFO - Iter [4550/80000] lr: 1.354e-06, eta: 13:07:24, time: 0.593, data_time: 0.004, memory: 60248, decode.loss_ce: 0.7078, decode.acc_seg: 62.9695, aux.loss_ce: 0.5931, aux.acc_seg: 50.1046, loss: 1.3009 +2022-05-05 10:02:50,164 - mmseg - INFO - Iter [4600/80000] lr: 1.353e-06, eta: 13:06:32, time: 0.601, data_time: 0.005, memory: 60248, decode.loss_ce: 0.6701, decode.acc_seg: 61.9782, aux.loss_ce: 0.5611, aux.acc_seg: 49.9948, loss: 1.2311 +2022-05-05 10:03:20,108 - mmseg - INFO - Iter [4650/80000] lr: 1.352e-06, eta: 13:05:39, time: 0.599, data_time: 0.005, memory: 60248, decode.loss_ce: 0.7115, decode.acc_seg: 61.7221, aux.loss_ce: 0.5774, aux.acc_seg: 49.6441, loss: 1.2889 +2022-05-05 10:03:49,927 - mmseg - INFO - Iter [4700/80000] lr: 1.351e-06, eta: 13:04:44, time: 0.596, data_time: 0.005, memory: 60248, decode.loss_ce: 0.7185, decode.acc_seg: 61.4810, aux.loss_ce: 0.5848, aux.acc_seg: 49.1269, loss: 1.3033 +2022-05-05 10:04:19,828 - mmseg - INFO - Iter [4750/80000] lr: 1.351e-06, eta: 13:03:51, time: 0.598, data_time: 0.005, memory: 60248, decode.loss_ce: 0.6640, decode.acc_seg: 62.3228, aux.loss_ce: 0.5522, aux.acc_seg: 50.2454, loss: 1.2162 +2022-05-05 10:04:49,864 - mmseg - INFO - Iter [4800/80000] lr: 1.350e-06, eta: 13:03:01, time: 0.601, data_time: 0.006, memory: 60248, decode.loss_ce: 0.6745, decode.acc_seg: 61.5291, aux.loss_ce: 0.5481, aux.acc_seg: 49.3039, loss: 1.2226 +2022-05-05 10:05:19,555 - mmseg - INFO - Iter [4850/80000] lr: 1.349e-06, eta: 13:02:06, time: 0.594, data_time: 0.004, memory: 60248, decode.loss_ce: 0.7170, decode.acc_seg: 61.8789, aux.loss_ce: 0.5791, aux.acc_seg: 49.5446, loss: 1.2961 +2022-05-05 10:05:49,680 - mmseg - INFO - Iter [4900/80000] lr: 1.348e-06, eta: 13:01:18, time: 0.602, data_time: 0.004, memory: 60248, decode.loss_ce: 0.7097, decode.acc_seg: 61.2306, aux.loss_ce: 0.5541, aux.acc_seg: 50.2378, loss: 1.2638 +2022-05-05 10:06:19,566 - mmseg - INFO - Iter [4950/80000] lr: 1.347e-06, eta: 13:00:27, time: 0.598, data_time: 0.005, memory: 60248, decode.loss_ce: 0.7120, decode.acc_seg: 61.3335, aux.loss_ce: 0.5520, aux.acc_seg: 49.8066, loss: 1.2640 +2022-05-05 10:06:49,537 - mmseg - INFO - Saving checkpoint at 5000 iterations +2022-05-05 10:07:11,058 - mmseg - INFO - Exp name: upernet_beit_adapter_large_512_80k_cocostuff10k_ss.py +2022-05-05 10:07:11,060 - mmseg - INFO - Iter [5000/80000] lr: 1.346e-06, eta: 13:04:58, time: 1.027, data_time: 0.004, memory: 60248, decode.loss_ce: 0.7254, decode.acc_seg: 61.6311, aux.loss_ce: 0.5515, aux.acc_seg: 51.1628, loss: 1.2768 +2022-05-05 10:07:41,035 - mmseg - INFO - Iter [5050/80000] lr: 1.345e-06, eta: 13:04:07, time: 0.603, data_time: 0.007, memory: 60248, decode.loss_ce: 0.6782, decode.acc_seg: 60.0216, aux.loss_ce: 0.5295, aux.acc_seg: 49.9513, loss: 1.2077 +2022-05-05 10:08:13,439 - mmseg - INFO - Iter [5100/80000] lr: 1.344e-06, eta: 13:03:51, time: 0.648, data_time: 0.052, memory: 60248, decode.loss_ce: 0.6430, decode.acc_seg: 63.5871, aux.loss_ce: 0.5294, aux.acc_seg: 52.2860, loss: 1.1725 +2022-05-05 10:08:43,094 - mmseg - INFO - Iter [5150/80000] lr: 1.343e-06, eta: 13:02:54, time: 0.593, data_time: 0.005, memory: 60248, decode.loss_ce: 0.6754, decode.acc_seg: 61.8448, aux.loss_ce: 0.5341, aux.acc_seg: 50.5779, loss: 1.2095 +2022-05-05 10:09:12,923 - mmseg - INFO - Iter [5200/80000] lr: 1.342e-06, eta: 13:02:00, time: 0.597, data_time: 0.005, memory: 60248, decode.loss_ce: 0.6723, decode.acc_seg: 63.2152, aux.loss_ce: 0.5478, aux.acc_seg: 50.6310, loss: 1.2201 +2022-05-05 10:09:42,767 - mmseg - INFO - Iter [5250/80000] lr: 1.342e-06, eta: 13:01:07, time: 0.596, data_time: 0.005, memory: 60248, decode.loss_ce: 0.6180, decode.acc_seg: 62.0383, aux.loss_ce: 0.5130, aux.acc_seg: 50.3336, loss: 1.1311 +2022-05-05 10:10:12,458 - mmseg - INFO - Iter [5300/80000] lr: 1.341e-06, eta: 13:00:13, time: 0.594, data_time: 0.005, memory: 60248, decode.loss_ce: 0.6481, decode.acc_seg: 61.7645, aux.loss_ce: 0.5141, aux.acc_seg: 50.7732, loss: 1.1623 +2022-05-05 10:10:42,397 - mmseg - INFO - Iter [5350/80000] lr: 1.340e-06, eta: 12:59:22, time: 0.598, data_time: 0.006, memory: 60248, decode.loss_ce: 0.6366, decode.acc_seg: 63.1531, aux.loss_ce: 0.5145, aux.acc_seg: 52.5204, loss: 1.1511 +2022-05-05 10:11:12,093 - mmseg - INFO - Iter [5400/80000] lr: 1.339e-06, eta: 12:58:28, time: 0.594, data_time: 0.005, memory: 60248, decode.loss_ce: 0.6482, decode.acc_seg: 63.3190, aux.loss_ce: 0.5036, aux.acc_seg: 53.6376, loss: 1.1518 +2022-05-05 10:11:42,134 - mmseg - INFO - Iter [5450/80000] lr: 1.338e-06, eta: 12:57:39, time: 0.600, data_time: 0.005, memory: 60248, decode.loss_ce: 0.6440, decode.acc_seg: 62.2178, aux.loss_ce: 0.4980, aux.acc_seg: 51.6398, loss: 1.1420 +2022-05-05 10:12:12,075 - mmseg - INFO - Iter [5500/80000] lr: 1.337e-06, eta: 12:56:50, time: 0.600, data_time: 0.006, memory: 60248, decode.loss_ce: 0.6394, decode.acc_seg: 63.0484, aux.loss_ce: 0.5028, aux.acc_seg: 52.8246, loss: 1.1423 +2022-05-05 10:12:41,923 - mmseg - INFO - Iter [5550/80000] lr: 1.336e-06, eta: 12:55:59, time: 0.597, data_time: 0.004, memory: 60248, decode.loss_ce: 0.6354, decode.acc_seg: 62.8673, aux.loss_ce: 0.4925, aux.acc_seg: 53.5134, loss: 1.1278 +2022-05-05 10:13:11,957 - mmseg - INFO - Iter [5600/80000] lr: 1.335e-06, eta: 12:55:12, time: 0.601, data_time: 0.005, memory: 60248, decode.loss_ce: 0.6359, decode.acc_seg: 62.2558, aux.loss_ce: 0.4882, aux.acc_seg: 52.7245, loss: 1.1241 +2022-05-05 10:13:44,419 - mmseg - INFO - Iter [5650/80000] lr: 1.334e-06, eta: 12:54:56, time: 0.649, data_time: 0.056, memory: 60248, decode.loss_ce: 0.6003, decode.acc_seg: 63.5563, aux.loss_ce: 0.4779, aux.acc_seg: 53.1797, loss: 1.0781 +2022-05-05 10:14:14,602 - mmseg - INFO - Iter [5700/80000] lr: 1.334e-06, eta: 12:54:10, time: 0.602, data_time: 0.005, memory: 60248, decode.loss_ce: 0.5730, decode.acc_seg: 65.4238, aux.loss_ce: 0.4680, aux.acc_seg: 55.4333, loss: 1.0410 +2022-05-05 10:14:44,793 - mmseg - INFO - Iter [5750/80000] lr: 1.333e-06, eta: 12:53:26, time: 0.605, data_time: 0.006, memory: 60248, decode.loss_ce: 0.6164, decode.acc_seg: 63.3586, aux.loss_ce: 0.4874, aux.acc_seg: 53.6455, loss: 1.1038 +2022-05-05 10:15:14,655 - mmseg - INFO - Iter [5800/80000] lr: 1.332e-06, eta: 12:52:37, time: 0.597, data_time: 0.004, memory: 60248, decode.loss_ce: 0.5810, decode.acc_seg: 65.3468, aux.loss_ce: 0.4677, aux.acc_seg: 55.7319, loss: 1.0487 +2022-05-05 10:15:44,592 - mmseg - INFO - Iter [5850/80000] lr: 1.331e-06, eta: 12:51:49, time: 0.598, data_time: 0.004, memory: 60248, decode.loss_ce: 0.5968, decode.acc_seg: 63.2602, aux.loss_ce: 0.4741, aux.acc_seg: 54.0016, loss: 1.0709 +2022-05-05 10:16:14,417 - mmseg - INFO - Iter [5900/80000] lr: 1.330e-06, eta: 12:51:00, time: 0.597, data_time: 0.006, memory: 60248, decode.loss_ce: 0.6307, decode.acc_seg: 62.9924, aux.loss_ce: 0.4742, aux.acc_seg: 53.3682, loss: 1.1050 +2022-05-05 10:16:44,439 - mmseg - INFO - Iter [5950/80000] lr: 1.329e-06, eta: 12:50:14, time: 0.600, data_time: 0.004, memory: 60248, decode.loss_ce: 0.6597, decode.acc_seg: 63.2023, aux.loss_ce: 0.4901, aux.acc_seg: 53.8100, loss: 1.1498 +2022-05-05 10:17:14,686 - mmseg - INFO - Saving checkpoint at 6000 iterations +2022-05-05 10:17:36,184 - mmseg - INFO - Exp name: upernet_beit_adapter_large_512_80k_cocostuff10k_ss.py +2022-05-05 10:17:36,189 - mmseg - INFO - Iter [6000/80000] lr: 1.328e-06, eta: 12:53:55, time: 1.033, data_time: 0.004, memory: 60248, decode.loss_ce: 0.6324, decode.acc_seg: 65.1552, aux.loss_ce: 0.4755, aux.acc_seg: 56.0908, loss: 1.1080 +2022-05-05 10:18:07,009 - mmseg - INFO - Iter [6050/80000] lr: 1.327e-06, eta: 12:53:18, time: 0.619, data_time: 0.007, memory: 60248, decode.loss_ce: 0.6079, decode.acc_seg: 63.4341, aux.loss_ce: 0.4581, aux.acc_seg: 54.5032, loss: 1.0660 +2022-05-05 10:18:36,844 - mmseg - INFO - Iter [6100/80000] lr: 1.326e-06, eta: 12:52:28, time: 0.597, data_time: 0.004, memory: 60248, decode.loss_ce: 0.6446, decode.acc_seg: 62.0391, aux.loss_ce: 0.4948, aux.acc_seg: 51.7819, loss: 1.1394 +2022-05-05 10:19:06,596 - mmseg - INFO - Iter [6150/80000] lr: 1.325e-06, eta: 12:51:37, time: 0.595, data_time: 0.005, memory: 60248, decode.loss_ce: 0.6227, decode.acc_seg: 60.3899, aux.loss_ce: 0.4726, aux.acc_seg: 50.6144, loss: 1.0953 +2022-05-05 10:19:39,343 - mmseg - INFO - Iter [6200/80000] lr: 1.325e-06, eta: 12:51:23, time: 0.655, data_time: 0.053, memory: 60248, decode.loss_ce: 0.6045, decode.acc_seg: 63.6032, aux.loss_ce: 0.4626, aux.acc_seg: 54.1231, loss: 1.0672 +2022-05-05 10:20:09,252 - mmseg - INFO - Iter [6250/80000] lr: 1.324e-06, eta: 12:50:34, time: 0.598, data_time: 0.005, memory: 60248, decode.loss_ce: 0.5950, decode.acc_seg: 65.4309, aux.loss_ce: 0.4763, aux.acc_seg: 54.7848, loss: 1.0713 +2022-05-05 10:20:39,330 - mmseg - INFO - Iter [6300/80000] lr: 1.323e-06, eta: 12:49:48, time: 0.601, data_time: 0.005, memory: 60248, decode.loss_ce: 0.5797, decode.acc_seg: 63.1854, aux.loss_ce: 0.4543, aux.acc_seg: 53.8901, loss: 1.0340 +2022-05-05 10:21:09,254 - mmseg - INFO - Iter [6350/80000] lr: 1.322e-06, eta: 12:49:00, time: 0.598, data_time: 0.004, memory: 60248, decode.loss_ce: 0.5860, decode.acc_seg: 63.5473, aux.loss_ce: 0.4442, aux.acc_seg: 54.8956, loss: 1.0302 +2022-05-05 10:21:39,118 - mmseg - INFO - Iter [6400/80000] lr: 1.321e-06, eta: 12:48:12, time: 0.597, data_time: 0.005, memory: 60248, decode.loss_ce: 0.5947, decode.acc_seg: 63.9119, aux.loss_ce: 0.4537, aux.acc_seg: 54.7113, loss: 1.0484 +2022-05-05 10:22:08,848 - mmseg - INFO - Iter [6450/80000] lr: 1.320e-06, eta: 12:47:23, time: 0.595, data_time: 0.004, memory: 60248, decode.loss_ce: 0.5728, decode.acc_seg: 64.8929, aux.loss_ce: 0.4481, aux.acc_seg: 55.1045, loss: 1.0209 +2022-05-05 10:22:38,676 - mmseg - INFO - Iter [6500/80000] lr: 1.319e-06, eta: 12:46:35, time: 0.597, data_time: 0.005, memory: 60248, decode.loss_ce: 0.5837, decode.acc_seg: 63.6466, aux.loss_ce: 0.4349, aux.acc_seg: 55.6810, loss: 1.0186 +2022-05-05 10:23:08,516 - mmseg - INFO - Iter [6550/80000] lr: 1.318e-06, eta: 12:45:47, time: 0.597, data_time: 0.004, memory: 60248, decode.loss_ce: 0.5997, decode.acc_seg: 63.2160, aux.loss_ce: 0.4369, aux.acc_seg: 54.9128, loss: 1.0366 +2022-05-05 10:23:38,347 - mmseg - INFO - Iter [6600/80000] lr: 1.317e-06, eta: 12:45:00, time: 0.597, data_time: 0.005, memory: 60248, decode.loss_ce: 0.5858, decode.acc_seg: 64.1664, aux.loss_ce: 0.4332, aux.acc_seg: 55.6251, loss: 1.0191 +2022-05-05 10:24:08,029 - mmseg - INFO - Iter [6650/80000] lr: 1.316e-06, eta: 12:44:11, time: 0.593, data_time: 0.004, memory: 60248, decode.loss_ce: 0.5809, decode.acc_seg: 64.5589, aux.loss_ce: 0.4240, aux.acc_seg: 56.9022, loss: 1.0049 +2022-05-05 10:24:37,956 - mmseg - INFO - Iter [6700/80000] lr: 1.316e-06, eta: 12:43:26, time: 0.599, data_time: 0.005, memory: 60248, decode.loss_ce: 0.5669, decode.acc_seg: 64.0638, aux.loss_ce: 0.4169, aux.acc_seg: 56.6501, loss: 0.9838 +2022-05-05 10:25:10,100 - mmseg - INFO - Iter [6750/80000] lr: 1.315e-06, eta: 12:43:04, time: 0.643, data_time: 0.053, memory: 60248, decode.loss_ce: 0.5829, decode.acc_seg: 64.9416, aux.loss_ce: 0.4395, aux.acc_seg: 55.8967, loss: 1.0224 +2022-05-05 10:25:40,034 - mmseg - INFO - Iter [6800/80000] lr: 1.314e-06, eta: 12:42:19, time: 0.599, data_time: 0.004, memory: 60248, decode.loss_ce: 0.5625, decode.acc_seg: 65.0436, aux.loss_ce: 0.4251, aux.acc_seg: 56.3932, loss: 0.9876 +2022-05-05 10:26:10,136 - mmseg - INFO - Iter [6850/80000] lr: 1.313e-06, eta: 12:41:35, time: 0.602, data_time: 0.005, memory: 60248, decode.loss_ce: 0.5563, decode.acc_seg: 66.9020, aux.loss_ce: 0.4352, aux.acc_seg: 57.4073, loss: 0.9915 +2022-05-05 10:26:40,349 - mmseg - INFO - Iter [6900/80000] lr: 1.312e-06, eta: 12:40:53, time: 0.604, data_time: 0.004, memory: 60248, decode.loss_ce: 0.5747, decode.acc_seg: 64.1201, aux.loss_ce: 0.4402, aux.acc_seg: 54.6864, loss: 1.0149 +2022-05-05 10:27:10,149 - mmseg - INFO - Iter [6950/80000] lr: 1.311e-06, eta: 12:40:06, time: 0.595, data_time: 0.004, memory: 60248, decode.loss_ce: 0.5206, decode.acc_seg: 65.1910, aux.loss_ce: 0.3942, aux.acc_seg: 57.0622, loss: 0.9148 +2022-05-05 10:27:40,256 - mmseg - INFO - Saving checkpoint at 7000 iterations +2022-05-05 10:28:01,111 - mmseg - INFO - Exp name: upernet_beit_adapter_large_512_80k_cocostuff10k_ss.py +2022-05-05 10:28:01,114 - mmseg - INFO - Iter [7000/80000] lr: 1.310e-06, eta: 12:43:01, time: 1.019, data_time: 0.006, memory: 60248, decode.loss_ce: 0.5543, decode.acc_seg: 65.2757, aux.loss_ce: 0.4222, aux.acc_seg: 56.3574, loss: 0.9765 +2022-05-05 10:28:31,189 - mmseg - INFO - Iter [7050/80000] lr: 1.309e-06, eta: 12:42:17, time: 0.603, data_time: 0.006, memory: 60248, decode.loss_ce: 0.5714, decode.acc_seg: 64.6160, aux.loss_ce: 0.4113, aux.acc_seg: 57.1767, loss: 0.9827 +2022-05-05 10:29:00,856 - mmseg - INFO - Iter [7100/80000] lr: 1.308e-06, eta: 12:41:28, time: 0.593, data_time: 0.004, memory: 60248, decode.loss_ce: 0.5153, decode.acc_seg: 66.3210, aux.loss_ce: 0.3868, aux.acc_seg: 58.6002, loss: 0.9021 +2022-05-05 10:29:30,727 - mmseg - INFO - Iter [7150/80000] lr: 1.307e-06, eta: 12:40:42, time: 0.597, data_time: 0.004, memory: 60248, decode.loss_ce: 0.5676, decode.acc_seg: 63.7085, aux.loss_ce: 0.4138, aux.acc_seg: 55.9299, loss: 0.9814 +2022-05-05 10:30:00,677 - mmseg - INFO - Iter [7200/80000] lr: 1.307e-06, eta: 12:39:57, time: 0.599, data_time: 0.004, memory: 60248, decode.loss_ce: 0.5597, decode.acc_seg: 63.9461, aux.loss_ce: 0.4063, aux.acc_seg: 56.2261, loss: 0.9660 +2022-05-05 10:30:30,751 - mmseg - INFO - Iter [7250/80000] lr: 1.306e-06, eta: 12:39:12, time: 0.601, data_time: 0.005, memory: 60248, decode.loss_ce: 0.5381, decode.acc_seg: 64.4545, aux.loss_ce: 0.4034, aux.acc_seg: 56.0074, loss: 0.9415 +2022-05-05 10:31:01,124 - mmseg - INFO - Iter [7300/80000] lr: 1.305e-06, eta: 12:38:32, time: 0.609, data_time: 0.006, memory: 60248, decode.loss_ce: 0.5611, decode.acc_seg: 64.9018, aux.loss_ce: 0.3985, aux.acc_seg: 58.0202, loss: 0.9596 +2022-05-05 10:31:34,125 - mmseg - INFO - Iter [7350/80000] lr: 1.304e-06, eta: 12:38:18, time: 0.660, data_time: 0.059, memory: 60248, decode.loss_ce: 0.5243, decode.acc_seg: 64.6841, aux.loss_ce: 0.3895, aux.acc_seg: 57.0079, loss: 0.9138 +2022-05-05 10:32:03,975 - mmseg - INFO - Iter [7400/80000] lr: 1.303e-06, eta: 12:37:32, time: 0.597, data_time: 0.004, memory: 60248, decode.loss_ce: 0.5049, decode.acc_seg: 65.7790, aux.loss_ce: 0.3841, aux.acc_seg: 57.2355, loss: 0.8890 +2022-05-05 10:32:33,672 - mmseg - INFO - Iter [7450/80000] lr: 1.302e-06, eta: 12:36:45, time: 0.594, data_time: 0.005, memory: 60248, decode.loss_ce: 0.5187, decode.acc_seg: 66.0607, aux.loss_ce: 0.3853, aux.acc_seg: 58.2737, loss: 0.9040 +2022-05-05 10:33:03,580 - mmseg - INFO - Iter [7500/80000] lr: 1.301e-06, eta: 12:36:00, time: 0.597, data_time: 0.004, memory: 60248, decode.loss_ce: 0.5221, decode.acc_seg: 65.0705, aux.loss_ce: 0.3995, aux.acc_seg: 55.8558, loss: 0.9215 +2022-05-05 10:33:33,039 - mmseg - INFO - Iter [7550/80000] lr: 1.300e-06, eta: 12:35:12, time: 0.590, data_time: 0.006, memory: 60248, decode.loss_ce: 0.5018, decode.acc_seg: 65.6233, aux.loss_ce: 0.3750, aux.acc_seg: 57.6015, loss: 0.8768 +2022-05-05 10:34:03,595 - mmseg - INFO - Iter [7600/80000] lr: 1.299e-06, eta: 12:34:33, time: 0.610, data_time: 0.005, memory: 60248, decode.loss_ce: 0.5241, decode.acc_seg: 65.0969, aux.loss_ce: 0.3749, aux.acc_seg: 58.3488, loss: 0.8990 +2022-05-05 10:34:33,288 - mmseg - INFO - Iter [7650/80000] lr: 1.299e-06, eta: 12:33:48, time: 0.595, data_time: 0.006, memory: 60248, decode.loss_ce: 0.5267, decode.acc_seg: 64.8976, aux.loss_ce: 0.3884, aux.acc_seg: 57.1654, loss: 0.9151 +2022-05-05 10:35:03,266 - mmseg - INFO - Iter [7700/80000] lr: 1.298e-06, eta: 12:33:04, time: 0.600, data_time: 0.004, memory: 60248, decode.loss_ce: 0.4955, decode.acc_seg: 65.6365, aux.loss_ce: 0.3753, aux.acc_seg: 57.4307, loss: 0.8708 +2022-05-05 10:35:33,046 - mmseg - INFO - Iter [7750/80000] lr: 1.297e-06, eta: 12:32:19, time: 0.596, data_time: 0.004, memory: 60248, decode.loss_ce: 0.4994, decode.acc_seg: 66.0405, aux.loss_ce: 0.3708, aux.acc_seg: 59.2065, loss: 0.8702 +2022-05-05 10:36:02,965 - mmseg - INFO - Iter [7800/80000] lr: 1.296e-06, eta: 12:31:35, time: 0.597, data_time: 0.004, memory: 60248, decode.loss_ce: 0.5220, decode.acc_seg: 66.4573, aux.loss_ce: 0.3922, aux.acc_seg: 58.0064, loss: 0.9143 +2022-05-05 10:36:32,871 - mmseg - INFO - Iter [7850/80000] lr: 1.295e-06, eta: 12:30:52, time: 0.599, data_time: 0.007, memory: 60248, decode.loss_ce: 0.5213, decode.acc_seg: 65.5653, aux.loss_ce: 0.3757, aux.acc_seg: 58.7129, loss: 0.8969 +2022-05-05 10:37:05,592 - mmseg - INFO - Iter [7900/80000] lr: 1.294e-06, eta: 12:30:35, time: 0.654, data_time: 0.055, memory: 60248, decode.loss_ce: 0.5046, decode.acc_seg: 66.2523, aux.loss_ce: 0.3751, aux.acc_seg: 58.6977, loss: 0.8797 +2022-05-05 10:37:35,321 - mmseg - INFO - Iter [7950/80000] lr: 1.293e-06, eta: 12:29:50, time: 0.595, data_time: 0.006, memory: 60248, decode.loss_ce: 0.4871, decode.acc_seg: 65.9399, aux.loss_ce: 0.3623, aux.acc_seg: 58.1871, loss: 0.8494 +2022-05-05 10:38:05,060 - mmseg - INFO - Saving checkpoint at 8000 iterations +2022-05-05 10:38:26,865 - mmseg - INFO - Exp name: upernet_beit_adapter_large_512_80k_cocostuff10k_ss.py +2022-05-05 10:38:26,866 - mmseg - INFO - Iter [8000/80000] lr: 1.292e-06, eta: 12:32:22, time: 1.031, data_time: 0.004, memory: 60248, decode.loss_ce: 0.5187, decode.acc_seg: 66.7870, aux.loss_ce: 0.3880, aux.acc_seg: 58.6389, loss: 0.9067 +2022-05-05 10:39:21,192 - mmseg - INFO - per class results: +2022-05-05 10:39:21,203 - mmseg - INFO - ++------------------+-------+-------+ +| Class | IoU | Acc | ++------------------+-------+-------+ +| person | 86.52 | 95.03 | +| bicycle | 65.66 | 88.08 | +| car | 58.57 | 66.69 | +| motorcycle | 83.68 | 91.76 | +| airplane | 83.31 | 95.14 | +| bus | 76.75 | 86.36 | +| train | 64.96 | 98.62 | +| truck | 73.74 | 85.75 | +| boat | 73.81 | 90.04 | +| traffic light | 66.16 | 86.74 | +| fire hydrant | 86.44 | 97.95 | +| stop sign | 91.51 | 96.25 | +| parking meter | 76.92 | 85.13 | +| bench | 54.75 | 73.51 | +| bird | 74.81 | 82.56 | +| cat | 91.93 | 95.55 | +| dog | 91.37 | 95.85 | +| horse | 88.13 | 96.2 | +| sheep | 81.72 | 91.95 | +| cow | 94.64 | 97.81 | +| elephant | 91.47 | 97.48 | +| bear | 93.77 | 98.32 | +| zebra | 89.04 | 94.9 | +| giraffe | 84.71 | 92.41 | +| backpack | 19.46 | 39.16 | +| umbrella | 78.11 | 88.54 | +| handbag | 12.61 | 15.64 | +| tie | 0.0 | 0.0 | +| suitcase | 74.5 | 96.25 | +| frisbee | 91.54 | 95.25 | +| skis | 27.26 | 42.49 | +| snowboard | 62.93 | 72.98 | +| sports ball | 10.0 | 10.2 | +| kite | 62.76 | 87.89 | +| baseball bat | 19.93 | 20.96 | +| baseball glove | 0.0 | 0.0 | +| skateboard | 59.2 | 82.33 | +| surfboard | 87.93 | 94.01 | +| tennis racket | 63.45 | 80.88 | +| bottle | 68.95 | 80.18 | +| wine glass | 80.97 | 89.6 | +| cup | 63.68 | 90.59 | +| fork | 28.21 | 39.69 | +| knife | 71.47 | 82.11 | +| spoon | 32.97 | 37.76 | +| bowl | 46.76 | 60.45 | +| banana | 70.93 | 86.8 | +| apple | 70.57 | 80.86 | +| sandwich | 76.58 | 99.49 | +| orange | 62.38 | 83.48 | +| broccoli | 86.25 | 92.81 | +| carrot | 42.37 | 65.42 | +| hot dog | 52.83 | 96.24 | +| pizza | 92.77 | 95.84 | +| donut | 58.86 | 83.66 | +| cake | 74.03 | 81.61 | +| chair | 53.87 | 68.92 | +| couch | 67.04 | 93.73 | +| potted plant | 36.72 | 46.84 | +| bed | 71.76 | 86.61 | +| dining table | 59.74 | 76.75 | +| toilet | 83.75 | 95.5 | +| tv | 67.03 | 90.09 | +| laptop | 69.65 | 76.06 | +| mouse | 34.45 | 36.09 | +| remote | 71.42 | 83.35 | +| keyboard | 80.98 | 95.15 | +| cell phone | 81.88 | 95.86 | +| microwave | 48.39 | 72.5 | +| oven | 60.27 | 84.72 | +| toaster | 0.0 | 0.0 | +| sink | 65.12 | 75.15 | +| refrigerator | 81.7 | 96.97 | +| book | 75.02 | 88.62 | +| clock | 77.64 | 84.31 | +| vase | 61.65 | 88.78 | +| scissors | 71.18 | 81.07 | +| teddy bear | 83.79 | 91.82 | +| hair drier | 0.0 | 0.0 | +| toothbrush | 0.0 | 0.0 | +| banner | 34.24 | 65.82 | +| blanket | 0.0 | 0.0 | +| branch | 0.0 | 0.0 | +| bridge | 2.32 | 3.54 | +| building-other | 54.33 | 72.29 | +| bush | 31.28 | 41.43 | +| cabinet | 18.04 | 22.91 | +| cage | 0.6 | 1.15 | +| cardboard | 24.44 | 28.4 | +| carpet | 57.63 | 79.06 | +| ceiling-other | 67.87 | 76.99 | +| ceiling-tile | 0.11 | 0.12 | +| cloth | 0.01 | 0.01 | +| clothes | 17.79 | 24.09 | +| clouds | 56.34 | 77.67 | +| counter | 40.81 | 48.14 | +| cupboard | 56.55 | 83.52 | +| curtain | 65.44 | 78.29 | +| desk-stuff | 33.55 | 38.64 | +| dirt | 42.16 | 76.99 | +| door-stuff | 45.43 | 64.06 | +| fence | 43.23 | 73.71 | +| floor-marble | 0.0 | 0.0 | +| floor-other | 34.74 | 49.72 | +| floor-stone | 14.75 | 18.49 | +| floor-tile | 59.57 | 76.75 | +| floor-wood | 73.69 | 85.8 | +| flower | 17.25 | 43.87 | +| fog | 0.0 | 0.0 | +| food-other | 31.27 | 44.58 | +| fruit | 60.26 | 67.38 | +| furniture-other | 13.04 | 17.7 | +| grass | 72.44 | 85.25 | +| gravel | 17.08 | 18.16 | +| ground-other | 10.79 | 17.98 | +| hill | 33.47 | 49.23 | +| house | 25.29 | 40.99 | +| leaves | 13.07 | 14.1 | +| light | 35.15 | 43.16 | +| mat | 4.53 | 4.85 | +| metal | 14.43 | 22.53 | +| mirror-stuff | 48.88 | 76.41 | +| moss | 0.0 | 0.0 | +| mountain | 25.47 | 35.7 | +| mud | 0.0 | 0.0 | +| napkin | 0.0 | 0.0 | +| net | 23.58 | 26.39 | +| paper | 43.8 | 55.89 | +| pavement | 53.9 | 73.35 | +| pillow | 0.0 | 0.0 | +| plant-other | 29.78 | 37.29 | +| plastic | 24.76 | 30.76 | +| platform | 50.62 | 60.41 | +| playingfield | 70.11 | 83.22 | +| railing | 19.76 | 30.05 | +| railroad | 57.72 | 92.1 | +| river | 21.35 | 26.07 | +| road | 71.32 | 77.12 | +| rock | 52.29 | 69.17 | +| roof | 8.73 | 19.75 | +| rug | 49.38 | 54.85 | +| salad | 0.0 | 0.0 | +| sand | 75.27 | 87.18 | +| sea | 74.5 | 86.74 | +| shelf | 22.76 | 33.3 | +| sky-other | 60.62 | 70.81 | +| skyscraper | 16.57 | 25.36 | +| snow | 91.07 | 95.21 | +| solid-other | nan | nan | +| stairs | 32.95 | 44.16 | +| stone | 5.45 | 6.54 | +| straw | 23.44 | 32.16 | +| structural-other | 17.19 | 30.04 | +| table | 23.97 | 38.1 | +| tent | 77.1 | 82.51 | +| textile-other | 16.12 | 22.1 | +| towel | 39.13 | 46.44 | +| tree | 77.86 | 88.74 | +| vegetable | 35.84 | 57.84 | +| wall-brick | 41.93 | 57.1 | +| wall-concrete | 33.79 | 46.23 | +| wall-other | 60.9 | 78.39 | +| wall-panel | 6.37 | 6.44 | +| wall-stone | 37.41 | 45.07 | +| wall-tile | 54.83 | 87.69 | +| wall-wood | 37.59 | 56.32 | +| water-other | 34.13 | 51.89 | +| waterdrops | nan | nan | +| window-blind | 37.02 | 72.68 | +| window-other | 45.93 | 55.15 | +| wood | 12.66 | 25.35 | ++------------------+-------+-------+ +2022-05-05 10:39:21,203 - mmseg - INFO - Summary: +2022-05-05 10:39:21,203 - mmseg - INFO - ++-------+------+-------+ +| aAcc | mIoU | mAcc | ++-------+------+-------+ +| 75.19 | 47.6 | 59.16 | ++-------+------+-------+ +2022-05-05 10:39:50,928 - mmseg - INFO - Now best checkpoint is saved as best_mIoU_iter_8000.pth. +2022-05-05 10:39:50,938 - mmseg - INFO - Best mIoU is 0.4760 at 8000 iter. +2022-05-05 10:39:50,949 - mmseg - INFO - Exp name: upernet_beit_adapter_large_512_80k_cocostuff10k_ss.py +2022-05-05 10:39:50,949 - mmseg - INFO - Iter(val) [125] aAcc: 0.7519, mIoU: 0.4760, mAcc: 0.5916, IoU.person: 0.8652, IoU.bicycle: 0.6566, IoU.car: 0.5857, IoU.motorcycle: 0.8368, IoU.airplane: 0.8331, IoU.bus: 0.7675, IoU.train: 0.6496, IoU.truck: 0.7374, IoU.boat: 0.7381, IoU.traffic light: 0.6616, IoU.fire hydrant: 0.8644, IoU.stop sign: 0.9151, IoU.parking meter: 0.7692, IoU.bench: 0.5475, IoU.bird: 0.7481, IoU.cat: 0.9193, IoU.dog: 0.9137, IoU.horse: 0.8813, IoU.sheep: 0.8172, IoU.cow: 0.9464, IoU.elephant: 0.9147, IoU.bear: 0.9377, IoU.zebra: 0.8904, IoU.giraffe: 0.8471, IoU.backpack: 0.1946, IoU.umbrella: 0.7811, IoU.handbag: 0.1261, IoU.tie: 0.0000, IoU.suitcase: 0.7450, IoU.frisbee: 0.9154, IoU.skis: 0.2726, IoU.snowboard: 0.6293, IoU.sports ball: 0.1000, IoU.kite: 0.6276, IoU.baseball bat: 0.1993, IoU.baseball glove: 0.0000, IoU.skateboard: 0.5920, IoU.surfboard: 0.8793, IoU.tennis racket: 0.6345, IoU.bottle: 0.6895, IoU.wine glass: 0.8097, IoU.cup: 0.6368, IoU.fork: 0.2821, IoU.knife: 0.7147, IoU.spoon: 0.3297, IoU.bowl: 0.4676, IoU.banana: 0.7093, IoU.apple: 0.7057, IoU.sandwich: 0.7658, IoU.orange: 0.6238, IoU.broccoli: 0.8625, IoU.carrot: 0.4237, IoU.hot dog: 0.5283, IoU.pizza: 0.9277, IoU.donut: 0.5886, IoU.cake: 0.7403, IoU.chair: 0.5387, IoU.couch: 0.6704, IoU.potted plant: 0.3672, IoU.bed: 0.7176, IoU.dining table: 0.5974, IoU.toilet: 0.8375, IoU.tv: 0.6703, IoU.laptop: 0.6965, IoU.mouse: 0.3445, IoU.remote: 0.7142, IoU.keyboard: 0.8098, IoU.cell phone: 0.8188, IoU.microwave: 0.4839, IoU.oven: 0.6027, IoU.toaster: 0.0000, IoU.sink: 0.6512, IoU.refrigerator: 0.8170, IoU.book: 0.7502, IoU.clock: 0.7764, IoU.vase: 0.6165, IoU.scissors: 0.7118, IoU.teddy bear: 0.8379, IoU.hair drier: 0.0000, IoU.toothbrush: 0.0000, IoU.banner: 0.3424, IoU.blanket: 0.0000, IoU.branch: 0.0000, IoU.bridge: 0.0232, IoU.building-other: 0.5433, IoU.bush: 0.3128, IoU.cabinet: 0.1804, IoU.cage: 0.0060, IoU.cardboard: 0.2444, IoU.carpet: 0.5763, IoU.ceiling-other: 0.6787, IoU.ceiling-tile: 0.0011, IoU.cloth: 0.0001, IoU.clothes: 0.1779, IoU.clouds: 0.5634, IoU.counter: 0.4081, IoU.cupboard: 0.5655, IoU.curtain: 0.6544, IoU.desk-stuff: 0.3355, IoU.dirt: 0.4216, IoU.door-stuff: 0.4543, IoU.fence: 0.4323, IoU.floor-marble: 0.0000, IoU.floor-other: 0.3474, IoU.floor-stone: 0.1475, IoU.floor-tile: 0.5957, IoU.floor-wood: 0.7369, IoU.flower: 0.1725, IoU.fog: 0.0000, IoU.food-other: 0.3127, IoU.fruit: 0.6026, IoU.furniture-other: 0.1304, IoU.grass: 0.7244, IoU.gravel: 0.1708, IoU.ground-other: 0.1079, IoU.hill: 0.3347, IoU.house: 0.2529, IoU.leaves: 0.1307, IoU.light: 0.3515, IoU.mat: 0.0453, IoU.metal: 0.1443, IoU.mirror-stuff: 0.4888, IoU.moss: 0.0000, IoU.mountain: 0.2547, IoU.mud: 0.0000, IoU.napkin: 0.0000, IoU.net: 0.2358, IoU.paper: 0.4380, IoU.pavement: 0.5390, IoU.pillow: 0.0000, IoU.plant-other: 0.2978, IoU.plastic: 0.2476, IoU.platform: 0.5062, IoU.playingfield: 0.7011, IoU.railing: 0.1976, IoU.railroad: 0.5772, IoU.river: 0.2135, IoU.road: 0.7132, IoU.rock: 0.5229, IoU.roof: 0.0873, IoU.rug: 0.4938, IoU.salad: 0.0000, IoU.sand: 0.7527, IoU.sea: 0.7450, IoU.shelf: 0.2276, IoU.sky-other: 0.6062, IoU.skyscraper: 0.1657, IoU.snow: 0.9107, IoU.solid-other: nan, IoU.stairs: 0.3295, IoU.stone: 0.0545, IoU.straw: 0.2344, IoU.structural-other: 0.1719, IoU.table: 0.2397, IoU.tent: 0.7710, IoU.textile-other: 0.1612, IoU.towel: 0.3913, IoU.tree: 0.7786, IoU.vegetable: 0.3584, IoU.wall-brick: 0.4193, IoU.wall-concrete: 0.3379, IoU.wall-other: 0.6090, IoU.wall-panel: 0.0637, IoU.wall-stone: 0.3741, IoU.wall-tile: 0.5483, IoU.wall-wood: 0.3759, IoU.water-other: 0.3413, IoU.waterdrops: nan, IoU.window-blind: 0.3702, IoU.window-other: 0.4593, IoU.wood: 0.1266, Acc.person: 0.9503, Acc.bicycle: 0.8808, Acc.car: 0.6669, Acc.motorcycle: 0.9176, Acc.airplane: 0.9514, Acc.bus: 0.8636, Acc.train: 0.9862, Acc.truck: 0.8575, Acc.boat: 0.9004, Acc.traffic light: 0.8674, Acc.fire hydrant: 0.9795, Acc.stop sign: 0.9625, Acc.parking meter: 0.8513, Acc.bench: 0.7351, Acc.bird: 0.8256, Acc.cat: 0.9555, Acc.dog: 0.9585, Acc.horse: 0.9620, Acc.sheep: 0.9195, Acc.cow: 0.9781, Acc.elephant: 0.9748, Acc.bear: 0.9832, Acc.zebra: 0.9490, Acc.giraffe: 0.9241, Acc.backpack: 0.3916, Acc.umbrella: 0.8854, Acc.handbag: 0.1564, Acc.tie: 0.0000, Acc.suitcase: 0.9625, Acc.frisbee: 0.9525, Acc.skis: 0.4249, Acc.snowboard: 0.7298, Acc.sports ball: 0.1020, Acc.kite: 0.8789, Acc.baseball bat: 0.2096, Acc.baseball glove: 0.0000, Acc.skateboard: 0.8233, Acc.surfboard: 0.9401, Acc.tennis racket: 0.8088, Acc.bottle: 0.8018, Acc.wine glass: 0.8960, Acc.cup: 0.9059, Acc.fork: 0.3969, Acc.knife: 0.8211, Acc.spoon: 0.3776, Acc.bowl: 0.6045, Acc.banana: 0.8680, Acc.apple: 0.8086, Acc.sandwich: 0.9949, Acc.orange: 0.8348, Acc.broccoli: 0.9281, Acc.carrot: 0.6542, Acc.hot dog: 0.9624, Acc.pizza: 0.9584, Acc.donut: 0.8366, Acc.cake: 0.8161, Acc.chair: 0.6892, Acc.couch: 0.9373, Acc.potted plant: 0.4684, Acc.bed: 0.8661, Acc.dining table: 0.7675, Acc.toilet: 0.9550, Acc.tv: 0.9009, Acc.laptop: 0.7606, Acc.mouse: 0.3609, Acc.remote: 0.8335, Acc.keyboard: 0.9515, Acc.cell phone: 0.9586, Acc.microwave: 0.7250, Acc.oven: 0.8472, Acc.toaster: 0.0000, Acc.sink: 0.7515, Acc.refrigerator: 0.9697, Acc.book: 0.8862, Acc.clock: 0.8431, Acc.vase: 0.8878, Acc.scissors: 0.8107, Acc.teddy bear: 0.9182, Acc.hair drier: 0.0000, Acc.toothbrush: 0.0000, Acc.banner: 0.6582, Acc.blanket: 0.0000, Acc.branch: 0.0000, Acc.bridge: 0.0354, Acc.building-other: 0.7229, Acc.bush: 0.4143, Acc.cabinet: 0.2291, Acc.cage: 0.0115, Acc.cardboard: 0.2840, Acc.carpet: 0.7906, Acc.ceiling-other: 0.7699, Acc.ceiling-tile: 0.0012, Acc.cloth: 0.0001, Acc.clothes: 0.2409, Acc.clouds: 0.7767, Acc.counter: 0.4814, Acc.cupboard: 0.8352, Acc.curtain: 0.7829, Acc.desk-stuff: 0.3864, Acc.dirt: 0.7699, Acc.door-stuff: 0.6406, Acc.fence: 0.7371, Acc.floor-marble: 0.0000, Acc.floor-other: 0.4972, Acc.floor-stone: 0.1849, Acc.floor-tile: 0.7675, Acc.floor-wood: 0.8580, Acc.flower: 0.4387, Acc.fog: 0.0000, Acc.food-other: 0.4458, Acc.fruit: 0.6738, Acc.furniture-other: 0.1770, Acc.grass: 0.8525, Acc.gravel: 0.1816, Acc.ground-other: 0.1798, Acc.hill: 0.4923, Acc.house: 0.4099, Acc.leaves: 0.1410, Acc.light: 0.4316, Acc.mat: 0.0485, Acc.metal: 0.2253, Acc.mirror-stuff: 0.7641, Acc.moss: 0.0000, Acc.mountain: 0.3570, Acc.mud: 0.0000, Acc.napkin: 0.0000, Acc.net: 0.2639, Acc.paper: 0.5589, Acc.pavement: 0.7335, Acc.pillow: 0.0000, Acc.plant-other: 0.3729, Acc.plastic: 0.3076, Acc.platform: 0.6041, Acc.playingfield: 0.8322, Acc.railing: 0.3005, Acc.railroad: 0.9210, Acc.river: 0.2607, Acc.road: 0.7712, Acc.rock: 0.6917, Acc.roof: 0.1975, Acc.rug: 0.5485, Acc.salad: 0.0000, Acc.sand: 0.8718, Acc.sea: 0.8674, Acc.shelf: 0.3330, Acc.sky-other: 0.7081, Acc.skyscraper: 0.2536, Acc.snow: 0.9521, Acc.solid-other: nan, Acc.stairs: 0.4416, Acc.stone: 0.0654, Acc.straw: 0.3216, Acc.structural-other: 0.3004, Acc.table: 0.3810, Acc.tent: 0.8251, Acc.textile-other: 0.2210, Acc.towel: 0.4644, Acc.tree: 0.8874, Acc.vegetable: 0.5784, Acc.wall-brick: 0.5710, Acc.wall-concrete: 0.4623, Acc.wall-other: 0.7839, Acc.wall-panel: 0.0644, Acc.wall-stone: 0.4507, Acc.wall-tile: 0.8769, Acc.wall-wood: 0.5632, Acc.water-other: 0.5189, Acc.waterdrops: nan, Acc.window-blind: 0.7268, Acc.window-other: 0.5515, Acc.wood: 0.2535 +2022-05-05 10:40:21,482 - mmseg - INFO - Iter [8050/80000] lr: 1.291e-06, eta: 12:44:15, time: 2.292, data_time: 1.687, memory: 60248, decode.loss_ce: 0.5102, decode.acc_seg: 64.8305, aux.loss_ce: 0.3750, aux.acc_seg: 57.0048, loss: 0.8852 +2022-05-05 10:40:51,483 - mmseg - INFO - Iter [8100/80000] lr: 1.290e-06, eta: 12:43:26, time: 0.600, data_time: 0.005, memory: 60248, decode.loss_ce: 0.4823, decode.acc_seg: 67.1559, aux.loss_ce: 0.3530, aux.acc_seg: 60.0911, loss: 0.8353 +2022-05-05 10:41:21,196 - mmseg - INFO - Iter [8150/80000] lr: 1.290e-06, eta: 12:42:35, time: 0.594, data_time: 0.005, memory: 60248, decode.loss_ce: 0.4790, decode.acc_seg: 67.4507, aux.loss_ce: 0.3537, aux.acc_seg: 60.1631, loss: 0.8327 +2022-05-05 10:41:51,547 - mmseg - INFO - Iter [8200/80000] lr: 1.289e-06, eta: 12:41:50, time: 0.607, data_time: 0.005, memory: 60248, decode.loss_ce: 0.4971, decode.acc_seg: 67.8403, aux.loss_ce: 0.3702, aux.acc_seg: 60.1069, loss: 0.8673 +2022-05-05 10:42:21,603 - mmseg - INFO - Iter [8250/80000] lr: 1.288e-06, eta: 12:41:03, time: 0.601, data_time: 0.005, memory: 60248, decode.loss_ce: 0.4827, decode.acc_seg: 65.5152, aux.loss_ce: 0.3417, aux.acc_seg: 59.0782, loss: 0.8244 +2022-05-05 10:42:51,565 - mmseg - INFO - Iter [8300/80000] lr: 1.287e-06, eta: 12:40:15, time: 0.599, data_time: 0.005, memory: 60248, decode.loss_ce: 0.5151, decode.acc_seg: 64.9496, aux.loss_ce: 0.3540, aux.acc_seg: 59.1357, loss: 0.8691 +2022-05-05 10:43:21,691 - mmseg - INFO - Iter [8350/80000] lr: 1.286e-06, eta: 12:39:29, time: 0.602, data_time: 0.005, memory: 60248, decode.loss_ce: 0.4856, decode.acc_seg: 65.7814, aux.loss_ce: 0.3450, aux.acc_seg: 58.9195, loss: 0.8307 +2022-05-05 10:43:51,768 - mmseg - INFO - Iter [8400/80000] lr: 1.285e-06, eta: 12:38:43, time: 0.602, data_time: 0.005, memory: 60248, decode.loss_ce: 0.5168, decode.acc_seg: 66.3797, aux.loss_ce: 0.3702, aux.acc_seg: 58.7767, loss: 0.8870 +2022-05-05 10:44:24,370 - mmseg - INFO - Iter [8450/80000] lr: 1.284e-06, eta: 12:38:18, time: 0.652, data_time: 0.054, memory: 60248, decode.loss_ce: 0.5049, decode.acc_seg: 65.2999, aux.loss_ce: 0.3620, aux.acc_seg: 58.1880, loss: 0.8669 +2022-05-05 10:44:54,348 - mmseg - INFO - Iter [8500/80000] lr: 1.283e-06, eta: 12:37:30, time: 0.599, data_time: 0.004, memory: 60248, decode.loss_ce: 0.4744, decode.acc_seg: 67.0694, aux.loss_ce: 0.3491, aux.acc_seg: 59.3897, loss: 0.8235 +2022-05-05 10:45:23,980 - mmseg - INFO - Iter [8550/80000] lr: 1.282e-06, eta: 12:36:41, time: 0.593, data_time: 0.005, memory: 60248, decode.loss_ce: 0.4718, decode.acc_seg: 66.2008, aux.loss_ce: 0.3513, aux.acc_seg: 58.4719, loss: 0.8231 +2022-05-05 10:45:53,880 - mmseg - INFO - Iter [8600/80000] lr: 1.281e-06, eta: 12:35:53, time: 0.598, data_time: 0.005, memory: 60248, decode.loss_ce: 0.4790, decode.acc_seg: 67.2463, aux.loss_ce: 0.3516, aux.acc_seg: 58.6417, loss: 0.8306 +2022-05-05 10:46:23,662 - mmseg - INFO - Iter [8650/80000] lr: 1.281e-06, eta: 12:35:05, time: 0.596, data_time: 0.004, memory: 60248, decode.loss_ce: 0.4635, decode.acc_seg: 65.4322, aux.loss_ce: 0.3337, aux.acc_seg: 58.9495, loss: 0.7973 +2022-05-05 10:46:53,624 - mmseg - INFO - Iter [8700/80000] lr: 1.280e-06, eta: 12:34:19, time: 0.599, data_time: 0.005, memory: 60248, decode.loss_ce: 0.4768, decode.acc_seg: 65.6031, aux.loss_ce: 0.3418, aux.acc_seg: 59.0359, loss: 0.8186 +2022-05-05 10:47:23,227 - mmseg - INFO - Iter [8750/80000] lr: 1.279e-06, eta: 12:33:30, time: 0.592, data_time: 0.005, memory: 60248, decode.loss_ce: 0.4673, decode.acc_seg: 66.4585, aux.loss_ce: 0.3351, aux.acc_seg: 59.4942, loss: 0.8023 +2022-05-05 10:47:52,969 - mmseg - INFO - Iter [8800/80000] lr: 1.278e-06, eta: 12:32:42, time: 0.595, data_time: 0.005, memory: 60248, decode.loss_ce: 0.4540, decode.acc_seg: 67.5750, aux.loss_ce: 0.3225, aux.acc_seg: 61.4204, loss: 0.7764 +2022-05-05 10:48:22,728 - mmseg - INFO - Iter [8850/80000] lr: 1.277e-06, eta: 12:31:55, time: 0.595, data_time: 0.004, memory: 60248, decode.loss_ce: 0.4868, decode.acc_seg: 67.2071, aux.loss_ce: 0.3511, aux.acc_seg: 59.1093, loss: 0.8380 +2022-05-05 10:48:52,948 - mmseg - INFO - Iter [8900/80000] lr: 1.276e-06, eta: 12:31:11, time: 0.604, data_time: 0.004, memory: 60248, decode.loss_ce: 0.4939, decode.acc_seg: 66.9535, aux.loss_ce: 0.3423, aux.acc_seg: 59.7763, loss: 0.8362 +2022-05-05 10:49:22,851 - mmseg - INFO - Iter [8950/80000] lr: 1.275e-06, eta: 12:30:25, time: 0.598, data_time: 0.004, memory: 60248, decode.loss_ce: 0.4722, decode.acc_seg: 68.5436, aux.loss_ce: 0.3440, aux.acc_seg: 61.4305, loss: 0.8161 +2022-05-05 10:49:55,188 - mmseg - INFO - Saving checkpoint at 9000 iterations +2022-05-05 10:50:15,365 - mmseg - INFO - Exp name: upernet_beit_adapter_large_512_80k_cocostuff10k_ss.py +2022-05-05 10:50:15,367 - mmseg - INFO - Iter [9000/80000] lr: 1.274e-06, eta: 12:32:37, time: 1.048, data_time: 0.053, memory: 60248, decode.loss_ce: 0.4902, decode.acc_seg: 67.9035, aux.loss_ce: 0.3413, aux.acc_seg: 61.2817, loss: 0.8315 +2022-05-05 10:50:45,308 - mmseg - INFO - Iter [9050/80000] lr: 1.273e-06, eta: 12:31:51, time: 0.601, data_time: 0.007, memory: 60248, decode.loss_ce: 0.4338, decode.acc_seg: 68.4999, aux.loss_ce: 0.3324, aux.acc_seg: 60.4884, loss: 0.7661 +2022-05-05 10:51:15,514 - mmseg - INFO - Iter [9100/80000] lr: 1.272e-06, eta: 12:31:07, time: 0.604, data_time: 0.006, memory: 60248, decode.loss_ce: 0.4443, decode.acc_seg: 68.5857, aux.loss_ce: 0.3221, aux.acc_seg: 61.3069, loss: 0.7664 +2022-05-05 10:51:45,154 - mmseg - INFO - Iter [9150/80000] lr: 1.272e-06, eta: 12:30:19, time: 0.593, data_time: 0.004, memory: 60248, decode.loss_ce: 0.4579, decode.acc_seg: 67.8539, aux.loss_ce: 0.3258, aux.acc_seg: 60.2591, loss: 0.7837 +2022-05-05 10:52:15,075 - mmseg - INFO - Iter [9200/80000] lr: 1.271e-06, eta: 12:29:33, time: 0.598, data_time: 0.004, memory: 60248, decode.loss_ce: 0.4296, decode.acc_seg: 67.1474, aux.loss_ce: 0.3213, aux.acc_seg: 59.9138, loss: 0.7509 +2022-05-05 10:52:44,871 - mmseg - INFO - Iter [9250/80000] lr: 1.270e-06, eta: 12:28:46, time: 0.596, data_time: 0.004, memory: 60248, decode.loss_ce: 0.4552, decode.acc_seg: 66.7961, aux.loss_ce: 0.3295, aux.acc_seg: 59.9769, loss: 0.7847 +2022-05-05 10:53:14,635 - mmseg - INFO - Iter [9300/80000] lr: 1.269e-06, eta: 12:27:59, time: 0.595, data_time: 0.005, memory: 60248, decode.loss_ce: 0.4195, decode.acc_seg: 67.6381, aux.loss_ce: 0.3070, aux.acc_seg: 60.5850, loss: 0.7266 +2022-05-05 10:53:44,521 - mmseg - INFO - Iter [9350/80000] lr: 1.268e-06, eta: 12:27:13, time: 0.597, data_time: 0.004, memory: 60248, decode.loss_ce: 0.4591, decode.acc_seg: 67.9761, aux.loss_ce: 0.3256, aux.acc_seg: 61.2592, loss: 0.7848 +2022-05-05 10:54:14,274 - mmseg - INFO - Iter [9400/80000] lr: 1.267e-06, eta: 12:26:27, time: 0.595, data_time: 0.005, memory: 60248, decode.loss_ce: 0.4790, decode.acc_seg: 65.4608, aux.loss_ce: 0.3316, aux.acc_seg: 59.2241, loss: 0.8106 +2022-05-05 10:54:43,986 - mmseg - INFO - Iter [9450/80000] lr: 1.266e-06, eta: 12:25:40, time: 0.594, data_time: 0.005, memory: 60248, decode.loss_ce: 0.4480, decode.acc_seg: 67.9876, aux.loss_ce: 0.3232, aux.acc_seg: 61.2231, loss: 0.7712 +2022-05-05 10:55:14,295 - mmseg - INFO - Iter [9500/80000] lr: 1.265e-06, eta: 12:24:58, time: 0.606, data_time: 0.006, memory: 60248, decode.loss_ce: 0.4585, decode.acc_seg: 66.8963, aux.loss_ce: 0.3266, aux.acc_seg: 59.7732, loss: 0.7850 +2022-05-05 10:55:44,482 - mmseg - INFO - Iter [9550/80000] lr: 1.264e-06, eta: 12:24:15, time: 0.604, data_time: 0.008, memory: 60248, decode.loss_ce: 0.4433, decode.acc_seg: 68.7418, aux.loss_ce: 0.3197, aux.acc_seg: 61.6299, loss: 0.7631 +2022-05-05 10:56:16,861 - mmseg - INFO - Iter [9600/80000] lr: 1.264e-06, eta: 12:23:49, time: 0.648, data_time: 0.053, memory: 60248, decode.loss_ce: 0.4410, decode.acc_seg: 68.5431, aux.loss_ce: 0.3219, aux.acc_seg: 61.7635, loss: 0.7630 +2022-05-05 10:56:47,162 - mmseg - INFO - Iter [9650/80000] lr: 1.263e-06, eta: 12:23:07, time: 0.606, data_time: 0.005, memory: 60248, decode.loss_ce: 0.4431, decode.acc_seg: 68.5598, aux.loss_ce: 0.3156, aux.acc_seg: 61.7616, loss: 0.7587 +2022-05-05 10:57:16,960 - mmseg - INFO - Iter [9700/80000] lr: 1.262e-06, eta: 12:22:21, time: 0.596, data_time: 0.005, memory: 60248, decode.loss_ce: 0.4410, decode.acc_seg: 67.7144, aux.loss_ce: 0.3191, aux.acc_seg: 60.7250, loss: 0.7601 +2022-05-05 10:57:46,670 - mmseg - INFO - Iter [9750/80000] lr: 1.261e-06, eta: 12:21:35, time: 0.594, data_time: 0.005, memory: 60248, decode.loss_ce: 0.4398, decode.acc_seg: 68.0818, aux.loss_ce: 0.3205, aux.acc_seg: 60.9891, loss: 0.7604 +2022-05-05 10:58:16,520 - mmseg - INFO - Iter [9800/80000] lr: 1.260e-06, eta: 12:20:51, time: 0.597, data_time: 0.004, memory: 60248, decode.loss_ce: 0.4184, decode.acc_seg: 66.9131, aux.loss_ce: 0.3044, aux.acc_seg: 60.3401, loss: 0.7229 +2022-05-05 10:58:46,075 - mmseg - INFO - Iter [9850/80000] lr: 1.259e-06, eta: 12:20:04, time: 0.592, data_time: 0.005, memory: 60248, decode.loss_ce: 0.4079, decode.acc_seg: 67.9330, aux.loss_ce: 0.2980, aux.acc_seg: 61.2472, loss: 0.7059 +2022-05-05 10:59:16,048 - mmseg - INFO - Iter [9900/80000] lr: 1.258e-06, eta: 12:19:19, time: 0.595, data_time: 0.004, memory: 60248, decode.loss_ce: 0.4381, decode.acc_seg: 67.4941, aux.loss_ce: 0.3241, aux.acc_seg: 59.7685, loss: 0.7622 +2022-05-05 10:59:46,152 - mmseg - INFO - Iter [9950/80000] lr: 1.257e-06, eta: 12:18:38, time: 0.606, data_time: 0.008, memory: 60248, decode.loss_ce: 0.4385, decode.acc_seg: 68.0722, aux.loss_ce: 0.3205, aux.acc_seg: 60.8055, loss: 0.7590 +2022-05-05 11:00:15,919 - mmseg - INFO - Saving checkpoint at 10000 iterations +2022-05-05 11:00:36,269 - mmseg - INFO - Exp name: upernet_beit_adapter_large_512_80k_cocostuff10k_ss.py +2022-05-05 11:00:36,276 - mmseg - INFO - Iter [10000/80000] lr: 1.256e-06, eta: 12:20:15, time: 1.000, data_time: 0.005, memory: 60248, decode.loss_ce: 0.4387, decode.acc_seg: 68.8654, aux.loss_ce: 0.3002, aux.acc_seg: 62.4459, loss: 0.7390 +2022-05-05 11:01:06,624 - mmseg - INFO - Iter [10050/80000] lr: 1.255e-06, eta: 12:19:35, time: 0.610, data_time: 0.007, memory: 60248, decode.loss_ce: 0.4322, decode.acc_seg: 67.9189, aux.loss_ce: 0.3095, aux.acc_seg: 61.3814, loss: 0.7417 +2022-05-05 11:01:36,272 - mmseg - INFO - Iter [10100/80000] lr: 1.255e-06, eta: 12:18:48, time: 0.593, data_time: 0.005, memory: 60248, decode.loss_ce: 0.4253, decode.acc_seg: 68.6239, aux.loss_ce: 0.3056, aux.acc_seg: 61.9955, loss: 0.7309 +2022-05-05 11:02:08,531 - mmseg - INFO - Iter [10150/80000] lr: 1.254e-06, eta: 12:18:20, time: 0.645, data_time: 0.054, memory: 60248, decode.loss_ce: 0.4186, decode.acc_seg: 68.4232, aux.loss_ce: 0.3019, aux.acc_seg: 61.7307, loss: 0.7204 +2022-05-05 11:02:38,168 - mmseg - INFO - Iter [10200/80000] lr: 1.253e-06, eta: 12:17:35, time: 0.593, data_time: 0.004, memory: 60248, decode.loss_ce: 0.4390, decode.acc_seg: 68.1459, aux.loss_ce: 0.3131, aux.acc_seg: 61.6234, loss: 0.7521 +2022-05-05 11:03:07,703 - mmseg - INFO - Iter [10250/80000] lr: 1.252e-06, eta: 12:16:48, time: 0.591, data_time: 0.005, memory: 60248, decode.loss_ce: 0.4392, decode.acc_seg: 67.7276, aux.loss_ce: 0.3111, aux.acc_seg: 60.5497, loss: 0.7503 +2022-05-05 11:03:37,373 - mmseg - INFO - Iter [10300/80000] lr: 1.251e-06, eta: 12:16:03, time: 0.593, data_time: 0.005, memory: 60248, decode.loss_ce: 0.3976, decode.acc_seg: 68.4186, aux.loss_ce: 0.2901, aux.acc_seg: 61.6139, loss: 0.6878 +2022-05-05 11:04:07,105 - mmseg - INFO - Iter [10350/80000] lr: 1.250e-06, eta: 12:15:18, time: 0.595, data_time: 0.004, memory: 60248, decode.loss_ce: 0.4135, decode.acc_seg: 67.8153, aux.loss_ce: 0.2927, aux.acc_seg: 61.4382, loss: 0.7062 +2022-05-05 11:04:36,641 - mmseg - INFO - Iter [10400/80000] lr: 1.249e-06, eta: 12:14:32, time: 0.590, data_time: 0.004, memory: 60248, decode.loss_ce: 0.4012, decode.acc_seg: 68.1373, aux.loss_ce: 0.2871, aux.acc_seg: 61.3909, loss: 0.6884 +2022-05-05 11:05:06,371 - mmseg - INFO - Iter [10450/80000] lr: 1.248e-06, eta: 12:13:47, time: 0.595, data_time: 0.005, memory: 60248, decode.loss_ce: 0.4161, decode.acc_seg: 69.1748, aux.loss_ce: 0.2969, aux.acc_seg: 62.6730, loss: 0.7131 +2022-05-05 11:05:36,442 - mmseg - INFO - Iter [10500/80000] lr: 1.247e-06, eta: 12:13:05, time: 0.601, data_time: 0.004, memory: 60248, decode.loss_ce: 0.4241, decode.acc_seg: 69.1874, aux.loss_ce: 0.3009, aux.acc_seg: 62.7399, loss: 0.7250 +2022-05-05 11:06:06,164 - mmseg - INFO - Iter [10550/80000] lr: 1.246e-06, eta: 12:12:21, time: 0.594, data_time: 0.005, memory: 60248, decode.loss_ce: 0.4382, decode.acc_seg: 68.3045, aux.loss_ce: 0.3029, aux.acc_seg: 62.4495, loss: 0.7412 +2022-05-05 11:06:35,974 - mmseg - INFO - Iter [10600/80000] lr: 1.246e-06, eta: 12:11:37, time: 0.596, data_time: 0.004, memory: 60248, decode.loss_ce: 0.4190, decode.acc_seg: 68.2868, aux.loss_ce: 0.2971, aux.acc_seg: 61.1967, loss: 0.7161 +2022-05-05 11:07:05,975 - mmseg - INFO - Iter [10650/80000] lr: 1.245e-06, eta: 12:10:55, time: 0.600, data_time: 0.005, memory: 60248, decode.loss_ce: 0.4306, decode.acc_seg: 67.7979, aux.loss_ce: 0.3048, aux.acc_seg: 60.8956, loss: 0.7354 +2022-05-05 11:07:38,486 - mmseg - INFO - Iter [10700/80000] lr: 1.244e-06, eta: 12:10:29, time: 0.650, data_time: 0.054, memory: 60248, decode.loss_ce: 0.4228, decode.acc_seg: 69.8914, aux.loss_ce: 0.2987, aux.acc_seg: 63.2781, loss: 0.7215 +2022-05-05 11:08:08,321 - mmseg - INFO - Iter [10750/80000] lr: 1.243e-06, eta: 12:09:46, time: 0.597, data_time: 0.006, memory: 60248, decode.loss_ce: 0.3878, decode.acc_seg: 70.0731, aux.loss_ce: 0.2870, aux.acc_seg: 63.2336, loss: 0.6748 +2022-05-05 11:08:38,118 - mmseg - INFO - Iter [10800/80000] lr: 1.242e-06, eta: 12:09:03, time: 0.596, data_time: 0.005, memory: 60248, decode.loss_ce: 0.4010, decode.acc_seg: 67.5323, aux.loss_ce: 0.2946, aux.acc_seg: 60.6932, loss: 0.6956 +2022-05-05 11:09:08,177 - mmseg - INFO - Iter [10850/80000] lr: 1.241e-06, eta: 12:08:21, time: 0.601, data_time: 0.004, memory: 60248, decode.loss_ce: 0.4111, decode.acc_seg: 68.5344, aux.loss_ce: 0.2934, aux.acc_seg: 61.5112, loss: 0.7045 +2022-05-05 11:09:37,880 - mmseg - INFO - Iter [10900/80000] lr: 1.240e-06, eta: 12:07:38, time: 0.594, data_time: 0.004, memory: 60248, decode.loss_ce: 0.4143, decode.acc_seg: 68.6874, aux.loss_ce: 0.2961, aux.acc_seg: 62.0926, loss: 0.7104 +2022-05-05 11:10:07,914 - mmseg - INFO - Iter [10950/80000] lr: 1.239e-06, eta: 12:06:56, time: 0.600, data_time: 0.005, memory: 60248, decode.loss_ce: 0.4028, decode.acc_seg: 68.8642, aux.loss_ce: 0.2765, aux.acc_seg: 63.2411, loss: 0.6793 +2022-05-05 11:10:37,613 - mmseg - INFO - Saving checkpoint at 11000 iterations +2022-05-05 11:10:57,973 - mmseg - INFO - Exp name: upernet_beit_adapter_large_512_80k_cocostuff10k_ss.py +2022-05-05 11:10:57,976 - mmseg - INFO - Iter [11000/80000] lr: 1.238e-06, eta: 12:08:20, time: 0.999, data_time: 0.004, memory: 60248, decode.loss_ce: 0.3741, decode.acc_seg: 69.6616, aux.loss_ce: 0.2713, aux.acc_seg: 63.3752, loss: 0.6454 +2022-05-05 11:11:27,931 - mmseg - INFO - Iter [11050/80000] lr: 1.237e-06, eta: 12:07:38, time: 0.601, data_time: 0.007, memory: 60248, decode.loss_ce: 0.3934, decode.acc_seg: 68.6430, aux.loss_ce: 0.2721, aux.acc_seg: 63.1226, loss: 0.6655 +2022-05-05 11:11:57,534 - mmseg - INFO - Iter [11100/80000] lr: 1.237e-06, eta: 12:06:54, time: 0.592, data_time: 0.005, memory: 60248, decode.loss_ce: 0.4208, decode.acc_seg: 69.4774, aux.loss_ce: 0.2926, aux.acc_seg: 62.9183, loss: 0.7134 +2022-05-05 11:12:27,718 - mmseg - INFO - Iter [11150/80000] lr: 1.236e-06, eta: 12:06:13, time: 0.604, data_time: 0.006, memory: 60248, decode.loss_ce: 0.4386, decode.acc_seg: 68.8680, aux.loss_ce: 0.3067, aux.acc_seg: 62.2274, loss: 0.7452 +2022-05-05 11:12:57,358 - mmseg - INFO - Iter [11200/80000] lr: 1.235e-06, eta: 12:05:29, time: 0.593, data_time: 0.005, memory: 60248, decode.loss_ce: 0.4087, decode.acc_seg: 68.9677, aux.loss_ce: 0.2824, aux.acc_seg: 62.8642, loss: 0.6910 +2022-05-05 11:13:29,710 - mmseg - INFO - Iter [11250/80000] lr: 1.234e-06, eta: 12:05:02, time: 0.647, data_time: 0.055, memory: 60248, decode.loss_ce: 0.3966, decode.acc_seg: 68.5361, aux.loss_ce: 0.2756, aux.acc_seg: 62.9545, loss: 0.6722 +2022-05-05 11:13:59,550 - mmseg - INFO - Iter [11300/80000] lr: 1.233e-06, eta: 12:04:19, time: 0.597, data_time: 0.004, memory: 60248, decode.loss_ce: 0.4031, decode.acc_seg: 68.4958, aux.loss_ce: 0.2846, aux.acc_seg: 62.2653, loss: 0.6876 +2022-05-05 11:14:29,233 - mmseg - INFO - Iter [11350/80000] lr: 1.232e-06, eta: 12:03:36, time: 0.594, data_time: 0.005, memory: 60248, decode.loss_ce: 0.3815, decode.acc_seg: 69.9612, aux.loss_ce: 0.2800, aux.acc_seg: 63.4778, loss: 0.6615 +2022-05-05 11:14:59,540 - mmseg - INFO - Iter [11400/80000] lr: 1.231e-06, eta: 12:02:57, time: 0.606, data_time: 0.004, memory: 60248, decode.loss_ce: 0.4044, decode.acc_seg: 68.5902, aux.loss_ce: 0.2892, aux.acc_seg: 61.6073, loss: 0.6936 +2022-05-05 11:15:29,432 - mmseg - INFO - Iter [11450/80000] lr: 1.230e-06, eta: 12:02:15, time: 0.598, data_time: 0.006, memory: 60248, decode.loss_ce: 0.3633, decode.acc_seg: 69.1959, aux.loss_ce: 0.2735, aux.acc_seg: 62.3991, loss: 0.6368 +2022-05-05 11:15:59,155 - mmseg - INFO - Iter [11500/80000] lr: 1.229e-06, eta: 12:01:32, time: 0.594, data_time: 0.004, memory: 60248, decode.loss_ce: 0.3947, decode.acc_seg: 69.4890, aux.loss_ce: 0.2733, aux.acc_seg: 63.1238, loss: 0.6680 +2022-05-05 11:16:29,360 - mmseg - INFO - Iter [11550/80000] lr: 1.229e-06, eta: 12:00:52, time: 0.604, data_time: 0.005, memory: 60248, decode.loss_ce: 0.4003, decode.acc_seg: 68.7949, aux.loss_ce: 0.2793, aux.acc_seg: 63.0201, loss: 0.6796 +2022-05-05 11:16:59,190 - mmseg - INFO - Iter [11600/80000] lr: 1.228e-06, eta: 12:00:10, time: 0.597, data_time: 0.005, memory: 60248, decode.loss_ce: 0.3822, decode.acc_seg: 69.9419, aux.loss_ce: 0.2691, aux.acc_seg: 64.3092, loss: 0.6513 +2022-05-05 11:17:28,992 - mmseg - INFO - Iter [11650/80000] lr: 1.227e-06, eta: 11:59:28, time: 0.596, data_time: 0.004, memory: 60248, decode.loss_ce: 0.3915, decode.acc_seg: 69.9516, aux.loss_ce: 0.2671, aux.acc_seg: 64.4722, loss: 0.6585 +2022-05-05 11:17:58,716 - mmseg - INFO - Iter [11700/80000] lr: 1.226e-06, eta: 11:58:45, time: 0.594, data_time: 0.005, memory: 60248, decode.loss_ce: 0.3852, decode.acc_seg: 69.3708, aux.loss_ce: 0.2685, aux.acc_seg: 63.7018, loss: 0.6538 +2022-05-05 11:18:28,576 - mmseg - INFO - Iter [11750/80000] lr: 1.225e-06, eta: 11:58:04, time: 0.597, data_time: 0.005, memory: 60248, decode.loss_ce: 0.3756, decode.acc_seg: 70.0346, aux.loss_ce: 0.2741, aux.acc_seg: 63.5683, loss: 0.6497 +2022-05-05 11:18:58,762 - mmseg - INFO - Iter [11800/80000] lr: 1.224e-06, eta: 11:57:24, time: 0.603, data_time: 0.004, memory: 60248, decode.loss_ce: 0.4111, decode.acc_seg: 70.1994, aux.loss_ce: 0.2808, aux.acc_seg: 64.2322, loss: 0.6919 +2022-05-05 11:19:31,280 - mmseg - INFO - Iter [11850/80000] lr: 1.223e-06, eta: 11:56:58, time: 0.649, data_time: 0.057, memory: 60248, decode.loss_ce: 0.3716, decode.acc_seg: 69.2552, aux.loss_ce: 0.2716, aux.acc_seg: 62.5196, loss: 0.6433 +2022-05-05 11:20:01,414 - mmseg - INFO - Iter [11900/80000] lr: 1.222e-06, eta: 11:56:19, time: 0.605, data_time: 0.006, memory: 60248, decode.loss_ce: 0.3810, decode.acc_seg: 70.1354, aux.loss_ce: 0.2638, aux.acc_seg: 64.2577, loss: 0.6447 +2022-05-05 11:20:31,134 - mmseg - INFO - Iter [11950/80000] lr: 1.221e-06, eta: 11:55:37, time: 0.594, data_time: 0.005, memory: 60248, decode.loss_ce: 0.3730, decode.acc_seg: 69.5429, aux.loss_ce: 0.2818, aux.acc_seg: 62.2697, loss: 0.6548 +2022-05-05 11:21:01,021 - mmseg - INFO - Saving checkpoint at 12000 iterations +2022-05-05 11:21:21,038 - mmseg - INFO - Exp name: upernet_beit_adapter_large_512_80k_cocostuff10k_ss.py +2022-05-05 11:21:21,041 - mmseg - INFO - Iter [12000/80000] lr: 1.220e-06, eta: 11:56:48, time: 0.995, data_time: 0.005, memory: 60248, decode.loss_ce: 0.3721, decode.acc_seg: 70.3151, aux.loss_ce: 0.2615, aux.acc_seg: 64.5911, loss: 0.6336 +2022-05-05 11:21:51,014 - mmseg - INFO - Iter [12050/80000] lr: 1.220e-06, eta: 11:56:08, time: 0.603, data_time: 0.007, memory: 60248, decode.loss_ce: 0.3548, decode.acc_seg: 69.5725, aux.loss_ce: 0.2536, aux.acc_seg: 63.6968, loss: 0.6084 +2022-05-05 11:22:20,711 - mmseg - INFO - Iter [12100/80000] lr: 1.219e-06, eta: 11:55:26, time: 0.594, data_time: 0.004, memory: 60248, decode.loss_ce: 0.3752, decode.acc_seg: 67.4781, aux.loss_ce: 0.2603, aux.acc_seg: 61.5296, loss: 0.6356 +2022-05-05 11:22:50,581 - mmseg - INFO - Iter [12150/80000] lr: 1.218e-06, eta: 11:54:44, time: 0.597, data_time: 0.004, memory: 60248, decode.loss_ce: 0.3848, decode.acc_seg: 70.7574, aux.loss_ce: 0.2689, aux.acc_seg: 65.3408, loss: 0.6537 +2022-05-05 11:23:20,370 - mmseg - INFO - Iter [12200/80000] lr: 1.217e-06, eta: 11:54:03, time: 0.596, data_time: 0.004, memory: 60248, decode.loss_ce: 0.3684, decode.acc_seg: 69.8212, aux.loss_ce: 0.2619, aux.acc_seg: 64.0040, loss: 0.6303 +2022-05-05 11:23:50,153 - mmseg - INFO - Iter [12250/80000] lr: 1.216e-06, eta: 11:53:21, time: 0.596, data_time: 0.005, memory: 60248, decode.loss_ce: 0.3555, decode.acc_seg: 68.6477, aux.loss_ce: 0.2525, aux.acc_seg: 62.1634, loss: 0.6080 +2022-05-05 11:24:20,079 - mmseg - INFO - Iter [12300/80000] lr: 1.215e-06, eta: 11:52:40, time: 0.599, data_time: 0.004, memory: 60248, decode.loss_ce: 0.3866, decode.acc_seg: 69.5885, aux.loss_ce: 0.2658, aux.acc_seg: 63.9953, loss: 0.6524 +2022-05-05 11:24:49,968 - mmseg - INFO - Iter [12350/80000] lr: 1.214e-06, eta: 11:51:59, time: 0.598, data_time: 0.004, memory: 60248, decode.loss_ce: 0.3653, decode.acc_seg: 70.2783, aux.loss_ce: 0.2566, aux.acc_seg: 64.9539, loss: 0.6219 +2022-05-05 11:25:22,501 - mmseg - INFO - Iter [12400/80000] lr: 1.213e-06, eta: 11:51:33, time: 0.651, data_time: 0.055, memory: 60248, decode.loss_ce: 0.3713, decode.acc_seg: 70.0610, aux.loss_ce: 0.2568, aux.acc_seg: 64.4514, loss: 0.6281 +2022-05-05 11:25:52,194 - mmseg - INFO - Iter [12450/80000] lr: 1.212e-06, eta: 11:50:51, time: 0.594, data_time: 0.004, memory: 60248, decode.loss_ce: 0.3695, decode.acc_seg: 71.3232, aux.loss_ce: 0.2601, aux.acc_seg: 65.3594, loss: 0.6296 +2022-05-05 11:26:22,095 - mmseg - INFO - Iter [12500/80000] lr: 1.211e-06, eta: 11:50:11, time: 0.598, data_time: 0.005, memory: 60248, decode.loss_ce: 0.3631, decode.acc_seg: 69.3670, aux.loss_ce: 0.2535, aux.acc_seg: 63.7111, loss: 0.6166 +2022-05-05 11:26:51,665 - mmseg - INFO - Iter [12550/80000] lr: 1.211e-06, eta: 11:49:28, time: 0.591, data_time: 0.005, memory: 60248, decode.loss_ce: 0.3643, decode.acc_seg: 69.5374, aux.loss_ce: 0.2686, aux.acc_seg: 62.9084, loss: 0.6329 +2022-05-05 11:27:21,478 - mmseg - INFO - Iter [12600/80000] lr: 1.210e-06, eta: 11:48:48, time: 0.596, data_time: 0.004, memory: 60248, decode.loss_ce: 0.3401, decode.acc_seg: 70.8031, aux.loss_ce: 0.2422, aux.acc_seg: 65.4248, loss: 0.5824 +2022-05-05 11:27:51,292 - mmseg - INFO - Iter [12650/80000] lr: 1.209e-06, eta: 11:48:07, time: 0.596, data_time: 0.004, memory: 60248, decode.loss_ce: 0.3592, decode.acc_seg: 70.5605, aux.loss_ce: 0.2643, aux.acc_seg: 64.2038, loss: 0.6235 +2022-05-05 11:28:21,461 - mmseg - INFO - Iter [12700/80000] lr: 1.208e-06, eta: 11:47:28, time: 0.603, data_time: 0.004, memory: 60248, decode.loss_ce: 0.3683, decode.acc_seg: 69.3042, aux.loss_ce: 0.2524, aux.acc_seg: 63.9934, loss: 0.6207 +2022-05-05 11:28:51,151 - mmseg - INFO - Iter [12750/80000] lr: 1.207e-06, eta: 11:46:47, time: 0.594, data_time: 0.004, memory: 60248, decode.loss_ce: 0.3653, decode.acc_seg: 70.6399, aux.loss_ce: 0.2588, aux.acc_seg: 64.8554, loss: 0.6241 +2022-05-05 11:29:20,829 - mmseg - INFO - Iter [12800/80000] lr: 1.206e-06, eta: 11:46:05, time: 0.593, data_time: 0.004, memory: 60248, decode.loss_ce: 0.3567, decode.acc_seg: 68.4262, aux.loss_ce: 0.2537, aux.acc_seg: 62.6291, loss: 0.6104 +2022-05-05 11:29:50,632 - mmseg - INFO - Iter [12850/80000] lr: 1.205e-06, eta: 11:45:25, time: 0.596, data_time: 0.005, memory: 60248, decode.loss_ce: 0.3470, decode.acc_seg: 71.1105, aux.loss_ce: 0.2463, aux.acc_seg: 65.2233, loss: 0.5933 +2022-05-05 11:30:20,764 - mmseg - INFO - Iter [12900/80000] lr: 1.204e-06, eta: 11:44:46, time: 0.603, data_time: 0.005, memory: 60248, decode.loss_ce: 0.3636, decode.acc_seg: 70.4293, aux.loss_ce: 0.2490, aux.acc_seg: 64.9139, loss: 0.6126 +2022-05-05 11:30:53,466 - mmseg - INFO - Iter [12950/80000] lr: 1.203e-06, eta: 11:44:21, time: 0.654, data_time: 0.051, memory: 60248, decode.loss_ce: 0.3478, decode.acc_seg: 69.6873, aux.loss_ce: 0.2485, aux.acc_seg: 63.9757, loss: 0.5964 +2022-05-05 11:31:23,270 - mmseg - INFO - Saving checkpoint at 13000 iterations +2022-05-05 11:31:43,884 - mmseg - INFO - Exp name: upernet_beit_adapter_large_512_80k_cocostuff10k_ss.py +2022-05-05 11:31:43,891 - mmseg - INFO - Iter [13000/80000] lr: 1.202e-06, eta: 11:45:26, time: 1.006, data_time: 0.004, memory: 60248, decode.loss_ce: 0.3334, decode.acc_seg: 70.3201, aux.loss_ce: 0.2388, aux.acc_seg: 64.6427, loss: 0.5722 +2022-05-05 11:32:14,224 - mmseg - INFO - Iter [13050/80000] lr: 1.202e-06, eta: 11:44:49, time: 0.609, data_time: 0.009, memory: 60248, decode.loss_ce: 0.3407, decode.acc_seg: 69.8394, aux.loss_ce: 0.2507, aux.acc_seg: 63.5836, loss: 0.5914 +2022-05-05 11:32:44,139 - mmseg - INFO - Iter [13100/80000] lr: 1.201e-06, eta: 11:44:09, time: 0.598, data_time: 0.004, memory: 60248, decode.loss_ce: 0.3545, decode.acc_seg: 69.8704, aux.loss_ce: 0.2529, aux.acc_seg: 63.9123, loss: 0.6073 +2022-05-05 11:33:14,373 - mmseg - INFO - Iter [13150/80000] lr: 1.200e-06, eta: 11:43:30, time: 0.604, data_time: 0.005, memory: 60248, decode.loss_ce: 0.3573, decode.acc_seg: 70.0524, aux.loss_ce: 0.2539, aux.acc_seg: 63.7462, loss: 0.6112 +2022-05-05 11:33:43,981 - mmseg - INFO - Iter [13200/80000] lr: 1.199e-06, eta: 11:42:49, time: 0.592, data_time: 0.005, memory: 60248, decode.loss_ce: 0.3226, decode.acc_seg: 71.9012, aux.loss_ce: 0.2361, aux.acc_seg: 66.3450, loss: 0.5587 +2022-05-05 11:34:13,639 - mmseg - INFO - Iter [13250/80000] lr: 1.198e-06, eta: 11:42:08, time: 0.593, data_time: 0.005, memory: 60248, decode.loss_ce: 0.3764, decode.acc_seg: 70.0641, aux.loss_ce: 0.2616, aux.acc_seg: 64.4762, loss: 0.6379 +2022-05-05 11:34:43,616 - mmseg - INFO - Iter [13300/80000] lr: 1.197e-06, eta: 11:41:28, time: 0.599, data_time: 0.005, memory: 60248, decode.loss_ce: 0.3620, decode.acc_seg: 69.0079, aux.loss_ce: 0.2526, aux.acc_seg: 63.3646, loss: 0.6146 +2022-05-05 11:35:13,253 - mmseg - INFO - Iter [13350/80000] lr: 1.196e-06, eta: 11:40:47, time: 0.593, data_time: 0.005, memory: 60248, decode.loss_ce: 0.3603, decode.acc_seg: 70.8040, aux.loss_ce: 0.2544, aux.acc_seg: 65.5350, loss: 0.6147 +2022-05-05 11:35:43,364 - mmseg - INFO - Iter [13400/80000] lr: 1.195e-06, eta: 11:40:08, time: 0.602, data_time: 0.005, memory: 60248, decode.loss_ce: 0.3695, decode.acc_seg: 69.7266, aux.loss_ce: 0.2465, aux.acc_seg: 64.3238, loss: 0.6160 +2022-05-05 11:36:12,952 - mmseg - INFO - Iter [13450/80000] lr: 1.194e-06, eta: 11:39:27, time: 0.592, data_time: 0.004, memory: 60248, decode.loss_ce: 0.3419, decode.acc_seg: 69.2610, aux.loss_ce: 0.2317, aux.acc_seg: 63.9947, loss: 0.5736 +2022-05-05 11:36:45,413 - mmseg - INFO - Iter [13500/80000] lr: 1.194e-06, eta: 11:39:00, time: 0.649, data_time: 0.054, memory: 60248, decode.loss_ce: 0.3367, decode.acc_seg: 70.7091, aux.loss_ce: 0.2298, aux.acc_seg: 65.4972, loss: 0.5665 +2022-05-05 11:37:14,923 - mmseg - INFO - Iter [13550/80000] lr: 1.193e-06, eta: 11:38:19, time: 0.590, data_time: 0.005, memory: 60248, decode.loss_ce: 0.3229, decode.acc_seg: 70.5775, aux.loss_ce: 0.2305, aux.acc_seg: 65.2340, loss: 0.5534 +2022-05-05 11:37:44,531 - mmseg - INFO - Iter [13600/80000] lr: 1.192e-06, eta: 11:37:38, time: 0.592, data_time: 0.004, memory: 60248, decode.loss_ce: 0.3499, decode.acc_seg: 71.1939, aux.loss_ce: 0.2440, aux.acc_seg: 65.6327, loss: 0.5939 +2022-05-05 11:38:14,105 - mmseg - INFO - Iter [13650/80000] lr: 1.191e-06, eta: 11:36:57, time: 0.591, data_time: 0.004, memory: 60248, decode.loss_ce: 0.3403, decode.acc_seg: 70.1939, aux.loss_ce: 0.2497, aux.acc_seg: 63.9531, loss: 0.5900 +2022-05-05 11:38:43,901 - mmseg - INFO - Iter [13700/80000] lr: 1.190e-06, eta: 11:36:17, time: 0.596, data_time: 0.004, memory: 60248, decode.loss_ce: 0.3558, decode.acc_seg: 70.2814, aux.loss_ce: 0.2497, aux.acc_seg: 64.6416, loss: 0.6055 +2022-05-05 11:39:13,607 - mmseg - INFO - Iter [13750/80000] lr: 1.189e-06, eta: 11:35:37, time: 0.594, data_time: 0.005, memory: 60248, decode.loss_ce: 0.3376, decode.acc_seg: 71.4161, aux.loss_ce: 0.2414, aux.acc_seg: 65.5927, loss: 0.5790 +2022-05-05 11:39:43,214 - mmseg - INFO - Iter [13800/80000] lr: 1.188e-06, eta: 11:34:56, time: 0.593, data_time: 0.005, memory: 60248, decode.loss_ce: 0.3320, decode.acc_seg: 70.8632, aux.loss_ce: 0.2326, aux.acc_seg: 65.7080, loss: 0.5646 +2022-05-05 11:40:12,838 - mmseg - INFO - Iter [13850/80000] lr: 1.187e-06, eta: 11:34:16, time: 0.592, data_time: 0.004, memory: 60248, decode.loss_ce: 0.3482, decode.acc_seg: 70.9457, aux.loss_ce: 0.2402, aux.acc_seg: 65.6899, loss: 0.5884 +2022-05-05 11:40:42,264 - mmseg - INFO - Iter [13900/80000] lr: 1.186e-06, eta: 11:33:35, time: 0.589, data_time: 0.004, memory: 60248, decode.loss_ce: 0.3600, decode.acc_seg: 69.4894, aux.loss_ce: 0.2523, aux.acc_seg: 63.2232, loss: 0.6123 +2022-05-05 11:41:12,079 - mmseg - INFO - Iter [13950/80000] lr: 1.185e-06, eta: 11:32:55, time: 0.596, data_time: 0.004, memory: 60248, decode.loss_ce: 0.3507, decode.acc_seg: 69.7386, aux.loss_ce: 0.2406, aux.acc_seg: 64.1714, loss: 0.5913 +2022-05-05 11:41:41,764 - mmseg - INFO - Saving checkpoint at 14000 iterations +2022-05-05 11:42:02,126 - mmseg - INFO - Exp name: upernet_beit_adapter_large_512_80k_cocostuff10k_ss.py +2022-05-05 11:42:02,128 - mmseg - INFO - Iter [14000/80000] lr: 1.185e-06, eta: 11:33:51, time: 0.999, data_time: 0.006, memory: 60248, decode.loss_ce: 0.3171, decode.acc_seg: 71.4592, aux.loss_ce: 0.2277, aux.acc_seg: 65.9477, loss: 0.5447 +2022-05-05 11:42:32,013 - mmseg - INFO - Iter [14050/80000] lr: 1.184e-06, eta: 11:33:12, time: 0.600, data_time: 0.006, memory: 60248, decode.loss_ce: 0.3344, decode.acc_seg: 70.9511, aux.loss_ce: 0.2328, aux.acc_seg: 65.8736, loss: 0.5672 +2022-05-05 11:43:04,347 - mmseg - INFO - Iter [14100/80000] lr: 1.183e-06, eta: 11:32:44, time: 0.647, data_time: 0.058, memory: 60248, decode.loss_ce: 0.3239, decode.acc_seg: 70.3343, aux.loss_ce: 0.2331, aux.acc_seg: 64.9953, loss: 0.5570 +2022-05-05 11:43:34,002 - mmseg - INFO - Iter [14150/80000] lr: 1.182e-06, eta: 11:32:04, time: 0.593, data_time: 0.005, memory: 60248, decode.loss_ce: 0.3419, decode.acc_seg: 70.5934, aux.loss_ce: 0.2315, aux.acc_seg: 65.0590, loss: 0.5734 +2022-05-05 11:44:03,883 - mmseg - INFO - Iter [14200/80000] lr: 1.181e-06, eta: 11:31:25, time: 0.598, data_time: 0.004, memory: 60248, decode.loss_ce: 0.3251, decode.acc_seg: 69.7625, aux.loss_ce: 0.2279, aux.acc_seg: 64.8957, loss: 0.5530 +2022-05-05 11:44:33,619 - mmseg - INFO - Iter [14250/80000] lr: 1.180e-06, eta: 11:30:45, time: 0.594, data_time: 0.005, memory: 60248, decode.loss_ce: 0.3400, decode.acc_seg: 70.3158, aux.loss_ce: 0.2336, aux.acc_seg: 65.2718, loss: 0.5736 +2022-05-05 11:45:03,643 - mmseg - INFO - Iter [14300/80000] lr: 1.179e-06, eta: 11:30:07, time: 0.601, data_time: 0.005, memory: 60248, decode.loss_ce: 0.3325, decode.acc_seg: 70.5668, aux.loss_ce: 0.2382, aux.acc_seg: 64.6701, loss: 0.5707 +2022-05-05 11:45:33,273 - mmseg - INFO - Iter [14350/80000] lr: 1.178e-06, eta: 11:29:26, time: 0.593, data_time: 0.004, memory: 60248, decode.loss_ce: 0.3071, decode.acc_seg: 69.8214, aux.loss_ce: 0.2170, aux.acc_seg: 65.1035, loss: 0.5242 +2022-05-05 11:46:03,370 - mmseg - INFO - Iter [14400/80000] lr: 1.177e-06, eta: 11:28:48, time: 0.602, data_time: 0.004, memory: 60248, decode.loss_ce: 0.3331, decode.acc_seg: 71.9581, aux.loss_ce: 0.2384, aux.acc_seg: 66.4926, loss: 0.5715 +2022-05-05 11:46:33,026 - mmseg - INFO - Iter [14450/80000] lr: 1.176e-06, eta: 11:28:09, time: 0.593, data_time: 0.004, memory: 60248, decode.loss_ce: 0.3245, decode.acc_seg: 69.2593, aux.loss_ce: 0.2300, aux.acc_seg: 63.7440, loss: 0.5544 +2022-05-05 11:47:03,289 - mmseg - INFO - Iter [14500/80000] lr: 1.176e-06, eta: 11:27:32, time: 0.605, data_time: 0.005, memory: 60248, decode.loss_ce: 0.3391, decode.acc_seg: 71.0253, aux.loss_ce: 0.2238, aux.acc_seg: 66.8211, loss: 0.5629 +2022-05-05 11:47:32,938 - mmseg - INFO - Iter [14550/80000] lr: 1.175e-06, eta: 11:26:52, time: 0.593, data_time: 0.004, memory: 60248, decode.loss_ce: 0.3591, decode.acc_seg: 70.7948, aux.loss_ce: 0.2455, aux.acc_seg: 65.0911, loss: 0.6046 +2022-05-05 11:48:02,645 - mmseg - INFO - Iter [14600/80000] lr: 1.174e-06, eta: 11:26:12, time: 0.594, data_time: 0.004, memory: 60248, decode.loss_ce: 0.3163, decode.acc_seg: 70.9974, aux.loss_ce: 0.2140, aux.acc_seg: 66.5040, loss: 0.5303 +2022-05-05 11:48:35,100 - mmseg - INFO - Iter [14650/80000] lr: 1.173e-06, eta: 11:25:45, time: 0.649, data_time: 0.058, memory: 60248, decode.loss_ce: 0.3248, decode.acc_seg: 70.8974, aux.loss_ce: 0.2323, aux.acc_seg: 65.3939, loss: 0.5571 +2022-05-05 11:49:05,232 - mmseg - INFO - Iter [14700/80000] lr: 1.172e-06, eta: 11:25:08, time: 0.603, data_time: 0.004, memory: 60248, decode.loss_ce: 0.3111, decode.acc_seg: 72.3681, aux.loss_ce: 0.2251, aux.acc_seg: 67.0431, loss: 0.5363 +2022-05-05 11:49:35,039 - mmseg - INFO - Iter [14750/80000] lr: 1.171e-06, eta: 11:24:29, time: 0.596, data_time: 0.004, memory: 60248, decode.loss_ce: 0.3149, decode.acc_seg: 70.9396, aux.loss_ce: 0.2215, aux.acc_seg: 65.7889, loss: 0.5364 +2022-05-05 11:50:04,593 - mmseg - INFO - Iter [14800/80000] lr: 1.170e-06, eta: 11:23:49, time: 0.591, data_time: 0.004, memory: 60248, decode.loss_ce: 0.3167, decode.acc_seg: 70.1899, aux.loss_ce: 0.2226, aux.acc_seg: 64.9248, loss: 0.5393 +2022-05-05 11:50:34,641 - mmseg - INFO - Iter [14850/80000] lr: 1.169e-06, eta: 11:23:11, time: 0.601, data_time: 0.006, memory: 60248, decode.loss_ce: 0.3030, decode.acc_seg: 70.2390, aux.loss_ce: 0.2225, aux.acc_seg: 65.0088, loss: 0.5255 +2022-05-05 11:51:04,433 - mmseg - INFO - Iter [14900/80000] lr: 1.168e-06, eta: 11:22:32, time: 0.596, data_time: 0.004, memory: 60248, decode.loss_ce: 0.3295, decode.acc_seg: 72.1900, aux.loss_ce: 0.2355, aux.acc_seg: 66.7296, loss: 0.5650 +2022-05-05 11:51:34,265 - mmseg - INFO - Iter [14950/80000] lr: 1.167e-06, eta: 11:21:54, time: 0.597, data_time: 0.005, memory: 60248, decode.loss_ce: 0.3246, decode.acc_seg: 71.8890, aux.loss_ce: 0.2281, aux.acc_seg: 66.6199, loss: 0.5526 +2022-05-05 11:52:03,951 - mmseg - INFO - Saving checkpoint at 15000 iterations +2022-05-05 11:52:24,032 - mmseg - INFO - Exp name: upernet_beit_adapter_large_512_80k_cocostuff10k_ss.py +2022-05-05 11:52:24,035 - mmseg - INFO - Iter [15000/80000] lr: 1.167e-06, eta: 11:22:41, time: 0.991, data_time: 0.004, memory: 60248, decode.loss_ce: 0.2949, decode.acc_seg: 70.7955, aux.loss_ce: 0.2111, aux.acc_seg: 66.0754, loss: 0.5061 +2022-05-05 11:52:54,036 - mmseg - INFO - Iter [15050/80000] lr: 1.166e-06, eta: 11:22:04, time: 0.604, data_time: 0.008, memory: 60248, decode.loss_ce: 0.3388, decode.acc_seg: 70.5756, aux.loss_ce: 0.2334, aux.acc_seg: 65.3113, loss: 0.5722 +2022-05-05 11:53:23,963 - mmseg - INFO - Iter [15100/80000] lr: 1.165e-06, eta: 11:21:26, time: 0.599, data_time: 0.005, memory: 60248, decode.loss_ce: 0.3159, decode.acc_seg: 71.7682, aux.loss_ce: 0.2189, aux.acc_seg: 66.8356, loss: 0.5348 +2022-05-05 11:53:53,618 - mmseg - INFO - Iter [15150/80000] lr: 1.164e-06, eta: 11:20:46, time: 0.593, data_time: 0.005, memory: 60248, decode.loss_ce: 0.3366, decode.acc_seg: 69.5499, aux.loss_ce: 0.2296, aux.acc_seg: 65.1753, loss: 0.5661 +2022-05-05 11:54:25,709 - mmseg - INFO - Iter [15200/80000] lr: 1.163e-06, eta: 11:20:17, time: 0.642, data_time: 0.055, memory: 60248, decode.loss_ce: 0.3159, decode.acc_seg: 69.7068, aux.loss_ce: 0.2128, aux.acc_seg: 64.9920, loss: 0.5287 +2022-05-05 11:54:55,751 - mmseg - INFO - Iter [15250/80000] lr: 1.162e-06, eta: 11:19:39, time: 0.598, data_time: 0.004, memory: 60248, decode.loss_ce: 0.3027, decode.acc_seg: 72.4269, aux.loss_ce: 0.2158, aux.acc_seg: 67.3339, loss: 0.5184 +2022-05-05 11:55:25,765 - mmseg - INFO - Iter [15300/80000] lr: 1.161e-06, eta: 11:19:02, time: 0.603, data_time: 0.007, memory: 60248, decode.loss_ce: 0.3307, decode.acc_seg: 71.5842, aux.loss_ce: 0.2394, aux.acc_seg: 65.4088, loss: 0.5701 +2022-05-05 11:55:55,387 - mmseg - INFO - Iter [15350/80000] lr: 1.160e-06, eta: 11:18:23, time: 0.592, data_time: 0.004, memory: 60248, decode.loss_ce: 0.3380, decode.acc_seg: 71.9283, aux.loss_ce: 0.2289, aux.acc_seg: 67.1795, loss: 0.5668 +2022-05-05 11:56:25,002 - mmseg - INFO - Iter [15400/80000] lr: 1.159e-06, eta: 11:17:43, time: 0.592, data_time: 0.004, memory: 60248, decode.loss_ce: 0.2965, decode.acc_seg: 72.3017, aux.loss_ce: 0.2181, aux.acc_seg: 67.0177, loss: 0.5146 +2022-05-05 11:56:55,150 - mmseg - INFO - Iter [15450/80000] lr: 1.159e-06, eta: 11:17:06, time: 0.603, data_time: 0.004, memory: 60248, decode.loss_ce: 0.2972, decode.acc_seg: 71.8140, aux.loss_ce: 0.2210, aux.acc_seg: 66.4514, loss: 0.5182 +2022-05-05 11:57:25,345 - mmseg - INFO - Iter [15500/80000] lr: 1.158e-06, eta: 11:16:29, time: 0.604, data_time: 0.006, memory: 60248, decode.loss_ce: 0.3237, decode.acc_seg: 70.5843, aux.loss_ce: 0.2248, aux.acc_seg: 65.4034, loss: 0.5485 +2022-05-05 11:57:55,422 - mmseg - INFO - Iter [15550/80000] lr: 1.157e-06, eta: 11:15:52, time: 0.601, data_time: 0.004, memory: 60248, decode.loss_ce: 0.3162, decode.acc_seg: 70.6480, aux.loss_ce: 0.2205, aux.acc_seg: 65.3252, loss: 0.5367 +2022-05-05 11:58:25,537 - mmseg - INFO - Iter [15600/80000] lr: 1.156e-06, eta: 11:15:15, time: 0.602, data_time: 0.005, memory: 60248, decode.loss_ce: 0.3099, decode.acc_seg: 72.0234, aux.loss_ce: 0.2102, aux.acc_seg: 67.8382, loss: 0.5201 +2022-05-05 11:58:55,180 - mmseg - INFO - Iter [15650/80000] lr: 1.155e-06, eta: 11:14:36, time: 0.593, data_time: 0.005, memory: 60248, decode.loss_ce: 0.3102, decode.acc_seg: 72.1055, aux.loss_ce: 0.2111, aux.acc_seg: 67.4104, loss: 0.5213 +2022-05-05 11:59:24,712 - mmseg - INFO - Iter [15700/80000] lr: 1.154e-06, eta: 11:13:57, time: 0.591, data_time: 0.005, memory: 60248, decode.loss_ce: 0.3283, decode.acc_seg: 71.2108, aux.loss_ce: 0.2274, aux.acc_seg: 66.0676, loss: 0.5557 +2022-05-05 11:59:57,128 - mmseg - INFO - Iter [15750/80000] lr: 1.153e-06, eta: 11:13:30, time: 0.648, data_time: 0.058, memory: 60248, decode.loss_ce: 0.3043, decode.acc_seg: 70.2079, aux.loss_ce: 0.2146, aux.acc_seg: 65.0893, loss: 0.5190 +2022-05-05 12:00:28,861 - mmseg - INFO - Iter [15800/80000] lr: 1.152e-06, eta: 11:12:59, time: 0.635, data_time: 0.005, memory: 60248, decode.loss_ce: 0.2976, decode.acc_seg: 72.2012, aux.loss_ce: 0.2226, aux.acc_seg: 66.6436, loss: 0.5202 +2022-05-05 12:00:58,694 - mmseg - INFO - Iter [15850/80000] lr: 1.151e-06, eta: 11:12:21, time: 0.597, data_time: 0.004, memory: 60248, decode.loss_ce: 0.3121, decode.acc_seg: 71.6083, aux.loss_ce: 0.2199, aux.acc_seg: 66.8839, loss: 0.5320 +2022-05-05 12:01:28,543 - mmseg - INFO - Iter [15900/80000] lr: 1.150e-06, eta: 11:11:43, time: 0.597, data_time: 0.004, memory: 60248, decode.loss_ce: 0.3084, decode.acc_seg: 71.6338, aux.loss_ce: 0.2138, aux.acc_seg: 66.8018, loss: 0.5223 +2022-05-05 12:01:58,464 - mmseg - INFO - Iter [15950/80000] lr: 1.150e-06, eta: 11:11:06, time: 0.598, data_time: 0.004, memory: 60248, decode.loss_ce: 0.2970, decode.acc_seg: 71.9754, aux.loss_ce: 0.2129, aux.acc_seg: 66.9898, loss: 0.5098 +2022-05-05 12:02:28,560 - mmseg - INFO - Saving checkpoint at 16000 iterations +2022-05-05 12:02:48,745 - mmseg - INFO - Exp name: upernet_beit_adapter_large_512_80k_cocostuff10k_ss.py +2022-05-05 12:02:48,752 - mmseg - INFO - Iter [16000/80000] lr: 1.149e-06, eta: 11:11:49, time: 1.004, data_time: 0.004, memory: 60248, decode.loss_ce: 0.2924, decode.acc_seg: 71.5030, aux.loss_ce: 0.2018, aux.acc_seg: 67.1449, loss: 0.4942 +2022-05-05 12:03:18,462 - mmseg - INFO - per class results: +2022-05-05 12:03:18,472 - mmseg - INFO - ++------------------+-------+-------+ +| Class | IoU | Acc | ++------------------+-------+-------+ +| person | 83.03 | 94.17 | +| bicycle | 73.09 | 89.93 | +| car | 63.34 | 70.61 | +| motorcycle | 87.17 | 96.48 | +| airplane | 85.54 | 94.9 | +| bus | 85.22 | 90.68 | +| train | 72.73 | 97.51 | +| truck | 74.02 | 88.77 | +| boat | 73.44 | 88.9 | +| traffic light | 68.55 | 90.83 | +| fire hydrant | 85.1 | 97.85 | +| stop sign | 90.32 | 98.35 | +| parking meter | 75.97 | 80.26 | +| bench | 53.42 | 68.19 | +| bird | 75.98 | 82.46 | +| cat | 91.37 | 93.74 | +| dog | 91.91 | 96.06 | +| horse | 88.98 | 96.33 | +| sheep | 84.69 | 90.67 | +| cow | 94.32 | 98.77 | +| elephant | 91.83 | 96.61 | +| bear | 93.91 | 97.43 | +| zebra | 89.58 | 96.75 | +| giraffe | 85.69 | 93.45 | +| backpack | 24.56 | 52.83 | +| umbrella | 78.52 | 90.61 | +| handbag | 15.69 | 21.09 | +| tie | 0.0 | 0.0 | +| suitcase | 73.97 | 97.15 | +| frisbee | 92.67 | 95.81 | +| skis | 27.91 | 42.31 | +| snowboard | 65.36 | 80.08 | +| sports ball | 73.12 | 78.72 | +| kite | 62.3 | 90.84 | +| baseball bat | 53.37 | 66.46 | +| baseball glove | 0.85 | 0.85 | +| skateboard | 64.13 | 84.12 | +| surfboard | 89.22 | 94.65 | +| tennis racket | 57.45 | 62.17 | +| bottle | 73.91 | 84.08 | +| wine glass | 81.89 | 91.46 | +| cup | 66.59 | 91.51 | +| fork | 37.39 | 54.38 | +| knife | 73.45 | 84.29 | +| spoon | 39.32 | 55.46 | +| bowl | 53.53 | 65.92 | +| banana | 78.81 | 92.07 | +| apple | 77.34 | 92.61 | +| sandwich | 84.31 | 96.67 | +| orange | 68.51 | 88.08 | +| broccoli | 89.92 | 95.13 | +| carrot | 44.74 | 66.41 | +| hot dog | 51.83 | 98.44 | +| pizza | 91.97 | 94.26 | +| donut | 69.98 | 89.64 | +| cake | 60.54 | 69.61 | +| chair | 58.11 | 74.96 | +| couch | 71.45 | 92.24 | +| potted plant | 37.43 | 51.86 | +| bed | 74.12 | 85.39 | +| dining table | 64.79 | 76.13 | +| toilet | 88.22 | 96.2 | +| tv | 69.79 | 90.05 | +| laptop | 86.97 | 98.85 | +| mouse | 64.07 | 69.61 | +| remote | 71.88 | 86.85 | +| keyboard | 83.24 | 94.71 | +| cell phone | 76.27 | 96.44 | +| microwave | 58.69 | 73.93 | +| oven | 59.44 | 86.67 | +| toaster | 0.0 | 0.0 | +| sink | 67.36 | 73.68 | +| refrigerator | 87.38 | 93.78 | +| book | 77.4 | 88.85 | +| clock | 75.46 | 86.96 | +| vase | 62.32 | 94.27 | +| scissors | 77.83 | 89.32 | +| teddy bear | 19.98 | 20.52 | +| hair drier | 0.0 | 0.0 | +| toothbrush | 14.26 | 16.31 | +| banner | 28.65 | 48.17 | +| blanket | 20.52 | 21.5 | +| branch | 0.66 | 0.75 | +| bridge | 2.42 | 3.39 | +| building-other | 55.15 | 75.17 | +| bush | 30.63 | 41.1 | +| cabinet | 20.44 | 41.35 | +| cage | 9.03 | 10.35 | +| cardboard | 26.28 | 29.39 | +| carpet | 61.51 | 79.03 | +| ceiling-other | 68.43 | 83.61 | +| ceiling-tile | 10.77 | 13.28 | +| cloth | 8.0 | 13.41 | +| clothes | 20.92 | 30.72 | +| clouds | 50.71 | 64.05 | +| counter | 38.59 | 44.64 | +| cupboard | 55.21 | 70.53 | +| curtain | 65.07 | 73.91 | +| desk-stuff | 33.91 | 39.21 | +| dirt | 35.38 | 58.55 | +| door-stuff | 45.84 | 61.85 | +| fence | 41.71 | 73.77 | +| floor-marble | 0.0 | 0.0 | +| floor-other | 38.42 | 51.93 | +| floor-stone | 14.79 | 22.08 | +| floor-tile | 56.67 | 73.04 | +| floor-wood | 72.49 | 84.38 | +| flower | 18.44 | 40.32 | +| fog | 0.0 | 0.0 | +| food-other | 36.54 | 52.58 | +| fruit | 67.0 | 76.11 | +| furniture-other | 13.62 | 18.74 | +| grass | 74.63 | 86.39 | +| gravel | 28.3 | 36.3 | +| ground-other | 6.0 | 11.93 | +| hill | 32.05 | 47.6 | +| house | 24.83 | 34.3 | +| leaves | 10.77 | 17.63 | +| light | 36.79 | 51.13 | +| mat | 8.15 | 9.12 | +| metal | 15.37 | 20.65 | +| mirror-stuff | 43.95 | 64.89 | +| moss | 0.0 | 0.0 | +| mountain | 30.65 | 43.4 | +| mud | 6.29 | 10.45 | +| napkin | 59.23 | 59.95 | +| net | 20.65 | 23.43 | +| paper | 46.79 | 70.25 | +| pavement | 55.0 | 71.74 | +| pillow | 0.0 | 0.0 | +| plant-other | 32.88 | 45.11 | +| plastic | 26.54 | 33.46 | +| platform | 42.39 | 57.56 | +| playingfield | 68.02 | 80.95 | +| railing | 17.11 | 26.96 | +| railroad | 61.59 | 80.95 | +| river | 11.13 | 13.98 | +| road | 67.72 | 79.34 | +| rock | 51.33 | 69.8 | +| roof | 7.19 | 12.72 | +| rug | 55.68 | 80.47 | +| salad | 0.44 | 0.44 | +| sand | 72.87 | 87.08 | +| sea | 74.71 | 87.32 | +| shelf | 25.59 | 42.16 | +| sky-other | 60.89 | 77.56 | +| skyscraper | 10.74 | 15.42 | +| snow | 91.62 | 94.57 | +| solid-other | nan | nan | +| stairs | 29.27 | 40.64 | +| stone | 6.85 | 8.36 | +| straw | 19.26 | 33.14 | +| structural-other | 16.15 | 23.53 | +| table | 27.97 | 45.33 | +| tent | 79.36 | 85.26 | +| textile-other | 19.29 | 22.26 | +| towel | 38.3 | 48.24 | +| tree | 77.79 | 87.73 | +| vegetable | 40.54 | 69.89 | +| wall-brick | 39.44 | 51.1 | +| wall-concrete | 29.85 | 40.82 | +| wall-other | 61.34 | 81.56 | +| wall-panel | 6.09 | 6.73 | +| wall-stone | 33.44 | 40.85 | +| wall-tile | 64.06 | 86.78 | +| wall-wood | 40.49 | 62.42 | +| water-other | 34.77 | 54.61 | +| waterdrops | 0.0 | nan | +| window-blind | 39.04 | 63.69 | +| window-other | 47.87 | 63.66 | +| wood | 16.24 | 37.42 | ++------------------+-------+-------+ +2022-05-05 12:03:18,472 - mmseg - INFO - Summary: +2022-05-05 12:03:18,472 - mmseg - INFO - ++-------+-------+-------+ +| aAcc | mIoU | mAcc | ++-------+-------+-------+ +| 74.96 | 49.54 | 61.49 | ++-------+-------+-------+ +2022-05-05 12:03:18,475 - mmseg - INFO - The previous best checkpoint /mnt/lustre/chenzhe.vendor/workspace/ViT-Adapter/segmentation/work_dirs/upernet_beit_adapter_large_512_80k_cocostuff10k_ss/best_mIoU_iter_8000.pth was removed +2022-05-05 12:03:38,581 - mmseg - INFO - Now best checkpoint is saved as best_mIoU_iter_16000.pth. +2022-05-05 12:03:38,592 - mmseg - INFO - Best mIoU is 0.4954 at 16000 iter. +2022-05-05 12:03:38,603 - mmseg - INFO - Exp name: upernet_beit_adapter_large_512_80k_cocostuff10k_ss.py +2022-05-05 12:03:38,603 - mmseg - INFO - Iter(val) [125] aAcc: 0.7496, mIoU: 0.4954, mAcc: 0.6149, IoU.person: 0.8303, IoU.bicycle: 0.7309, IoU.car: 0.6334, IoU.motorcycle: 0.8717, IoU.airplane: 0.8554, IoU.bus: 0.8522, IoU.train: 0.7273, IoU.truck: 0.7402, IoU.boat: 0.7344, IoU.traffic light: 0.6855, IoU.fire hydrant: 0.8510, IoU.stop sign: 0.9032, IoU.parking meter: 0.7597, IoU.bench: 0.5342, IoU.bird: 0.7598, IoU.cat: 0.9137, IoU.dog: 0.9191, IoU.horse: 0.8898, IoU.sheep: 0.8469, IoU.cow: 0.9432, IoU.elephant: 0.9183, IoU.bear: 0.9391, IoU.zebra: 0.8958, IoU.giraffe: 0.8569, IoU.backpack: 0.2456, IoU.umbrella: 0.7852, IoU.handbag: 0.1569, IoU.tie: 0.0000, IoU.suitcase: 0.7397, IoU.frisbee: 0.9267, IoU.skis: 0.2791, IoU.snowboard: 0.6536, IoU.sports ball: 0.7312, IoU.kite: 0.6230, IoU.baseball bat: 0.5337, IoU.baseball glove: 0.0085, IoU.skateboard: 0.6413, IoU.surfboard: 0.8922, IoU.tennis racket: 0.5745, IoU.bottle: 0.7391, IoU.wine glass: 0.8189, IoU.cup: 0.6659, IoU.fork: 0.3739, IoU.knife: 0.7345, IoU.spoon: 0.3932, IoU.bowl: 0.5353, IoU.banana: 0.7881, IoU.apple: 0.7734, IoU.sandwich: 0.8431, IoU.orange: 0.6851, IoU.broccoli: 0.8992, IoU.carrot: 0.4474, IoU.hot dog: 0.5183, IoU.pizza: 0.9197, IoU.donut: 0.6998, IoU.cake: 0.6054, IoU.chair: 0.5811, IoU.couch: 0.7145, IoU.potted plant: 0.3743, IoU.bed: 0.7412, IoU.dining table: 0.6479, IoU.toilet: 0.8822, IoU.tv: 0.6979, IoU.laptop: 0.8697, IoU.mouse: 0.6407, IoU.remote: 0.7188, IoU.keyboard: 0.8324, IoU.cell phone: 0.7627, IoU.microwave: 0.5869, IoU.oven: 0.5944, IoU.toaster: 0.0000, IoU.sink: 0.6736, IoU.refrigerator: 0.8738, IoU.book: 0.7740, IoU.clock: 0.7546, IoU.vase: 0.6232, IoU.scissors: 0.7783, IoU.teddy bear: 0.1998, IoU.hair drier: 0.0000, IoU.toothbrush: 0.1426, IoU.banner: 0.2865, IoU.blanket: 0.2052, IoU.branch: 0.0066, IoU.bridge: 0.0242, IoU.building-other: 0.5515, IoU.bush: 0.3063, IoU.cabinet: 0.2044, IoU.cage: 0.0903, IoU.cardboard: 0.2628, IoU.carpet: 0.6151, IoU.ceiling-other: 0.6843, IoU.ceiling-tile: 0.1077, IoU.cloth: 0.0800, IoU.clothes: 0.2092, IoU.clouds: 0.5071, IoU.counter: 0.3859, IoU.cupboard: 0.5521, IoU.curtain: 0.6507, IoU.desk-stuff: 0.3391, IoU.dirt: 0.3538, IoU.door-stuff: 0.4584, IoU.fence: 0.4171, IoU.floor-marble: 0.0000, IoU.floor-other: 0.3842, IoU.floor-stone: 0.1479, IoU.floor-tile: 0.5667, IoU.floor-wood: 0.7249, IoU.flower: 0.1844, IoU.fog: 0.0000, IoU.food-other: 0.3654, IoU.fruit: 0.6700, IoU.furniture-other: 0.1362, IoU.grass: 0.7463, IoU.gravel: 0.2830, IoU.ground-other: 0.0600, IoU.hill: 0.3205, IoU.house: 0.2483, IoU.leaves: 0.1077, IoU.light: 0.3679, IoU.mat: 0.0815, IoU.metal: 0.1537, IoU.mirror-stuff: 0.4395, IoU.moss: 0.0000, IoU.mountain: 0.3065, IoU.mud: 0.0629, IoU.napkin: 0.5923, IoU.net: 0.2065, IoU.paper: 0.4679, IoU.pavement: 0.5500, IoU.pillow: 0.0000, IoU.plant-other: 0.3288, IoU.plastic: 0.2654, IoU.platform: 0.4239, IoU.playingfield: 0.6802, IoU.railing: 0.1711, IoU.railroad: 0.6159, IoU.river: 0.1113, IoU.road: 0.6772, IoU.rock: 0.5133, IoU.roof: 0.0719, IoU.rug: 0.5568, IoU.salad: 0.0044, IoU.sand: 0.7287, IoU.sea: 0.7471, IoU.shelf: 0.2559, IoU.sky-other: 0.6089, IoU.skyscraper: 0.1074, IoU.snow: 0.9162, IoU.solid-other: nan, IoU.stairs: 0.2927, IoU.stone: 0.0685, IoU.straw: 0.1926, IoU.structural-other: 0.1615, IoU.table: 0.2797, IoU.tent: 0.7936, IoU.textile-other: 0.1929, IoU.towel: 0.3830, IoU.tree: 0.7779, IoU.vegetable: 0.4054, IoU.wall-brick: 0.3944, IoU.wall-concrete: 0.2985, IoU.wall-other: 0.6134, IoU.wall-panel: 0.0609, IoU.wall-stone: 0.3344, IoU.wall-tile: 0.6406, IoU.wall-wood: 0.4049, IoU.water-other: 0.3477, IoU.waterdrops: 0.0000, IoU.window-blind: 0.3904, IoU.window-other: 0.4787, IoU.wood: 0.1624, Acc.person: 0.9417, Acc.bicycle: 0.8993, Acc.car: 0.7061, Acc.motorcycle: 0.9648, Acc.airplane: 0.9490, Acc.bus: 0.9068, Acc.train: 0.9751, Acc.truck: 0.8877, Acc.boat: 0.8890, Acc.traffic light: 0.9083, Acc.fire hydrant: 0.9785, Acc.stop sign: 0.9835, Acc.parking meter: 0.8026, Acc.bench: 0.6819, Acc.bird: 0.8246, Acc.cat: 0.9374, Acc.dog: 0.9606, Acc.horse: 0.9633, Acc.sheep: 0.9067, Acc.cow: 0.9877, Acc.elephant: 0.9661, Acc.bear: 0.9743, Acc.zebra: 0.9675, Acc.giraffe: 0.9345, Acc.backpack: 0.5283, Acc.umbrella: 0.9061, Acc.handbag: 0.2109, Acc.tie: 0.0000, Acc.suitcase: 0.9715, Acc.frisbee: 0.9581, Acc.skis: 0.4231, Acc.snowboard: 0.8008, Acc.sports ball: 0.7872, Acc.kite: 0.9084, Acc.baseball bat: 0.6646, Acc.baseball glove: 0.0085, Acc.skateboard: 0.8412, Acc.surfboard: 0.9465, Acc.tennis racket: 0.6217, Acc.bottle: 0.8408, Acc.wine glass: 0.9146, Acc.cup: 0.9151, Acc.fork: 0.5438, Acc.knife: 0.8429, Acc.spoon: 0.5546, Acc.bowl: 0.6592, Acc.banana: 0.9207, Acc.apple: 0.9261, Acc.sandwich: 0.9667, Acc.orange: 0.8808, Acc.broccoli: 0.9513, Acc.carrot: 0.6641, Acc.hot dog: 0.9844, Acc.pizza: 0.9426, Acc.donut: 0.8964, Acc.cake: 0.6961, Acc.chair: 0.7496, Acc.couch: 0.9224, Acc.potted plant: 0.5186, Acc.bed: 0.8539, Acc.dining table: 0.7613, Acc.toilet: 0.9620, Acc.tv: 0.9005, Acc.laptop: 0.9885, Acc.mouse: 0.6961, Acc.remote: 0.8685, Acc.keyboard: 0.9471, Acc.cell phone: 0.9644, Acc.microwave: 0.7393, Acc.oven: 0.8667, Acc.toaster: 0.0000, Acc.sink: 0.7368, Acc.refrigerator: 0.9378, Acc.book: 0.8885, Acc.clock: 0.8696, Acc.vase: 0.9427, Acc.scissors: 0.8932, Acc.teddy bear: 0.2052, Acc.hair drier: 0.0000, Acc.toothbrush: 0.1631, Acc.banner: 0.4817, Acc.blanket: 0.2150, Acc.branch: 0.0075, Acc.bridge: 0.0339, Acc.building-other: 0.7517, Acc.bush: 0.4110, Acc.cabinet: 0.4135, Acc.cage: 0.1035, Acc.cardboard: 0.2939, Acc.carpet: 0.7903, Acc.ceiling-other: 0.8361, Acc.ceiling-tile: 0.1328, Acc.cloth: 0.1341, Acc.clothes: 0.3072, Acc.clouds: 0.6405, Acc.counter: 0.4464, Acc.cupboard: 0.7053, Acc.curtain: 0.7391, Acc.desk-stuff: 0.3921, Acc.dirt: 0.5855, Acc.door-stuff: 0.6185, Acc.fence: 0.7377, Acc.floor-marble: 0.0000, Acc.floor-other: 0.5193, Acc.floor-stone: 0.2208, Acc.floor-tile: 0.7304, Acc.floor-wood: 0.8438, Acc.flower: 0.4032, Acc.fog: 0.0000, Acc.food-other: 0.5258, Acc.fruit: 0.7611, Acc.furniture-other: 0.1874, Acc.grass: 0.8639, Acc.gravel: 0.3630, Acc.ground-other: 0.1193, Acc.hill: 0.4760, Acc.house: 0.3430, Acc.leaves: 0.1763, Acc.light: 0.5113, Acc.mat: 0.0912, Acc.metal: 0.2065, Acc.mirror-stuff: 0.6489, Acc.moss: 0.0000, Acc.mountain: 0.4340, Acc.mud: 0.1045, Acc.napkin: 0.5995, Acc.net: 0.2343, Acc.paper: 0.7025, Acc.pavement: 0.7174, Acc.pillow: 0.0000, Acc.plant-other: 0.4511, Acc.plastic: 0.3346, Acc.platform: 0.5756, Acc.playingfield: 0.8095, Acc.railing: 0.2696, Acc.railroad: 0.8095, Acc.river: 0.1398, Acc.road: 0.7934, Acc.rock: 0.6980, Acc.roof: 0.1272, Acc.rug: 0.8047, Acc.salad: 0.0044, Acc.sand: 0.8708, Acc.sea: 0.8732, Acc.shelf: 0.4216, Acc.sky-other: 0.7756, Acc.skyscraper: 0.1542, Acc.snow: 0.9457, Acc.solid-other: nan, Acc.stairs: 0.4064, Acc.stone: 0.0836, Acc.straw: 0.3314, Acc.structural-other: 0.2353, Acc.table: 0.4533, Acc.tent: 0.8526, Acc.textile-other: 0.2226, Acc.towel: 0.4824, Acc.tree: 0.8773, Acc.vegetable: 0.6989, Acc.wall-brick: 0.5110, Acc.wall-concrete: 0.4082, Acc.wall-other: 0.8156, Acc.wall-panel: 0.0673, Acc.wall-stone: 0.4085, Acc.wall-tile: 0.8678, Acc.wall-wood: 0.6242, Acc.water-other: 0.5461, Acc.waterdrops: nan, Acc.window-blind: 0.6369, Acc.window-other: 0.6366, Acc.wood: 0.3742 +2022-05-05 12:04:08,933 - mmseg - INFO - Iter [16050/80000] lr: 1.148e-06, eta: 11:14:32, time: 1.603, data_time: 1.005, memory: 60248, decode.loss_ce: 0.2943, decode.acc_seg: 71.6261, aux.loss_ce: 0.2037, aux.acc_seg: 67.0591, loss: 0.4980 +2022-05-05 12:04:38,733 - mmseg - INFO - Iter [16100/80000] lr: 1.147e-06, eta: 11:13:53, time: 0.598, data_time: 0.007, memory: 60248, decode.loss_ce: 0.2931, decode.acc_seg: 72.7859, aux.loss_ce: 0.2173, aux.acc_seg: 67.1567, loss: 0.5103 +2022-05-05 12:05:09,103 - mmseg - INFO - Iter [16150/80000] lr: 1.146e-06, eta: 11:13:17, time: 0.608, data_time: 0.004, memory: 60248, decode.loss_ce: 0.3042, decode.acc_seg: 71.4480, aux.loss_ce: 0.2123, aux.acc_seg: 66.6468, loss: 0.5165 +2022-05-05 12:05:39,153 - mmseg - INFO - Iter [16200/80000] lr: 1.145e-06, eta: 11:12:39, time: 0.601, data_time: 0.007, memory: 60248, decode.loss_ce: 0.3336, decode.acc_seg: 71.4858, aux.loss_ce: 0.2200, aux.acc_seg: 66.9712, loss: 0.5536 +2022-05-05 12:06:09,123 - mmseg - INFO - Iter [16250/80000] lr: 1.144e-06, eta: 11:12:01, time: 0.599, data_time: 0.004, memory: 60248, decode.loss_ce: 0.3003, decode.acc_seg: 71.4924, aux.loss_ce: 0.1998, aux.acc_seg: 67.2960, loss: 0.5001 +2022-05-05 12:06:41,340 - mmseg - INFO - Iter [16300/80000] lr: 1.143e-06, eta: 11:11:31, time: 0.644, data_time: 0.052, memory: 60248, decode.loss_ce: 0.3048, decode.acc_seg: 71.7941, aux.loss_ce: 0.2134, aux.acc_seg: 66.8979, loss: 0.5182 +2022-05-05 12:07:11,049 - mmseg - INFO - Iter [16350/80000] lr: 1.142e-06, eta: 11:10:52, time: 0.594, data_time: 0.005, memory: 60248, decode.loss_ce: 0.2829, decode.acc_seg: 71.5417, aux.loss_ce: 0.1941, aux.acc_seg: 67.1469, loss: 0.4770 +2022-05-05 12:07:40,788 - mmseg - INFO - Iter [16400/80000] lr: 1.141e-06, eta: 11:10:13, time: 0.595, data_time: 0.004, memory: 60248, decode.loss_ce: 0.2986, decode.acc_seg: 72.1810, aux.loss_ce: 0.2099, aux.acc_seg: 67.1794, loss: 0.5085 +2022-05-05 12:08:10,590 - mmseg - INFO - Iter [16450/80000] lr: 1.141e-06, eta: 11:09:35, time: 0.596, data_time: 0.005, memory: 60248, decode.loss_ce: 0.3118, decode.acc_seg: 71.5560, aux.loss_ce: 0.2184, aux.acc_seg: 66.4572, loss: 0.5302 +2022-05-05 12:08:40,351 - mmseg - INFO - Iter [16500/80000] lr: 1.140e-06, eta: 11:08:56, time: 0.595, data_time: 0.005, memory: 60248, decode.loss_ce: 0.3029, decode.acc_seg: 72.2310, aux.loss_ce: 0.2116, aux.acc_seg: 67.1772, loss: 0.5145 +2022-05-05 12:09:10,314 - mmseg - INFO - Iter [16550/80000] lr: 1.139e-06, eta: 11:08:18, time: 0.599, data_time: 0.004, memory: 60248, decode.loss_ce: 0.3030, decode.acc_seg: 71.7308, aux.loss_ce: 0.2127, aux.acc_seg: 66.7077, loss: 0.5157 +2022-05-05 12:09:39,832 - mmseg - INFO - Iter [16600/80000] lr: 1.138e-06, eta: 11:07:39, time: 0.591, data_time: 0.005, memory: 60248, decode.loss_ce: 0.3067, decode.acc_seg: 72.0225, aux.loss_ce: 0.2099, aux.acc_seg: 67.5467, loss: 0.5166 +2022-05-05 12:10:09,596 - mmseg - INFO - Iter [16650/80000] lr: 1.137e-06, eta: 11:07:00, time: 0.595, data_time: 0.004, memory: 60248, decode.loss_ce: 0.3139, decode.acc_seg: 73.3960, aux.loss_ce: 0.2137, aux.acc_seg: 69.0466, loss: 0.5277 +2022-05-05 12:10:39,356 - mmseg - INFO - Iter [16700/80000] lr: 1.136e-06, eta: 11:06:21, time: 0.595, data_time: 0.004, memory: 60248, decode.loss_ce: 0.2972, decode.acc_seg: 71.6018, aux.loss_ce: 0.2119, aux.acc_seg: 66.5184, loss: 0.5091 +2022-05-05 12:11:08,860 - mmseg - INFO - Iter [16750/80000] lr: 1.135e-06, eta: 11:05:42, time: 0.590, data_time: 0.004, memory: 60248, decode.loss_ce: 0.2967, decode.acc_seg: 72.0663, aux.loss_ce: 0.2056, aux.acc_seg: 67.4169, loss: 0.5024 +2022-05-05 12:11:38,617 - mmseg - INFO - Iter [16800/80000] lr: 1.134e-06, eta: 11:05:04, time: 0.594, data_time: 0.005, memory: 60248, decode.loss_ce: 0.3152, decode.acc_seg: 72.0640, aux.loss_ce: 0.2136, aux.acc_seg: 67.1619, loss: 0.5289 +2022-05-05 12:12:08,262 - mmseg - INFO - Iter [16850/80000] lr: 1.133e-06, eta: 11:04:25, time: 0.594, data_time: 0.005, memory: 60248, decode.loss_ce: 0.3180, decode.acc_seg: 71.6626, aux.loss_ce: 0.2197, aux.acc_seg: 66.7282, loss: 0.5377 +2022-05-05 12:12:40,717 - mmseg - INFO - Iter [16900/80000] lr: 1.133e-06, eta: 11:03:57, time: 0.649, data_time: 0.051, memory: 60248, decode.loss_ce: 0.2924, decode.acc_seg: 72.9770, aux.loss_ce: 0.2051, aux.acc_seg: 68.2017, loss: 0.4975 +2022-05-05 12:13:10,681 - mmseg - INFO - Iter [16950/80000] lr: 1.132e-06, eta: 11:03:19, time: 0.599, data_time: 0.005, memory: 60248, decode.loss_ce: 0.2745, decode.acc_seg: 73.2883, aux.loss_ce: 0.1964, aux.acc_seg: 68.6923, loss: 0.4709 +2022-05-05 12:13:40,237 - mmseg - INFO - Saving checkpoint at 17000 iterations +2022-05-05 12:14:01,070 - mmseg - INFO - Exp name: upernet_beit_adapter_large_512_80k_cocostuff10k_ss.py +2022-05-05 12:14:01,079 - mmseg - INFO - Iter [17000/80000] lr: 1.131e-06, eta: 11:03:57, time: 1.006, data_time: 0.004, memory: 60248, decode.loss_ce: 0.2785, decode.acc_seg: 71.6219, aux.loss_ce: 0.1899, aux.acc_seg: 67.8612, loss: 0.4685 +2022-05-05 12:14:31,205 - mmseg - INFO - Iter [17050/80000] lr: 1.130e-06, eta: 11:03:20, time: 0.604, data_time: 0.006, memory: 60248, decode.loss_ce: 0.2942, decode.acc_seg: 73.4263, aux.loss_ce: 0.2105, aux.acc_seg: 68.4612, loss: 0.5047 +2022-05-05 12:15:01,175 - mmseg - INFO - Iter [17100/80000] lr: 1.129e-06, eta: 11:02:43, time: 0.599, data_time: 0.004, memory: 60248, decode.loss_ce: 0.2784, decode.acc_seg: 71.2288, aux.loss_ce: 0.2073, aux.acc_seg: 65.8661, loss: 0.4857 +2022-05-05 12:15:30,866 - mmseg - INFO - Iter [17150/80000] lr: 1.128e-06, eta: 11:02:04, time: 0.594, data_time: 0.004, memory: 60248, decode.loss_ce: 0.2891, decode.acc_seg: 71.3536, aux.loss_ce: 0.2015, aux.acc_seg: 66.4494, loss: 0.4905 +2022-05-05 12:16:00,540 - mmseg - INFO - Iter [17200/80000] lr: 1.127e-06, eta: 11:01:25, time: 0.593, data_time: 0.004, memory: 60248, decode.loss_ce: 0.2793, decode.acc_seg: 72.6588, aux.loss_ce: 0.1987, aux.acc_seg: 68.2176, loss: 0.4780 +2022-05-05 12:16:30,319 - mmseg - INFO - Iter [17250/80000] lr: 1.126e-06, eta: 11:00:47, time: 0.596, data_time: 0.005, memory: 60248, decode.loss_ce: 0.2874, decode.acc_seg: 71.3789, aux.loss_ce: 0.1962, aux.acc_seg: 67.2404, loss: 0.4836 +2022-05-05 12:17:00,195 - mmseg - INFO - Iter [17300/80000] lr: 1.125e-06, eta: 11:00:09, time: 0.597, data_time: 0.004, memory: 60248, decode.loss_ce: 0.2850, decode.acc_seg: 71.5390, aux.loss_ce: 0.2024, aux.acc_seg: 66.8090, loss: 0.4874 +2022-05-05 12:17:30,012 - mmseg - INFO - Iter [17350/80000] lr: 1.124e-06, eta: 10:59:31, time: 0.596, data_time: 0.004, memory: 60248, decode.loss_ce: 0.3083, decode.acc_seg: 71.2246, aux.loss_ce: 0.2025, aux.acc_seg: 66.9410, loss: 0.5109 +2022-05-05 12:17:59,686 - mmseg - INFO - Iter [17400/80000] lr: 1.124e-06, eta: 10:58:53, time: 0.594, data_time: 0.005, memory: 60248, decode.loss_ce: 0.2702, decode.acc_seg: 71.9542, aux.loss_ce: 0.1886, aux.acc_seg: 67.4210, loss: 0.4589 +2022-05-05 12:18:32,068 - mmseg - INFO - Iter [17450/80000] lr: 1.123e-06, eta: 10:58:24, time: 0.647, data_time: 0.058, memory: 60248, decode.loss_ce: 0.2841, decode.acc_seg: 71.8764, aux.loss_ce: 0.1948, aux.acc_seg: 67.8249, loss: 0.4790 +2022-05-05 12:19:01,647 - mmseg - INFO - Iter [17500/80000] lr: 1.122e-06, eta: 10:57:45, time: 0.592, data_time: 0.005, memory: 60248, decode.loss_ce: 0.2840, decode.acc_seg: 72.3883, aux.loss_ce: 0.2035, aux.acc_seg: 67.6669, loss: 0.4875 +2022-05-05 12:19:31,117 - mmseg - INFO - Iter [17550/80000] lr: 1.121e-06, eta: 10:57:06, time: 0.589, data_time: 0.004, memory: 60248, decode.loss_ce: 0.2827, decode.acc_seg: 71.9089, aux.loss_ce: 0.1932, aux.acc_seg: 67.8468, loss: 0.4759 +2022-05-05 12:20:00,800 - mmseg - INFO - Iter [17600/80000] lr: 1.120e-06, eta: 10:56:28, time: 0.594, data_time: 0.004, memory: 60248, decode.loss_ce: 0.2716, decode.acc_seg: 72.8009, aux.loss_ce: 0.1903, aux.acc_seg: 68.5429, loss: 0.4619 +2022-05-05 12:20:30,752 - mmseg - INFO - Iter [17650/80000] lr: 1.119e-06, eta: 10:55:51, time: 0.599, data_time: 0.004, memory: 60248, decode.loss_ce: 0.2967, decode.acc_seg: 71.3103, aux.loss_ce: 0.2059, aux.acc_seg: 66.5390, loss: 0.5026 +2022-05-05 12:21:00,519 - mmseg - INFO - Iter [17700/80000] lr: 1.118e-06, eta: 10:55:13, time: 0.595, data_time: 0.005, memory: 60248, decode.loss_ce: 0.2913, decode.acc_seg: 71.9437, aux.loss_ce: 0.2040, aux.acc_seg: 67.1815, loss: 0.4952 +2022-05-05 12:21:30,350 - mmseg - INFO - Iter [17750/80000] lr: 1.117e-06, eta: 10:54:35, time: 0.597, data_time: 0.005, memory: 60248, decode.loss_ce: 0.2794, decode.acc_seg: 72.6066, aux.loss_ce: 0.1929, aux.acc_seg: 68.5564, loss: 0.4723 +2022-05-05 12:22:00,003 - mmseg - INFO - Iter [17800/80000] lr: 1.116e-06, eta: 10:53:57, time: 0.593, data_time: 0.004, memory: 60248, decode.loss_ce: 0.2804, decode.acc_seg: 72.9316, aux.loss_ce: 0.1963, aux.acc_seg: 68.4201, loss: 0.4768 +2022-05-05 12:22:29,811 - mmseg - INFO - Iter [17850/80000] lr: 1.115e-06, eta: 10:53:20, time: 0.596, data_time: 0.004, memory: 60248, decode.loss_ce: 0.2788, decode.acc_seg: 71.7521, aux.loss_ce: 0.1880, aux.acc_seg: 67.7065, loss: 0.4668 +2022-05-05 12:22:59,401 - mmseg - INFO - Iter [17900/80000] lr: 1.115e-06, eta: 10:52:41, time: 0.592, data_time: 0.004, memory: 60248, decode.loss_ce: 0.2702, decode.acc_seg: 72.4974, aux.loss_ce: 0.1848, aux.acc_seg: 68.5473, loss: 0.4550 +2022-05-05 12:23:29,080 - mmseg - INFO - Iter [17950/80000] lr: 1.114e-06, eta: 10:52:03, time: 0.593, data_time: 0.005, memory: 60248, decode.loss_ce: 0.2872, decode.acc_seg: 72.0674, aux.loss_ce: 0.1954, aux.acc_seg: 67.8437, loss: 0.4826 +2022-05-05 12:24:01,208 - mmseg - INFO - Saving checkpoint at 18000 iterations +2022-05-05 12:24:21,437 - mmseg - INFO - Exp name: upernet_beit_adapter_large_512_80k_cocostuff10k_ss.py +2022-05-05 12:24:21,440 - mmseg - INFO - Iter [18000/80000] lr: 1.113e-06, eta: 10:52:43, time: 1.046, data_time: 0.057, memory: 60248, decode.loss_ce: 0.2874, decode.acc_seg: 72.0650, aux.loss_ce: 0.1984, aux.acc_seg: 67.5423, loss: 0.4858 +2022-05-05 12:24:51,402 - mmseg - INFO - Iter [18050/80000] lr: 1.112e-06, eta: 10:52:07, time: 0.601, data_time: 0.006, memory: 60248, decode.loss_ce: 0.2741, decode.acc_seg: 70.6256, aux.loss_ce: 0.1871, aux.acc_seg: 66.7052, loss: 0.4612 +2022-05-05 12:25:21,485 - mmseg - INFO - Iter [18100/80000] lr: 1.111e-06, eta: 10:51:30, time: 0.602, data_time: 0.005, memory: 60248, decode.loss_ce: 0.2932, decode.acc_seg: 71.8793, aux.loss_ce: 0.1957, aux.acc_seg: 67.7331, loss: 0.4890 +2022-05-05 12:25:51,374 - mmseg - INFO - Iter [18150/80000] lr: 1.110e-06, eta: 10:50:52, time: 0.597, data_time: 0.004, memory: 60248, decode.loss_ce: 0.2804, decode.acc_seg: 71.6935, aux.loss_ce: 0.1934, aux.acc_seg: 67.4930, loss: 0.4738 +2022-05-05 12:26:21,073 - mmseg - INFO - Iter [18200/80000] lr: 1.109e-06, eta: 10:50:15, time: 0.594, data_time: 0.005, memory: 60248, decode.loss_ce: 0.2907, decode.acc_seg: 73.2787, aux.loss_ce: 0.2010, aux.acc_seg: 68.8740, loss: 0.4917 +2022-05-05 12:26:50,921 - mmseg - INFO - Iter [18250/80000] lr: 1.108e-06, eta: 10:49:37, time: 0.597, data_time: 0.004, memory: 60248, decode.loss_ce: 0.2742, decode.acc_seg: 70.8904, aux.loss_ce: 0.1913, aux.acc_seg: 66.3867, loss: 0.4655 +2022-05-05 12:27:20,796 - mmseg - INFO - Iter [18300/80000] lr: 1.107e-06, eta: 10:49:00, time: 0.597, data_time: 0.004, memory: 60248, decode.loss_ce: 0.2838, decode.acc_seg: 72.5568, aux.loss_ce: 0.1906, aux.acc_seg: 68.8204, loss: 0.4744 +2022-05-05 12:27:51,107 - mmseg - INFO - Iter [18350/80000] lr: 1.106e-06, eta: 10:48:24, time: 0.606, data_time: 0.006, memory: 60248, decode.loss_ce: 0.2862, decode.acc_seg: 72.0887, aux.loss_ce: 0.1946, aux.acc_seg: 67.9772, loss: 0.4808 +2022-05-05 12:28:20,985 - mmseg - INFO - Iter [18400/80000] lr: 1.106e-06, eta: 10:47:47, time: 0.598, data_time: 0.005, memory: 60248, decode.loss_ce: 0.2760, decode.acc_seg: 73.1748, aux.loss_ce: 0.1903, aux.acc_seg: 69.0704, loss: 0.4663 +2022-05-05 12:28:50,732 - mmseg - INFO - Iter [18450/80000] lr: 1.105e-06, eta: 10:47:09, time: 0.595, data_time: 0.004, memory: 60248, decode.loss_ce: 0.2946, decode.acc_seg: 72.8018, aux.loss_ce: 0.1961, aux.acc_seg: 69.1040, loss: 0.4908 +2022-05-05 12:29:20,216 - mmseg - INFO - Iter [18500/80000] lr: 1.104e-06, eta: 10:46:31, time: 0.590, data_time: 0.004, memory: 60248, decode.loss_ce: 0.2735, decode.acc_seg: 71.8312, aux.loss_ce: 0.1896, aux.acc_seg: 67.5097, loss: 0.4631 +2022-05-05 12:29:52,169 - mmseg - INFO - Iter [18550/80000] lr: 1.103e-06, eta: 10:46:01, time: 0.639, data_time: 0.053, memory: 60248, decode.loss_ce: 0.2696, decode.acc_seg: 72.0453, aux.loss_ce: 0.1876, aux.acc_seg: 67.8812, loss: 0.4573 +2022-05-05 12:30:21,762 - mmseg - INFO - Iter [18600/80000] lr: 1.102e-06, eta: 10:45:23, time: 0.592, data_time: 0.005, memory: 60248, decode.loss_ce: 0.2640, decode.acc_seg: 71.9694, aux.loss_ce: 0.1828, aux.acc_seg: 67.9296, loss: 0.4468 +2022-05-05 12:30:51,742 - mmseg - INFO - Iter [18650/80000] lr: 1.101e-06, eta: 10:44:46, time: 0.599, data_time: 0.004, memory: 60248, decode.loss_ce: 0.2587, decode.acc_seg: 71.3539, aux.loss_ce: 0.1800, aux.acc_seg: 67.5328, loss: 0.4387 +2022-05-05 12:31:21,459 - mmseg - INFO - Iter [18700/80000] lr: 1.100e-06, eta: 10:44:09, time: 0.594, data_time: 0.005, memory: 60248, decode.loss_ce: 0.2509, decode.acc_seg: 71.5414, aux.loss_ce: 0.1836, aux.acc_seg: 67.1088, loss: 0.4345 +2022-05-05 12:31:50,932 - mmseg - INFO - Iter [18750/80000] lr: 1.099e-06, eta: 10:43:31, time: 0.589, data_time: 0.004, memory: 60248, decode.loss_ce: 0.2490, decode.acc_seg: 71.7627, aux.loss_ce: 0.1731, aux.acc_seg: 67.8512, loss: 0.4221 +2022-05-05 12:32:20,794 - mmseg - INFO - Iter [18800/80000] lr: 1.098e-06, eta: 10:42:54, time: 0.597, data_time: 0.004, memory: 60248, decode.loss_ce: 0.2683, decode.acc_seg: 73.8844, aux.loss_ce: 0.1890, aux.acc_seg: 69.5636, loss: 0.4574 +2022-05-05 12:32:50,576 - mmseg - INFO - Iter [18850/80000] lr: 1.098e-06, eta: 10:42:16, time: 0.595, data_time: 0.005, memory: 60248, decode.loss_ce: 0.3005, decode.acc_seg: 71.9710, aux.loss_ce: 0.2020, aux.acc_seg: 67.4929, loss: 0.5025 +2022-05-05 12:33:20,264 - mmseg - INFO - Iter [18900/80000] lr: 1.097e-06, eta: 10:41:39, time: 0.594, data_time: 0.005, memory: 60248, decode.loss_ce: 0.2913, decode.acc_seg: 72.4342, aux.loss_ce: 0.1960, aux.acc_seg: 67.8393, loss: 0.4873 +2022-05-05 12:33:49,917 - mmseg - INFO - Iter [18950/80000] lr: 1.096e-06, eta: 10:41:02, time: 0.593, data_time: 0.004, memory: 60248, decode.loss_ce: 0.2994, decode.acc_seg: 71.4270, aux.loss_ce: 0.1833, aux.acc_seg: 68.1992, loss: 0.4827 +2022-05-05 12:34:19,464 - mmseg - INFO - Saving checkpoint at 19000 iterations +2022-05-05 12:34:39,492 - mmseg - INFO - Exp name: upernet_beit_adapter_large_512_80k_cocostuff10k_ss.py +2022-05-05 12:34:39,497 - mmseg - INFO - Iter [19000/80000] lr: 1.095e-06, eta: 10:41:28, time: 0.989, data_time: 0.004, memory: 60248, decode.loss_ce: 0.2857, decode.acc_seg: 72.7959, aux.loss_ce: 0.1886, aux.acc_seg: 68.8523, loss: 0.4743 +2022-05-05 12:35:09,618 - mmseg - INFO - Iter [19050/80000] lr: 1.094e-06, eta: 10:40:52, time: 0.604, data_time: 0.007, memory: 60248, decode.loss_ce: 0.2724, decode.acc_seg: 72.2120, aux.loss_ce: 0.1843, aux.acc_seg: 68.1259, loss: 0.4568 +2022-05-05 12:35:39,202 - mmseg - INFO - Iter [19100/80000] lr: 1.093e-06, eta: 10:40:14, time: 0.592, data_time: 0.005, memory: 60248, decode.loss_ce: 0.2580, decode.acc_seg: 73.3949, aux.loss_ce: 0.1813, aux.acc_seg: 69.2134, loss: 0.4393 +2022-05-05 12:36:11,589 - mmseg - INFO - Iter [19150/80000] lr: 1.092e-06, eta: 10:39:45, time: 0.648, data_time: 0.052, memory: 60248, decode.loss_ce: 0.2555, decode.acc_seg: 73.0310, aux.loss_ce: 0.1859, aux.acc_seg: 68.4761, loss: 0.4414 +2022-05-05 12:36:41,274 - mmseg - INFO - Iter [19200/80000] lr: 1.091e-06, eta: 10:39:08, time: 0.594, data_time: 0.004, memory: 60248, decode.loss_ce: 0.2674, decode.acc_seg: 72.8357, aux.loss_ce: 0.1897, aux.acc_seg: 68.3394, loss: 0.4571 +2022-05-05 12:37:11,341 - mmseg - INFO - Iter [19250/80000] lr: 1.090e-06, eta: 10:38:32, time: 0.601, data_time: 0.005, memory: 60248, decode.loss_ce: 0.2879, decode.acc_seg: 71.8376, aux.loss_ce: 0.1918, aux.acc_seg: 67.9569, loss: 0.4796 +2022-05-05 12:37:41,105 - mmseg - INFO - Iter [19300/80000] lr: 1.089e-06, eta: 10:37:55, time: 0.595, data_time: 0.004, memory: 60248, decode.loss_ce: 0.2641, decode.acc_seg: 72.4067, aux.loss_ce: 0.1781, aux.acc_seg: 68.2345, loss: 0.4422 +2022-05-05 12:38:10,913 - mmseg - INFO - Iter [19350/80000] lr: 1.089e-06, eta: 10:37:18, time: 0.596, data_time: 0.005, memory: 60248, decode.loss_ce: 0.2844, decode.acc_seg: 70.3724, aux.loss_ce: 0.1808, aux.acc_seg: 66.7503, loss: 0.4652 +2022-05-05 12:38:40,545 - mmseg - INFO - Iter [19400/80000] lr: 1.088e-06, eta: 10:36:40, time: 0.592, data_time: 0.004, memory: 60248, decode.loss_ce: 0.2756, decode.acc_seg: 71.7868, aux.loss_ce: 0.1931, aux.acc_seg: 67.4903, loss: 0.4686 +2022-05-05 12:39:10,230 - mmseg - INFO - Iter [19450/80000] lr: 1.087e-06, eta: 10:36:03, time: 0.594, data_time: 0.004, memory: 60248, decode.loss_ce: 0.2675, decode.acc_seg: 74.0358, aux.loss_ce: 0.1806, aux.acc_seg: 70.0704, loss: 0.4481 +2022-05-05 12:39:39,694 - mmseg - INFO - Iter [19500/80000] lr: 1.086e-06, eta: 10:35:25, time: 0.589, data_time: 0.004, memory: 60248, decode.loss_ce: 0.2769, decode.acc_seg: 72.3623, aux.loss_ce: 0.1844, aux.acc_seg: 68.5937, loss: 0.4613 +2022-05-05 12:40:09,162 - mmseg - INFO - Iter [19550/80000] lr: 1.085e-06, eta: 10:34:47, time: 0.589, data_time: 0.004, memory: 60248, decode.loss_ce: 0.2587, decode.acc_seg: 72.0909, aux.loss_ce: 0.1785, aux.acc_seg: 68.2830, loss: 0.4372 +2022-05-05 12:40:38,679 - mmseg - INFO - Iter [19600/80000] lr: 1.084e-06, eta: 10:34:10, time: 0.590, data_time: 0.004, memory: 60248, decode.loss_ce: 0.2625, decode.acc_seg: 71.3367, aux.loss_ce: 0.1781, aux.acc_seg: 67.3789, loss: 0.4406 +2022-05-05 12:41:08,460 - mmseg - INFO - Iter [19650/80000] lr: 1.083e-06, eta: 10:33:33, time: 0.595, data_time: 0.005, memory: 60248, decode.loss_ce: 0.2592, decode.acc_seg: 73.6378, aux.loss_ce: 0.1734, aux.acc_seg: 70.0635, loss: 0.4326 +2022-05-05 12:41:40,464 - mmseg - INFO - Iter [19700/80000] lr: 1.082e-06, eta: 10:33:03, time: 0.640, data_time: 0.052, memory: 60248, decode.loss_ce: 0.2710, decode.acc_seg: 72.7119, aux.loss_ce: 0.1898, aux.acc_seg: 68.0604, loss: 0.4609 +2022-05-05 12:42:10,020 - mmseg - INFO - Iter [19750/80000] lr: 1.081e-06, eta: 10:32:26, time: 0.591, data_time: 0.004, memory: 60248, decode.loss_ce: 0.2670, decode.acc_seg: 71.6594, aux.loss_ce: 0.1848, aux.acc_seg: 67.4205, loss: 0.4517 +2022-05-05 12:42:39,604 - mmseg - INFO - Iter [19800/80000] lr: 1.080e-06, eta: 10:31:48, time: 0.592, data_time: 0.004, memory: 60248, decode.loss_ce: 0.2628, decode.acc_seg: 73.8580, aux.loss_ce: 0.1827, aux.acc_seg: 69.6973, loss: 0.4455 +2022-05-05 12:43:09,422 - mmseg - INFO - Iter [19850/80000] lr: 1.080e-06, eta: 10:31:12, time: 0.596, data_time: 0.004, memory: 60248, decode.loss_ce: 0.2697, decode.acc_seg: 71.8253, aux.loss_ce: 0.1850, aux.acc_seg: 67.7375, loss: 0.4547 +2022-05-05 12:43:38,960 - mmseg - INFO - Iter [19900/80000] lr: 1.079e-06, eta: 10:30:35, time: 0.591, data_time: 0.005, memory: 60248, decode.loss_ce: 0.2418, decode.acc_seg: 73.7907, aux.loss_ce: 0.1712, aux.acc_seg: 70.0116, loss: 0.4130 +2022-05-05 12:44:08,572 - mmseg - INFO - Iter [19950/80000] lr: 1.078e-06, eta: 10:29:57, time: 0.592, data_time: 0.004, memory: 60248, decode.loss_ce: 0.2500, decode.acc_seg: 71.7295, aux.loss_ce: 0.1679, aux.acc_seg: 68.2309, loss: 0.4179 +2022-05-05 12:44:38,509 - mmseg - INFO - Saving checkpoint at 20000 iterations +2022-05-05 12:44:59,733 - mmseg - INFO - Exp name: upernet_beit_adapter_large_512_80k_cocostuff10k_ss.py +2022-05-05 12:44:59,736 - mmseg - INFO - Iter [20000/80000] lr: 1.077e-06, eta: 10:30:25, time: 1.021, data_time: 0.004, memory: 60248, decode.loss_ce: 0.2589, decode.acc_seg: 72.5072, aux.loss_ce: 0.1783, aux.acc_seg: 68.4940, loss: 0.4372 +2022-05-05 12:45:29,649 - mmseg - INFO - Iter [20050/80000] lr: 1.076e-06, eta: 10:29:49, time: 0.600, data_time: 0.007, memory: 60248, decode.loss_ce: 0.2440, decode.acc_seg: 71.7282, aux.loss_ce: 0.1643, aux.acc_seg: 68.2373, loss: 0.4083 +2022-05-05 12:45:59,462 - mmseg - INFO - Iter [20100/80000] lr: 1.075e-06, eta: 10:29:12, time: 0.597, data_time: 0.005, memory: 60248, decode.loss_ce: 0.2359, decode.acc_seg: 71.0436, aux.loss_ce: 0.1678, aux.acc_seg: 66.8605, loss: 0.4037 +2022-05-05 12:46:29,145 - mmseg - INFO - Iter [20150/80000] lr: 1.074e-06, eta: 10:28:35, time: 0.594, data_time: 0.004, memory: 60248, decode.loss_ce: 0.2748, decode.acc_seg: 72.2998, aux.loss_ce: 0.1892, aux.acc_seg: 68.1114, loss: 0.4640 +2022-05-05 12:46:59,127 - mmseg - INFO - Iter [20200/80000] lr: 1.073e-06, eta: 10:27:59, time: 0.599, data_time: 0.004, memory: 60248, decode.loss_ce: 0.2647, decode.acc_seg: 72.2355, aux.loss_ce: 0.1760, aux.acc_seg: 68.4964, loss: 0.4407 +2022-05-05 12:47:31,439 - mmseg - INFO - Iter [20250/80000] lr: 1.072e-06, eta: 10:27:30, time: 0.644, data_time: 0.052, memory: 60248, decode.loss_ce: 0.2629, decode.acc_seg: 72.9248, aux.loss_ce: 0.1784, aux.acc_seg: 69.2739, loss: 0.4413 +2022-05-05 12:48:01,310 - mmseg - INFO - Iter [20300/80000] lr: 1.071e-06, eta: 10:26:54, time: 0.600, data_time: 0.007, memory: 60248, decode.loss_ce: 0.2575, decode.acc_seg: 73.6040, aux.loss_ce: 0.1684, aux.acc_seg: 70.3244, loss: 0.4259 +2022-05-05 12:48:31,405 - mmseg - INFO - Iter [20350/80000] lr: 1.071e-06, eta: 10:26:18, time: 0.602, data_time: 0.004, memory: 60248, decode.loss_ce: 0.2664, decode.acc_seg: 72.2942, aux.loss_ce: 0.1757, aux.acc_seg: 68.3649, loss: 0.4421 +2022-05-05 12:49:01,522 - mmseg - INFO - Iter [20400/80000] lr: 1.070e-06, eta: 10:25:42, time: 0.602, data_time: 0.004, memory: 60248, decode.loss_ce: 0.2555, decode.acc_seg: 72.4196, aux.loss_ce: 0.1700, aux.acc_seg: 68.7211, loss: 0.4255 +2022-05-05 12:49:31,790 - mmseg - INFO - Iter [20450/80000] lr: 1.069e-06, eta: 10:25:07, time: 0.605, data_time: 0.004, memory: 60248, decode.loss_ce: 0.2551, decode.acc_seg: 72.8887, aux.loss_ce: 0.1756, aux.acc_seg: 69.0105, loss: 0.4307 +2022-05-05 12:50:01,679 - mmseg - INFO - Iter [20500/80000] lr: 1.068e-06, eta: 10:24:31, time: 0.598, data_time: 0.004, memory: 60248, decode.loss_ce: 0.2430, decode.acc_seg: 72.8244, aux.loss_ce: 0.1664, aux.acc_seg: 69.2562, loss: 0.4094 +2022-05-05 12:50:31,639 - mmseg - INFO - Iter [20550/80000] lr: 1.067e-06, eta: 10:23:55, time: 0.599, data_time: 0.004, memory: 60248, decode.loss_ce: 0.2679, decode.acc_seg: 72.5633, aux.loss_ce: 0.1851, aux.acc_seg: 68.4699, loss: 0.4530 +2022-05-05 12:51:01,516 - mmseg - INFO - Iter [20600/80000] lr: 1.066e-06, eta: 10:23:19, time: 0.597, data_time: 0.004, memory: 60248, decode.loss_ce: 0.2567, decode.acc_seg: 73.0929, aux.loss_ce: 0.1733, aux.acc_seg: 69.7002, loss: 0.4300 +2022-05-05 12:51:31,268 - mmseg - INFO - Iter [20650/80000] lr: 1.065e-06, eta: 10:22:43, time: 0.595, data_time: 0.005, memory: 60248, decode.loss_ce: 0.2622, decode.acc_seg: 71.1539, aux.loss_ce: 0.1750, aux.acc_seg: 67.4492, loss: 0.4372 +2022-05-05 12:52:01,116 - mmseg - INFO - Iter [20700/80000] lr: 1.064e-06, eta: 10:22:07, time: 0.597, data_time: 0.004, memory: 60248, decode.loss_ce: 0.2556, decode.acc_seg: 73.6426, aux.loss_ce: 0.1765, aux.acc_seg: 69.6722, loss: 0.4321 +2022-05-05 12:52:30,796 - mmseg - INFO - Iter [20750/80000] lr: 1.063e-06, eta: 10:21:30, time: 0.594, data_time: 0.004, memory: 60248, decode.loss_ce: 0.2633, decode.acc_seg: 71.5606, aux.loss_ce: 0.1727, aux.acc_seg: 68.0564, loss: 0.4360 +2022-05-05 12:53:03,133 - mmseg - INFO - Iter [20800/80000] lr: 1.063e-06, eta: 10:21:01, time: 0.647, data_time: 0.054, memory: 60248, decode.loss_ce: 0.2582, decode.acc_seg: 72.1358, aux.loss_ce: 0.1733, aux.acc_seg: 68.4588, loss: 0.4315 +2022-05-05 12:53:32,729 - mmseg - INFO - Iter [20850/80000] lr: 1.062e-06, eta: 10:20:24, time: 0.592, data_time: 0.004, memory: 60248, decode.loss_ce: 0.2405, decode.acc_seg: 74.4300, aux.loss_ce: 0.1684, aux.acc_seg: 70.6827, loss: 0.4089 +2022-05-05 12:54:02,363 - mmseg - INFO - Iter [20900/80000] lr: 1.061e-06, eta: 10:19:48, time: 0.593, data_time: 0.004, memory: 60248, decode.loss_ce: 0.2489, decode.acc_seg: 72.8122, aux.loss_ce: 0.1675, aux.acc_seg: 69.2939, loss: 0.4164 +2022-05-05 12:54:32,065 - mmseg - INFO - Iter [20950/80000] lr: 1.060e-06, eta: 10:19:11, time: 0.594, data_time: 0.004, memory: 60248, decode.loss_ce: 0.2544, decode.acc_seg: 72.7612, aux.loss_ce: 0.1739, aux.acc_seg: 68.7695, loss: 0.4282 +2022-05-05 12:55:01,756 - mmseg - INFO - Saving checkpoint at 21000 iterations +2022-05-05 12:55:21,940 - mmseg - INFO - Exp name: upernet_beit_adapter_large_512_80k_cocostuff10k_ss.py +2022-05-05 12:55:21,942 - mmseg - INFO - Iter [21000/80000] lr: 1.059e-06, eta: 10:19:31, time: 0.996, data_time: 0.004, memory: 60248, decode.loss_ce: 0.2397, decode.acc_seg: 72.0435, aux.loss_ce: 0.1607, aux.acc_seg: 68.4750, loss: 0.4004 +2022-05-05 12:55:52,062 - mmseg - INFO - Iter [21050/80000] lr: 1.058e-06, eta: 10:18:56, time: 0.603, data_time: 0.006, memory: 60248, decode.loss_ce: 0.2529, decode.acc_seg: 72.9866, aux.loss_ce: 0.1725, aux.acc_seg: 69.3096, loss: 0.4254 +2022-05-05 12:56:21,759 - mmseg - INFO - Iter [21100/80000] lr: 1.057e-06, eta: 10:18:20, time: 0.596, data_time: 0.006, memory: 60248, decode.loss_ce: 0.2504, decode.acc_seg: 72.3001, aux.loss_ce: 0.1675, aux.acc_seg: 68.5761, loss: 0.4179 +2022-05-05 12:56:51,743 - mmseg - INFO - Iter [21150/80000] lr: 1.056e-06, eta: 10:17:44, time: 0.600, data_time: 0.006, memory: 60248, decode.loss_ce: 0.2658, decode.acc_seg: 72.1867, aux.loss_ce: 0.1785, aux.acc_seg: 68.3503, loss: 0.4442 +2022-05-05 12:57:21,441 - mmseg - INFO - Iter [21200/80000] lr: 1.055e-06, eta: 10:17:07, time: 0.594, data_time: 0.004, memory: 60248, decode.loss_ce: 0.2496, decode.acc_seg: 72.8443, aux.loss_ce: 0.1712, aux.acc_seg: 68.9121, loss: 0.4209 +2022-05-05 12:57:50,934 - mmseg - INFO - Iter [21250/80000] lr: 1.054e-06, eta: 10:16:30, time: 0.590, data_time: 0.005, memory: 60248, decode.loss_ce: 0.2449, decode.acc_seg: 73.7136, aux.loss_ce: 0.1673, aux.acc_seg: 70.0283, loss: 0.4122 +2022-05-05 12:58:20,438 - mmseg - INFO - Iter [21300/80000] lr: 1.054e-06, eta: 10:15:53, time: 0.590, data_time: 0.004, memory: 60248, decode.loss_ce: 0.2546, decode.acc_seg: 74.1875, aux.loss_ce: 0.1703, aux.acc_seg: 70.4101, loss: 0.4250 +2022-05-05 12:58:49,904 - mmseg - INFO - Iter [21350/80000] lr: 1.053e-06, eta: 10:15:16, time: 0.590, data_time: 0.004, memory: 60248, decode.loss_ce: 0.2442, decode.acc_seg: 73.3493, aux.loss_ce: 0.1708, aux.acc_seg: 69.3698, loss: 0.4150 +2022-05-05 12:59:21,885 - mmseg - INFO - Iter [21400/80000] lr: 1.052e-06, eta: 10:14:46, time: 0.639, data_time: 0.052, memory: 60248, decode.loss_ce: 0.2357, decode.acc_seg: 74.0663, aux.loss_ce: 0.1663, aux.acc_seg: 70.1081, loss: 0.4020 +2022-05-05 12:59:51,614 - mmseg - INFO - Iter [21450/80000] lr: 1.051e-06, eta: 10:14:10, time: 0.595, data_time: 0.004, memory: 60248, decode.loss_ce: 0.2480, decode.acc_seg: 72.5059, aux.loss_ce: 0.1718, aux.acc_seg: 68.8720, loss: 0.4198 +2022-05-05 13:00:21,573 - mmseg - INFO - Iter [21500/80000] lr: 1.050e-06, eta: 10:13:35, time: 0.599, data_time: 0.005, memory: 60248, decode.loss_ce: 0.2382, decode.acc_seg: 73.2704, aux.loss_ce: 0.1681, aux.acc_seg: 69.3489, loss: 0.4063 +2022-05-05 13:00:51,301 - mmseg - INFO - Iter [21550/80000] lr: 1.049e-06, eta: 10:12:58, time: 0.595, data_time: 0.004, memory: 60248, decode.loss_ce: 0.2456, decode.acc_seg: 72.4814, aux.loss_ce: 0.1666, aux.acc_seg: 68.7651, loss: 0.4121 +2022-05-05 13:01:20,803 - mmseg - INFO - Iter [21600/80000] lr: 1.048e-06, eta: 10:12:22, time: 0.590, data_time: 0.005, memory: 60248, decode.loss_ce: 0.2392, decode.acc_seg: 72.5436, aux.loss_ce: 0.1625, aux.acc_seg: 69.1060, loss: 0.4017 +2022-05-05 13:01:50,482 - mmseg - INFO - Iter [21650/80000] lr: 1.047e-06, eta: 10:11:45, time: 0.592, data_time: 0.005, memory: 60248, decode.loss_ce: 0.2438, decode.acc_seg: 73.1306, aux.loss_ce: 0.1648, aux.acc_seg: 69.6454, loss: 0.4085 +2022-05-05 13:02:20,287 - mmseg - INFO - Iter [21700/80000] lr: 1.046e-06, eta: 10:11:09, time: 0.598, data_time: 0.006, memory: 60248, decode.loss_ce: 0.2374, decode.acc_seg: 72.8551, aux.loss_ce: 0.1562, aux.acc_seg: 69.6004, loss: 0.3936 +2022-05-05 13:02:49,833 - mmseg - INFO - Iter [21750/80000] lr: 1.045e-06, eta: 10:10:33, time: 0.591, data_time: 0.004, memory: 60248, decode.loss_ce: 0.2466, decode.acc_seg: 73.0851, aux.loss_ce: 0.1683, aux.acc_seg: 69.4750, loss: 0.4149 +2022-05-05 13:03:19,478 - mmseg - INFO - Iter [21800/80000] lr: 1.045e-06, eta: 10:09:57, time: 0.593, data_time: 0.006, memory: 60248, decode.loss_ce: 0.2590, decode.acc_seg: 73.9485, aux.loss_ce: 0.1729, aux.acc_seg: 70.1133, loss: 0.4320 +2022-05-05 13:03:49,123 - mmseg - INFO - Iter [21850/80000] lr: 1.044e-06, eta: 10:09:20, time: 0.593, data_time: 0.005, memory: 60248, decode.loss_ce: 0.2565, decode.acc_seg: 73.1564, aux.loss_ce: 0.1704, aux.acc_seg: 69.4297, loss: 0.4270 +2022-05-05 13:04:18,687 - mmseg - INFO - Iter [21900/80000] lr: 1.043e-06, eta: 10:08:44, time: 0.591, data_time: 0.004, memory: 60248, decode.loss_ce: 0.2476, decode.acc_seg: 71.7254, aux.loss_ce: 0.1655, aux.acc_seg: 67.9298, loss: 0.4131 +2022-05-05 13:04:51,100 - mmseg - INFO - Iter [21950/80000] lr: 1.042e-06, eta: 10:08:15, time: 0.648, data_time: 0.056, memory: 60248, decode.loss_ce: 0.2295, decode.acc_seg: 73.9539, aux.loss_ce: 0.1583, aux.acc_seg: 70.4816, loss: 0.3878 +2022-05-05 13:05:20,667 - mmseg - INFO - Saving checkpoint at 22000 iterations +2022-05-05 13:05:40,870 - mmseg - INFO - Exp name: upernet_beit_adapter_large_512_80k_cocostuff10k_ss.py +2022-05-05 13:05:40,872 - mmseg - INFO - Iter [22000/80000] lr: 1.041e-06, eta: 10:08:32, time: 0.993, data_time: 0.004, memory: 60248, decode.loss_ce: 0.2558, decode.acc_seg: 72.3262, aux.loss_ce: 0.1703, aux.acc_seg: 68.6893, loss: 0.4261 +2022-05-05 13:06:10,695 - mmseg - INFO - Iter [22050/80000] lr: 1.040e-06, eta: 10:07:56, time: 0.598, data_time: 0.006, memory: 60248, decode.loss_ce: 0.2284, decode.acc_seg: 73.5989, aux.loss_ce: 0.1599, aux.acc_seg: 70.0770, loss: 0.3882 +2022-05-05 13:06:40,104 - mmseg - INFO - Iter [22100/80000] lr: 1.039e-06, eta: 10:07:19, time: 0.589, data_time: 0.005, memory: 60248, decode.loss_ce: 0.2524, decode.acc_seg: 72.1866, aux.loss_ce: 0.1716, aux.acc_seg: 68.5473, loss: 0.4240 +2022-05-05 13:07:09,889 - mmseg - INFO - Iter [22150/80000] lr: 1.038e-06, eta: 10:06:43, time: 0.594, data_time: 0.004, memory: 60248, decode.loss_ce: 0.2425, decode.acc_seg: 71.7701, aux.loss_ce: 0.1674, aux.acc_seg: 67.9299, loss: 0.4099 +2022-05-05 13:07:39,557 - mmseg - INFO - Iter [22200/80000] lr: 1.037e-06, eta: 10:06:07, time: 0.596, data_time: 0.007, memory: 60248, decode.loss_ce: 0.2363, decode.acc_seg: 73.5735, aux.loss_ce: 0.1555, aux.acc_seg: 70.2905, loss: 0.3918 +2022-05-05 13:08:09,110 - mmseg - INFO - Iter [22250/80000] lr: 1.036e-06, eta: 10:05:31, time: 0.591, data_time: 0.004, memory: 60248, decode.loss_ce: 0.2515, decode.acc_seg: 74.0744, aux.loss_ce: 0.1716, aux.acc_seg: 70.0230, loss: 0.4231 +2022-05-05 13:08:38,508 - mmseg - INFO - Iter [22300/80000] lr: 1.036e-06, eta: 10:04:54, time: 0.588, data_time: 0.004, memory: 60248, decode.loss_ce: 0.2435, decode.acc_seg: 74.2547, aux.loss_ce: 0.1675, aux.acc_seg: 70.5096, loss: 0.4110 +2022-05-05 13:09:08,049 - mmseg - INFO - Iter [22350/80000] lr: 1.035e-06, eta: 10:04:18, time: 0.591, data_time: 0.004, memory: 60248, decode.loss_ce: 0.2461, decode.acc_seg: 73.3969, aux.loss_ce: 0.1649, aux.acc_seg: 70.0252, loss: 0.4110 +2022-05-05 13:09:37,923 - mmseg - INFO - Iter [22400/80000] lr: 1.034e-06, eta: 10:03:42, time: 0.596, data_time: 0.004, memory: 60248, decode.loss_ce: 0.2567, decode.acc_seg: 73.2881, aux.loss_ce: 0.1688, aux.acc_seg: 69.9370, loss: 0.4255 +2022-05-05 13:10:07,659 - mmseg - INFO - Iter [22450/80000] lr: 1.033e-06, eta: 10:03:07, time: 0.597, data_time: 0.007, memory: 60248, decode.loss_ce: 0.2630, decode.acc_seg: 73.2132, aux.loss_ce: 0.1684, aux.acc_seg: 69.9869, loss: 0.4314 +2022-05-05 13:10:40,327 - mmseg - INFO - Iter [22500/80000] lr: 1.032e-06, eta: 10:02:38, time: 0.653, data_time: 0.056, memory: 60248, decode.loss_ce: 0.2406, decode.acc_seg: 73.5054, aux.loss_ce: 0.1630, aux.acc_seg: 69.7033, loss: 0.4036 +2022-05-05 13:11:09,988 - mmseg - INFO - Iter [22550/80000] lr: 1.031e-06, eta: 10:02:02, time: 0.593, data_time: 0.004, memory: 60248, decode.loss_ce: 0.2310, decode.acc_seg: 73.5412, aux.loss_ce: 0.1524, aux.acc_seg: 70.3924, loss: 0.3834 +2022-05-05 13:11:39,592 - mmseg - INFO - Iter [22600/80000] lr: 1.030e-06, eta: 10:01:26, time: 0.592, data_time: 0.004, memory: 60248, decode.loss_ce: 0.2539, decode.acc_seg: 73.3967, aux.loss_ce: 0.1696, aux.acc_seg: 69.7852, loss: 0.4235 +2022-05-05 13:12:09,668 - mmseg - INFO - Iter [22650/80000] lr: 1.029e-06, eta: 10:00:51, time: 0.602, data_time: 0.006, memory: 60248, decode.loss_ce: 0.2449, decode.acc_seg: 73.9564, aux.loss_ce: 0.1615, aux.acc_seg: 70.3644, loss: 0.4064 +2022-05-05 13:12:39,401 - mmseg - INFO - Iter [22700/80000] lr: 1.028e-06, eta: 10:00:16, time: 0.595, data_time: 0.004, memory: 60248, decode.loss_ce: 0.2442, decode.acc_seg: 73.2880, aux.loss_ce: 0.1629, aux.acc_seg: 69.7138, loss: 0.4071 +2022-05-05 13:13:09,060 - mmseg - INFO - Iter [22750/80000] lr: 1.028e-06, eta: 9:59:40, time: 0.593, data_time: 0.004, memory: 60248, decode.loss_ce: 0.2430, decode.acc_seg: 73.2568, aux.loss_ce: 0.1685, aux.acc_seg: 69.3204, loss: 0.4115 +2022-05-05 13:13:38,460 - mmseg - INFO - Iter [22800/80000] lr: 1.027e-06, eta: 9:59:03, time: 0.588, data_time: 0.004, memory: 60248, decode.loss_ce: 0.2379, decode.acc_seg: 74.4577, aux.loss_ce: 0.1585, aux.acc_seg: 70.9569, loss: 0.3964 +2022-05-05 13:14:08,194 - mmseg - INFO - Iter [22850/80000] lr: 1.026e-06, eta: 9:58:27, time: 0.595, data_time: 0.004, memory: 60248, decode.loss_ce: 0.2544, decode.acc_seg: 71.9878, aux.loss_ce: 0.1658, aux.acc_seg: 68.7563, loss: 0.4202 +2022-05-05 13:14:37,926 - mmseg - INFO - Iter [22900/80000] lr: 1.025e-06, eta: 9:57:52, time: 0.595, data_time: 0.005, memory: 60248, decode.loss_ce: 0.2435, decode.acc_seg: 73.2580, aux.loss_ce: 0.1609, aux.acc_seg: 69.9123, loss: 0.4044 +2022-05-05 13:15:07,404 - mmseg - INFO - Iter [22950/80000] lr: 1.024e-06, eta: 9:57:16, time: 0.589, data_time: 0.004, memory: 60248, decode.loss_ce: 0.2501, decode.acc_seg: 72.5075, aux.loss_ce: 0.1648, aux.acc_seg: 69.1470, loss: 0.4150 +2022-05-05 13:15:37,045 - mmseg - INFO - Saving checkpoint at 23000 iterations +2022-05-05 13:15:58,517 - mmseg - INFO - Exp name: upernet_beit_adapter_large_512_80k_cocostuff10k_ss.py +2022-05-05 13:15:58,519 - mmseg - INFO - Iter [23000/80000] lr: 1.023e-06, eta: 9:57:33, time: 1.020, data_time: 0.004, memory: 60248, decode.loss_ce: 0.2283, decode.acc_seg: 72.7590, aux.loss_ce: 0.1593, aux.acc_seg: 69.1596, loss: 0.3876 +2022-05-05 13:16:31,244 - mmseg - INFO - Iter [23050/80000] lr: 1.022e-06, eta: 9:57:05, time: 0.657, data_time: 0.054, memory: 60248, decode.loss_ce: 0.2454, decode.acc_seg: 73.3367, aux.loss_ce: 0.1610, aux.acc_seg: 70.0622, loss: 0.4064 +2022-05-05 13:17:01,021 - mmseg - INFO - Iter [23100/80000] lr: 1.021e-06, eta: 9:56:29, time: 0.596, data_time: 0.004, memory: 60248, decode.loss_ce: 0.2352, decode.acc_seg: 73.7692, aux.loss_ce: 0.1626, aux.acc_seg: 69.8085, loss: 0.3978 +2022-05-05 13:17:30,616 - mmseg - INFO - Iter [23150/80000] lr: 1.020e-06, eta: 9:55:53, time: 0.592, data_time: 0.004, memory: 60248, decode.loss_ce: 0.2326, decode.acc_seg: 74.2448, aux.loss_ce: 0.1553, aux.acc_seg: 71.2090, loss: 0.3879 +2022-05-05 13:18:00,580 - mmseg - INFO - Iter [23200/80000] lr: 1.019e-06, eta: 9:55:18, time: 0.599, data_time: 0.005, memory: 60248, decode.loss_ce: 0.2475, decode.acc_seg: 73.9720, aux.loss_ce: 0.1668, aux.acc_seg: 70.3495, loss: 0.4144 +2022-05-05 13:18:30,353 - mmseg - INFO - Iter [23250/80000] lr: 1.019e-06, eta: 9:54:43, time: 0.596, data_time: 0.005, memory: 60248, decode.loss_ce: 0.2424, decode.acc_seg: 73.1176, aux.loss_ce: 0.1634, aux.acc_seg: 69.7626, loss: 0.4058 +2022-05-05 13:18:59,811 - mmseg - INFO - Iter [23300/80000] lr: 1.018e-06, eta: 9:54:06, time: 0.589, data_time: 0.004, memory: 60248, decode.loss_ce: 0.2278, decode.acc_seg: 73.0043, aux.loss_ce: 0.1542, aux.acc_seg: 69.4655, loss: 0.3820 +2022-05-05 13:19:29,397 - mmseg - INFO - Iter [23350/80000] lr: 1.017e-06, eta: 9:53:30, time: 0.592, data_time: 0.004, memory: 60248, decode.loss_ce: 0.2354, decode.acc_seg: 72.6271, aux.loss_ce: 0.1575, aux.acc_seg: 69.1238, loss: 0.3929 +2022-05-05 13:19:58,928 - mmseg - INFO - Iter [23400/80000] lr: 1.016e-06, eta: 9:52:54, time: 0.591, data_time: 0.005, memory: 60248, decode.loss_ce: 0.2249, decode.acc_seg: 73.8571, aux.loss_ce: 0.1518, aux.acc_seg: 70.4789, loss: 0.3767 +2022-05-05 13:20:28,566 - mmseg - INFO - Iter [23450/80000] lr: 1.015e-06, eta: 9:52:19, time: 0.593, data_time: 0.004, memory: 60248, decode.loss_ce: 0.2508, decode.acc_seg: 73.7523, aux.loss_ce: 0.1661, aux.acc_seg: 70.1169, loss: 0.4168 +2022-05-05 13:20:58,385 - mmseg - INFO - Iter [23500/80000] lr: 1.014e-06, eta: 9:51:43, time: 0.596, data_time: 0.004, memory: 60248, decode.loss_ce: 0.2306, decode.acc_seg: 74.6854, aux.loss_ce: 0.1558, aux.acc_seg: 71.3654, loss: 0.3864 +2022-05-05 13:21:28,154 - mmseg - INFO - Iter [23550/80000] lr: 1.013e-06, eta: 9:51:08, time: 0.596, data_time: 0.005, memory: 60248, decode.loss_ce: 0.2262, decode.acc_seg: 72.9862, aux.loss_ce: 0.1476, aux.acc_seg: 70.0240, loss: 0.3739 +2022-05-05 13:21:57,879 - mmseg - INFO - Iter [23600/80000] lr: 1.012e-06, eta: 9:50:32, time: 0.592, data_time: 0.004, memory: 60248, decode.loss_ce: 0.2385, decode.acc_seg: 73.7061, aux.loss_ce: 0.1600, aux.acc_seg: 70.0854, loss: 0.3985 +2022-05-05 13:22:29,969 - mmseg - INFO - Iter [23650/80000] lr: 1.011e-06, eta: 9:50:03, time: 0.644, data_time: 0.054, memory: 60248, decode.loss_ce: 0.2171, decode.acc_seg: 73.9267, aux.loss_ce: 0.1461, aux.acc_seg: 70.4363, loss: 0.3631 +2022-05-05 13:23:00,008 - mmseg - INFO - Iter [23700/80000] lr: 1.010e-06, eta: 9:49:28, time: 0.600, data_time: 0.005, memory: 60248, decode.loss_ce: 0.2195, decode.acc_seg: 73.5433, aux.loss_ce: 0.1541, aux.acc_seg: 69.8255, loss: 0.3736 +2022-05-05 13:23:29,690 - mmseg - INFO - Iter [23750/80000] lr: 1.010e-06, eta: 9:48:53, time: 0.594, data_time: 0.007, memory: 60248, decode.loss_ce: 0.2292, decode.acc_seg: 71.5467, aux.loss_ce: 0.1484, aux.acc_seg: 68.6262, loss: 0.3776 +2022-05-05 13:23:59,473 - mmseg - INFO - Iter [23800/80000] lr: 1.009e-06, eta: 9:48:17, time: 0.594, data_time: 0.004, memory: 60248, decode.loss_ce: 0.2188, decode.acc_seg: 75.1510, aux.loss_ce: 0.1521, aux.acc_seg: 71.8612, loss: 0.3709 +2022-05-05 13:24:29,238 - mmseg - INFO - Iter [23850/80000] lr: 1.008e-06, eta: 9:47:42, time: 0.597, data_time: 0.006, memory: 60248, decode.loss_ce: 0.2429, decode.acc_seg: 72.2194, aux.loss_ce: 0.1623, aux.acc_seg: 68.6459, loss: 0.4052 +2022-05-05 13:24:58,759 - mmseg - INFO - Iter [23900/80000] lr: 1.007e-06, eta: 9:47:06, time: 0.590, data_time: 0.004, memory: 60248, decode.loss_ce: 0.2260, decode.acc_seg: 73.2198, aux.loss_ce: 0.1489, aux.acc_seg: 70.1926, loss: 0.3749 +2022-05-05 13:25:28,312 - mmseg - INFO - Iter [23950/80000] lr: 1.006e-06, eta: 9:46:31, time: 0.591, data_time: 0.005, memory: 60248, decode.loss_ce: 0.2250, decode.acc_seg: 71.8724, aux.loss_ce: 0.1562, aux.acc_seg: 68.3994, loss: 0.3811 +2022-05-05 13:25:58,236 - mmseg - INFO - Saving checkpoint at 24000 iterations +2022-05-05 13:26:18,807 - mmseg - INFO - Exp name: upernet_beit_adapter_large_512_80k_cocostuff10k_ss.py +2022-05-05 13:26:18,809 - mmseg - INFO - Iter [24000/80000] lr: 1.005e-06, eta: 9:46:44, time: 1.008, data_time: 0.004, memory: 60248, decode.loss_ce: 0.2296, decode.acc_seg: 73.2478, aux.loss_ce: 0.1539, aux.acc_seg: 69.9269, loss: 0.3834 +2022-05-05 13:26:48,362 - mmseg - INFO - per class results: +2022-05-05 13:26:48,372 - mmseg - INFO - ++------------------+-------+-------+ +| Class | IoU | Acc | ++------------------+-------+-------+ +| person | 87.15 | 94.7 | +| bicycle | 72.63 | 88.22 | +| car | 62.48 | 70.32 | +| motorcycle | 87.98 | 96.23 | +| airplane | 88.63 | 95.23 | +| bus | 87.53 | 94.53 | +| train | 83.19 | 97.5 | +| truck | 75.94 | 88.15 | +| boat | 74.58 | 88.95 | +| traffic light | 71.48 | 90.54 | +| fire hydrant | 84.58 | 97.62 | +| stop sign | 88.74 | 98.71 | +| parking meter | 75.55 | 78.87 | +| bench | 54.47 | 68.77 | +| bird | 75.29 | 81.49 | +| cat | 92.64 | 96.25 | +| dog | 89.24 | 96.37 | +| horse | 88.97 | 95.97 | +| sheep | 87.3 | 91.22 | +| cow | 94.02 | 98.63 | +| elephant | 91.84 | 97.42 | +| bear | 86.6 | 88.97 | +| zebra | 90.31 | 95.85 | +| giraffe | 85.79 | 94.01 | +| backpack | 22.87 | 51.65 | +| umbrella | 79.71 | 90.34 | +| handbag | 17.11 | 21.4 | +| tie | 20.7 | 20.7 | +| suitcase | 75.56 | 96.98 | +| frisbee | 94.23 | 96.42 | +| skis | 33.47 | 51.48 | +| snowboard | 65.86 | 74.11 | +| sports ball | 79.75 | 87.36 | +| kite | 63.36 | 89.79 | +| baseball bat | 55.72 | 70.34 | +| baseball glove | 0.0 | 0.0 | +| skateboard | 65.01 | 83.45 | +| surfboard | 88.63 | 95.22 | +| tennis racket | 73.65 | 83.27 | +| bottle | 74.14 | 82.69 | +| wine glass | 83.74 | 91.6 | +| cup | 67.19 | 91.12 | +| fork | 41.34 | 62.42 | +| knife | 74.31 | 83.69 | +| spoon | 43.54 | 60.0 | +| bowl | 58.14 | 71.83 | +| banana | 73.87 | 86.21 | +| apple | 67.13 | 87.66 | +| sandwich | 86.02 | 97.79 | +| orange | 74.64 | 78.7 | +| broccoli | 89.3 | 90.87 | +| carrot | 42.75 | 75.93 | +| hot dog | 51.51 | 95.94 | +| pizza | 94.69 | 96.26 | +| donut | 69.02 | 90.8 | +| cake | 70.14 | 84.34 | +| chair | 60.22 | 76.64 | +| couch | 78.16 | 92.77 | +| potted plant | 37.36 | 52.45 | +| bed | 73.28 | 84.55 | +| dining table | 63.32 | 77.04 | +| toilet | 88.49 | 96.39 | +| tv | 68.4 | 91.14 | +| laptop | 85.99 | 96.21 | +| mouse | 66.08 | 73.03 | +| remote | 73.59 | 88.03 | +| keyboard | 83.7 | 97.91 | +| cell phone | 79.93 | 95.46 | +| microwave | 53.66 | 67.34 | +| oven | 62.73 | 86.01 | +| toaster | 0.0 | 0.0 | +| sink | 71.15 | 79.07 | +| refrigerator | 85.9 | 97.49 | +| book | 79.9 | 89.23 | +| clock | 78.26 | 87.03 | +| vase | 61.53 | 96.08 | +| scissors | 78.29 | 93.25 | +| teddy bear | 84.41 | 96.12 | +| hair drier | 0.0 | 0.0 | +| toothbrush | 13.86 | 17.29 | +| banner | 26.49 | 48.37 | +| blanket | 18.15 | 21.94 | +| branch | 8.88 | 8.98 | +| bridge | 2.47 | 3.34 | +| building-other | 53.92 | 71.56 | +| bush | 29.31 | 40.24 | +| cabinet | 16.8 | 35.7 | +| cage | 6.92 | 27.75 | +| cardboard | 22.17 | 29.68 | +| carpet | 56.8 | 76.26 | +| ceiling-other | 67.32 | 84.79 | +| ceiling-tile | 0.0 | 0.0 | +| cloth | 3.29 | 4.94 | +| clothes | 19.17 | 28.83 | +| clouds | 49.25 | 61.21 | +| counter | 35.66 | 43.19 | +| cupboard | 46.86 | 57.17 | +| curtain | 67.43 | 80.65 | +| desk-stuff | 31.9 | 35.34 | +| dirt | 31.23 | 48.72 | +| door-stuff | 46.05 | 58.37 | +| fence | 43.93 | 69.48 | +| floor-marble | 0.0 | 0.0 | +| floor-other | 40.35 | 53.21 | +| floor-stone | 28.56 | 41.27 | +| floor-tile | 57.16 | 74.7 | +| floor-wood | 68.11 | 81.37 | +| flower | 19.51 | 42.6 | +| fog | 0.0 | 0.0 | +| food-other | 37.6 | 56.9 | +| fruit | 55.69 | 67.04 | +| furniture-other | 14.92 | 21.62 | +| grass | 73.54 | 85.65 | +| gravel | 23.03 | 27.02 | +| ground-other | 9.32 | 19.14 | +| hill | 27.05 | 35.29 | +| house | 27.55 | 46.52 | +| leaves | 9.67 | 18.67 | +| light | 35.22 | 46.98 | +| mat | 9.04 | 12.11 | +| metal | 14.01 | 19.05 | +| mirror-stuff | 45.07 | 66.25 | +| moss | 0.0 | 0.0 | +| mountain | 36.15 | 63.63 | +| mud | 5.05 | 9.72 | +| napkin | 31.87 | 66.19 | +| net | 28.39 | 31.5 | +| paper | 50.29 | 66.01 | +| pavement | 53.82 | 71.21 | +| pillow | 0.0 | 0.0 | +| plant-other | 32.19 | 42.23 | +| plastic | 19.92 | 24.52 | +| platform | 42.82 | 52.79 | +| playingfield | 69.77 | 80.76 | +| railing | 21.15 | 33.33 | +| railroad | 62.23 | 94.39 | +| river | 4.85 | 5.43 | +| road | 67.41 | 76.1 | +| rock | 47.83 | 73.8 | +| roof | 7.01 | 12.0 | +| rug | 38.96 | 53.41 | +| salad | 11.86 | 12.81 | +| sand | 71.75 | 86.1 | +| sea | 73.14 | 89.33 | +| shelf | 26.22 | 39.46 | +| sky-other | 61.01 | 79.59 | +| skyscraper | 6.96 | 9.74 | +| snow | 91.39 | 94.89 | +| solid-other | 0.0 | nan | +| stairs | 33.83 | 54.04 | +| stone | 5.67 | 7.04 | +| straw | 14.17 | 33.15 | +| structural-other | 16.79 | 25.73 | +| table | 26.75 | 45.0 | +| tent | 79.78 | 87.68 | +| textile-other | 18.07 | 26.16 | +| towel | 40.09 | 51.31 | +| tree | 77.84 | 88.76 | +| vegetable | 40.37 | 67.2 | +| wall-brick | 40.84 | 50.85 | +| wall-concrete | 23.51 | 34.38 | +| wall-other | 60.47 | 77.72 | +| wall-panel | 4.52 | 6.7 | +| wall-stone | 30.84 | 37.05 | +| wall-tile | 57.66 | 90.04 | +| wall-wood | 39.62 | 65.21 | +| water-other | 33.46 | 51.9 | +| waterdrops | 0.0 | nan | +| window-blind | 39.04 | 73.24 | +| window-other | 46.89 | 60.7 | +| wood | 14.06 | 27.98 | ++------------------+-------+-------+ +2022-05-05 13:26:48,372 - mmseg - INFO - Summary: +2022-05-05 13:26:48,372 - mmseg - INFO - ++-------+-------+-------+ +| aAcc | mIoU | mAcc | ++-------+-------+-------+ +| 75.07 | 49.64 | 62.36 | ++-------+-------+-------+ +2022-05-05 13:26:48,374 - mmseg - INFO - The previous best checkpoint /mnt/lustre/chenzhe.vendor/workspace/ViT-Adapter/segmentation/work_dirs/upernet_beit_adapter_large_512_80k_cocostuff10k_ss/best_mIoU_iter_16000.pth was removed +2022-05-05 13:27:08,012 - mmseg - INFO - Now best checkpoint is saved as best_mIoU_iter_24000.pth. +2022-05-05 13:27:08,024 - mmseg - INFO - Best mIoU is 0.4964 at 24000 iter. +2022-05-05 13:27:08,034 - mmseg - INFO - Exp name: upernet_beit_adapter_large_512_80k_cocostuff10k_ss.py +2022-05-05 13:27:08,034 - mmseg - INFO - Iter(val) [125] aAcc: 0.7507, mIoU: 0.4964, mAcc: 0.6236, IoU.person: 0.8715, IoU.bicycle: 0.7263, IoU.car: 0.6248, IoU.motorcycle: 0.8798, IoU.airplane: 0.8863, IoU.bus: 0.8753, IoU.train: 0.8319, IoU.truck: 0.7594, IoU.boat: 0.7458, IoU.traffic light: 0.7148, IoU.fire hydrant: 0.8458, IoU.stop sign: 0.8874, IoU.parking meter: 0.7555, IoU.bench: 0.5447, IoU.bird: 0.7529, IoU.cat: 0.9264, IoU.dog: 0.8924, IoU.horse: 0.8897, IoU.sheep: 0.8730, IoU.cow: 0.9402, IoU.elephant: 0.9184, IoU.bear: 0.8660, IoU.zebra: 0.9031, IoU.giraffe: 0.8579, IoU.backpack: 0.2287, IoU.umbrella: 0.7971, IoU.handbag: 0.1711, IoU.tie: 0.2070, IoU.suitcase: 0.7556, IoU.frisbee: 0.9423, IoU.skis: 0.3347, IoU.snowboard: 0.6586, IoU.sports ball: 0.7975, IoU.kite: 0.6336, IoU.baseball bat: 0.5572, IoU.baseball glove: 0.0000, IoU.skateboard: 0.6501, IoU.surfboard: 0.8863, IoU.tennis racket: 0.7365, IoU.bottle: 0.7414, IoU.wine glass: 0.8374, IoU.cup: 0.6719, IoU.fork: 0.4134, IoU.knife: 0.7431, IoU.spoon: 0.4354, IoU.bowl: 0.5814, IoU.banana: 0.7387, IoU.apple: 0.6713, IoU.sandwich: 0.8602, IoU.orange: 0.7464, IoU.broccoli: 0.8930, IoU.carrot: 0.4275, IoU.hot dog: 0.5151, IoU.pizza: 0.9469, IoU.donut: 0.6902, IoU.cake: 0.7014, IoU.chair: 0.6022, IoU.couch: 0.7816, IoU.potted plant: 0.3736, IoU.bed: 0.7328, IoU.dining table: 0.6332, IoU.toilet: 0.8849, IoU.tv: 0.6840, IoU.laptop: 0.8599, IoU.mouse: 0.6608, IoU.remote: 0.7359, IoU.keyboard: 0.8370, IoU.cell phone: 0.7993, IoU.microwave: 0.5366, IoU.oven: 0.6273, IoU.toaster: 0.0000, IoU.sink: 0.7115, IoU.refrigerator: 0.8590, IoU.book: 0.7990, IoU.clock: 0.7826, IoU.vase: 0.6153, IoU.scissors: 0.7829, IoU.teddy bear: 0.8441, IoU.hair drier: 0.0000, IoU.toothbrush: 0.1386, IoU.banner: 0.2649, IoU.blanket: 0.1815, IoU.branch: 0.0888, IoU.bridge: 0.0247, IoU.building-other: 0.5392, IoU.bush: 0.2931, IoU.cabinet: 0.1680, IoU.cage: 0.0692, IoU.cardboard: 0.2217, IoU.carpet: 0.5680, IoU.ceiling-other: 0.6732, IoU.ceiling-tile: 0.0000, IoU.cloth: 0.0329, IoU.clothes: 0.1917, IoU.clouds: 0.4925, IoU.counter: 0.3566, IoU.cupboard: 0.4686, IoU.curtain: 0.6743, IoU.desk-stuff: 0.3190, IoU.dirt: 0.3123, IoU.door-stuff: 0.4605, IoU.fence: 0.4393, IoU.floor-marble: 0.0000, IoU.floor-other: 0.4035, IoU.floor-stone: 0.2856, IoU.floor-tile: 0.5716, IoU.floor-wood: 0.6811, IoU.flower: 0.1951, IoU.fog: 0.0000, IoU.food-other: 0.3760, IoU.fruit: 0.5569, IoU.furniture-other: 0.1492, IoU.grass: 0.7354, IoU.gravel: 0.2303, IoU.ground-other: 0.0932, IoU.hill: 0.2705, IoU.house: 0.2755, IoU.leaves: 0.0967, IoU.light: 0.3522, IoU.mat: 0.0904, IoU.metal: 0.1401, IoU.mirror-stuff: 0.4507, IoU.moss: 0.0000, IoU.mountain: 0.3615, IoU.mud: 0.0505, IoU.napkin: 0.3187, IoU.net: 0.2839, IoU.paper: 0.5029, IoU.pavement: 0.5382, IoU.pillow: 0.0000, IoU.plant-other: 0.3219, IoU.plastic: 0.1992, IoU.platform: 0.4282, IoU.playingfield: 0.6977, IoU.railing: 0.2115, IoU.railroad: 0.6223, IoU.river: 0.0485, IoU.road: 0.6741, IoU.rock: 0.4783, IoU.roof: 0.0701, IoU.rug: 0.3896, IoU.salad: 0.1186, IoU.sand: 0.7175, IoU.sea: 0.7314, IoU.shelf: 0.2622, IoU.sky-other: 0.6101, IoU.skyscraper: 0.0696, IoU.snow: 0.9139, IoU.solid-other: 0.0000, IoU.stairs: 0.3383, IoU.stone: 0.0567, IoU.straw: 0.1417, IoU.structural-other: 0.1679, IoU.table: 0.2675, IoU.tent: 0.7978, IoU.textile-other: 0.1807, IoU.towel: 0.4009, IoU.tree: 0.7784, IoU.vegetable: 0.4037, IoU.wall-brick: 0.4084, IoU.wall-concrete: 0.2351, IoU.wall-other: 0.6047, IoU.wall-panel: 0.0452, IoU.wall-stone: 0.3084, IoU.wall-tile: 0.5766, IoU.wall-wood: 0.3962, IoU.water-other: 0.3346, IoU.waterdrops: 0.0000, IoU.window-blind: 0.3904, IoU.window-other: 0.4689, IoU.wood: 0.1406, Acc.person: 0.9470, Acc.bicycle: 0.8822, Acc.car: 0.7032, Acc.motorcycle: 0.9623, Acc.airplane: 0.9523, Acc.bus: 0.9453, Acc.train: 0.9750, Acc.truck: 0.8815, Acc.boat: 0.8895, Acc.traffic light: 0.9054, Acc.fire hydrant: 0.9762, Acc.stop sign: 0.9871, Acc.parking meter: 0.7887, Acc.bench: 0.6877, Acc.bird: 0.8149, Acc.cat: 0.9625, Acc.dog: 0.9637, Acc.horse: 0.9597, Acc.sheep: 0.9122, Acc.cow: 0.9863, Acc.elephant: 0.9742, Acc.bear: 0.8897, Acc.zebra: 0.9585, Acc.giraffe: 0.9401, Acc.backpack: 0.5165, Acc.umbrella: 0.9034, Acc.handbag: 0.2140, Acc.tie: 0.2070, Acc.suitcase: 0.9698, Acc.frisbee: 0.9642, Acc.skis: 0.5148, Acc.snowboard: 0.7411, Acc.sports ball: 0.8736, Acc.kite: 0.8979, Acc.baseball bat: 0.7034, Acc.baseball glove: 0.0000, Acc.skateboard: 0.8345, Acc.surfboard: 0.9522, Acc.tennis racket: 0.8327, Acc.bottle: 0.8269, Acc.wine glass: 0.9160, Acc.cup: 0.9112, Acc.fork: 0.6242, Acc.knife: 0.8369, Acc.spoon: 0.6000, Acc.bowl: 0.7183, Acc.banana: 0.8621, Acc.apple: 0.8766, Acc.sandwich: 0.9779, Acc.orange: 0.7870, Acc.broccoli: 0.9087, Acc.carrot: 0.7593, Acc.hot dog: 0.9594, Acc.pizza: 0.9626, Acc.donut: 0.9080, Acc.cake: 0.8434, Acc.chair: 0.7664, Acc.couch: 0.9277, Acc.potted plant: 0.5245, Acc.bed: 0.8455, Acc.dining table: 0.7704, Acc.toilet: 0.9639, Acc.tv: 0.9114, Acc.laptop: 0.9621, Acc.mouse: 0.7303, Acc.remote: 0.8803, Acc.keyboard: 0.9791, Acc.cell phone: 0.9546, Acc.microwave: 0.6734, Acc.oven: 0.8601, Acc.toaster: 0.0000, Acc.sink: 0.7907, Acc.refrigerator: 0.9749, Acc.book: 0.8923, Acc.clock: 0.8703, Acc.vase: 0.9608, Acc.scissors: 0.9325, Acc.teddy bear: 0.9612, Acc.hair drier: 0.0000, Acc.toothbrush: 0.1729, Acc.banner: 0.4837, Acc.blanket: 0.2194, Acc.branch: 0.0898, Acc.bridge: 0.0334, Acc.building-other: 0.7156, Acc.bush: 0.4024, Acc.cabinet: 0.3570, Acc.cage: 0.2775, Acc.cardboard: 0.2968, Acc.carpet: 0.7626, Acc.ceiling-other: 0.8479, Acc.ceiling-tile: 0.0000, Acc.cloth: 0.0494, Acc.clothes: 0.2883, Acc.clouds: 0.6121, Acc.counter: 0.4319, Acc.cupboard: 0.5717, Acc.curtain: 0.8065, Acc.desk-stuff: 0.3534, Acc.dirt: 0.4872, Acc.door-stuff: 0.5837, Acc.fence: 0.6948, Acc.floor-marble: 0.0000, Acc.floor-other: 0.5321, Acc.floor-stone: 0.4127, Acc.floor-tile: 0.7470, Acc.floor-wood: 0.8137, Acc.flower: 0.4260, Acc.fog: 0.0000, Acc.food-other: 0.5690, Acc.fruit: 0.6704, Acc.furniture-other: 0.2162, Acc.grass: 0.8565, Acc.gravel: 0.2702, Acc.ground-other: 0.1914, Acc.hill: 0.3529, Acc.house: 0.4652, Acc.leaves: 0.1867, Acc.light: 0.4698, Acc.mat: 0.1211, Acc.metal: 0.1905, Acc.mirror-stuff: 0.6625, Acc.moss: 0.0000, Acc.mountain: 0.6363, Acc.mud: 0.0972, Acc.napkin: 0.6619, Acc.net: 0.3150, Acc.paper: 0.6601, Acc.pavement: 0.7121, Acc.pillow: 0.0000, Acc.plant-other: 0.4223, Acc.plastic: 0.2452, Acc.platform: 0.5279, Acc.playingfield: 0.8076, Acc.railing: 0.3333, Acc.railroad: 0.9439, Acc.river: 0.0543, Acc.road: 0.7610, Acc.rock: 0.7380, Acc.roof: 0.1200, Acc.rug: 0.5341, Acc.salad: 0.1281, Acc.sand: 0.8610, Acc.sea: 0.8933, Acc.shelf: 0.3946, Acc.sky-other: 0.7959, Acc.skyscraper: 0.0974, Acc.snow: 0.9489, Acc.solid-other: nan, Acc.stairs: 0.5404, Acc.stone: 0.0704, Acc.straw: 0.3315, Acc.structural-other: 0.2573, Acc.table: 0.4500, Acc.tent: 0.8768, Acc.textile-other: 0.2616, Acc.towel: 0.5131, Acc.tree: 0.8876, Acc.vegetable: 0.6720, Acc.wall-brick: 0.5085, Acc.wall-concrete: 0.3438, Acc.wall-other: 0.7772, Acc.wall-panel: 0.0670, Acc.wall-stone: 0.3705, Acc.wall-tile: 0.9004, Acc.wall-wood: 0.6521, Acc.water-other: 0.5190, Acc.waterdrops: nan, Acc.window-blind: 0.7324, Acc.window-other: 0.6070, Acc.wood: 0.2798 +2022-05-05 13:27:38,116 - mmseg - INFO - Iter [24050/80000] lr: 1.004e-06, eta: 9:48:04, time: 1.588, data_time: 0.992, memory: 60248, decode.loss_ce: 0.2320, decode.acc_seg: 74.3531, aux.loss_ce: 0.1544, aux.acc_seg: 71.0359, loss: 0.3864 +2022-05-05 13:28:07,788 - mmseg - INFO - Iter [24100/80000] lr: 1.003e-06, eta: 9:47:28, time: 0.593, data_time: 0.004, memory: 60248, decode.loss_ce: 0.2464, decode.acc_seg: 73.1067, aux.loss_ce: 0.1540, aux.acc_seg: 70.2531, loss: 0.4004 +2022-05-05 13:28:37,279 - mmseg - INFO - Iter [24150/80000] lr: 1.002e-06, eta: 9:46:52, time: 0.590, data_time: 0.005, memory: 60248, decode.loss_ce: 0.2242, decode.acc_seg: 74.7668, aux.loss_ce: 0.1500, aux.acc_seg: 71.5716, loss: 0.3742 +2022-05-05 13:29:09,359 - mmseg - INFO - Iter [24200/80000] lr: 1.001e-06, eta: 9:46:21, time: 0.642, data_time: 0.053, memory: 60248, decode.loss_ce: 0.2295, decode.acc_seg: 71.6048, aux.loss_ce: 0.1525, aux.acc_seg: 68.2361, loss: 0.3820 +2022-05-05 13:29:38,901 - mmseg - INFO - Iter [24250/80000] lr: 1.001e-06, eta: 9:45:45, time: 0.591, data_time: 0.005, memory: 60248, decode.loss_ce: 0.2230, decode.acc_seg: 73.0466, aux.loss_ce: 0.1482, aux.acc_seg: 69.9808, loss: 0.3712 +2022-05-05 13:30:08,379 - mmseg - INFO - Iter [24300/80000] lr: 9.997e-07, eta: 9:45:09, time: 0.590, data_time: 0.004, memory: 60248, decode.loss_ce: 0.2353, decode.acc_seg: 72.7193, aux.loss_ce: 0.1584, aux.acc_seg: 69.2610, loss: 0.3937 +2022-05-05 13:30:38,007 - mmseg - INFO - Iter [24350/80000] lr: 9.988e-07, eta: 9:44:33, time: 0.593, data_time: 0.004, memory: 60248, decode.loss_ce: 0.2351, decode.acc_seg: 74.7311, aux.loss_ce: 0.1564, aux.acc_seg: 71.2006, loss: 0.3916 +2022-05-05 13:31:07,683 - mmseg - INFO - Iter [24400/80000] lr: 9.979e-07, eta: 9:43:58, time: 0.593, data_time: 0.004, memory: 60248, decode.loss_ce: 0.2305, decode.acc_seg: 73.2325, aux.loss_ce: 0.1576, aux.acc_seg: 69.6924, loss: 0.3881 +2022-05-05 13:31:37,144 - mmseg - INFO - Iter [24450/80000] lr: 9.970e-07, eta: 9:43:21, time: 0.589, data_time: 0.005, memory: 60248, decode.loss_ce: 0.2303, decode.acc_seg: 73.2594, aux.loss_ce: 0.1554, aux.acc_seg: 69.9204, loss: 0.3858 +2022-05-05 13:32:06,815 - mmseg - INFO - Iter [24500/80000] lr: 9.961e-07, eta: 9:42:46, time: 0.593, data_time: 0.005, memory: 60248, decode.loss_ce: 0.2269, decode.acc_seg: 73.5564, aux.loss_ce: 0.1553, aux.acc_seg: 69.9116, loss: 0.3822 +2022-05-05 13:32:36,510 - mmseg - INFO - Iter [24550/80000] lr: 9.952e-07, eta: 9:42:10, time: 0.594, data_time: 0.004, memory: 60248, decode.loss_ce: 0.2334, decode.acc_seg: 73.8125, aux.loss_ce: 0.1518, aux.acc_seg: 70.6109, loss: 0.3852 +2022-05-05 13:33:05,871 - mmseg - INFO - Iter [24600/80000] lr: 9.943e-07, eta: 9:41:34, time: 0.588, data_time: 0.005, memory: 60248, decode.loss_ce: 0.2191, decode.acc_seg: 74.3163, aux.loss_ce: 0.1499, aux.acc_seg: 70.8746, loss: 0.3690 +2022-05-05 13:33:35,847 - mmseg - INFO - Iter [24650/80000] lr: 9.934e-07, eta: 9:40:59, time: 0.599, data_time: 0.005, memory: 60248, decode.loss_ce: 0.2221, decode.acc_seg: 72.4116, aux.loss_ce: 0.1505, aux.acc_seg: 69.3102, loss: 0.3727 +2022-05-05 13:34:05,262 - mmseg - INFO - Iter [24700/80000] lr: 9.925e-07, eta: 9:40:23, time: 0.588, data_time: 0.004, memory: 60248, decode.loss_ce: 0.2339, decode.acc_seg: 72.6574, aux.loss_ce: 0.1467, aux.acc_seg: 70.0999, loss: 0.3807 +2022-05-05 13:34:37,365 - mmseg - INFO - Iter [24750/80000] lr: 9.916e-07, eta: 9:39:53, time: 0.642, data_time: 0.055, memory: 60248, decode.loss_ce: 0.2155, decode.acc_seg: 73.8648, aux.loss_ce: 0.1418, aux.acc_seg: 70.8252, loss: 0.3572 +2022-05-05 13:35:06,791 - mmseg - INFO - Iter [24800/80000] lr: 9.907e-07, eta: 9:39:17, time: 0.589, data_time: 0.005, memory: 60248, decode.loss_ce: 0.2359, decode.acc_seg: 72.9024, aux.loss_ce: 0.1550, aux.acc_seg: 69.8429, loss: 0.3909 +2022-05-05 13:35:36,181 - mmseg - INFO - Iter [24850/80000] lr: 9.898e-07, eta: 9:38:40, time: 0.588, data_time: 0.004, memory: 60248, decode.loss_ce: 0.2191, decode.acc_seg: 73.1051, aux.loss_ce: 0.1442, aux.acc_seg: 70.4999, loss: 0.3633 +2022-05-05 13:36:05,748 - mmseg - INFO - Iter [24900/80000] lr: 9.889e-07, eta: 9:38:05, time: 0.591, data_time: 0.004, memory: 60248, decode.loss_ce: 0.2139, decode.acc_seg: 72.8430, aux.loss_ce: 0.1451, aux.acc_seg: 69.6246, loss: 0.3590 +2022-05-05 13:36:35,269 - mmseg - INFO - Iter [24950/80000] lr: 9.880e-07, eta: 9:37:29, time: 0.590, data_time: 0.004, memory: 60248, decode.loss_ce: 0.2087, decode.acc_seg: 74.3848, aux.loss_ce: 0.1455, aux.acc_seg: 70.9069, loss: 0.3542 +2022-05-05 13:37:04,632 - mmseg - INFO - Saving checkpoint at 25000 iterations +2022-05-05 13:37:26,499 - mmseg - INFO - Exp name: upernet_beit_adapter_large_512_80k_cocostuff10k_ss.py +2022-05-05 13:37:26,501 - mmseg - INFO - Iter [25000/80000] lr: 9.871e-07, eta: 9:37:41, time: 1.022, data_time: 0.005, memory: 60248, decode.loss_ce: 0.2085, decode.acc_seg: 73.2766, aux.loss_ce: 0.1431, aux.acc_seg: 70.2456, loss: 0.3516 +2022-05-05 13:37:56,684 - mmseg - INFO - Iter [25050/80000] lr: 9.862e-07, eta: 9:37:07, time: 0.606, data_time: 0.007, memory: 60248, decode.loss_ce: 0.2241, decode.acc_seg: 74.2939, aux.loss_ce: 0.1483, aux.acc_seg: 70.9640, loss: 0.3724 +2022-05-05 13:38:26,550 - mmseg - INFO - Iter [25100/80000] lr: 9.853e-07, eta: 9:36:31, time: 0.597, data_time: 0.004, memory: 60248, decode.loss_ce: 0.2215, decode.acc_seg: 73.8716, aux.loss_ce: 0.1495, aux.acc_seg: 70.4495, loss: 0.3710 +2022-05-05 13:38:55,984 - mmseg - INFO - Iter [25150/80000] lr: 9.844e-07, eta: 9:35:55, time: 0.589, data_time: 0.005, memory: 60248, decode.loss_ce: 0.2227, decode.acc_seg: 74.3440, aux.loss_ce: 0.1461, aux.acc_seg: 71.1817, loss: 0.3688 +2022-05-05 13:39:25,750 - mmseg - INFO - Iter [25200/80000] lr: 9.835e-07, eta: 9:35:20, time: 0.595, data_time: 0.005, memory: 60248, decode.loss_ce: 0.2413, decode.acc_seg: 72.9344, aux.loss_ce: 0.1564, aux.acc_seg: 69.4694, loss: 0.3977 +2022-05-05 13:39:55,093 - mmseg - INFO - Iter [25250/80000] lr: 9.826e-07, eta: 9:34:44, time: 0.586, data_time: 0.005, memory: 60248, decode.loss_ce: 0.2436, decode.acc_seg: 73.3626, aux.loss_ce: 0.1605, aux.acc_seg: 69.7841, loss: 0.4041 +2022-05-05 13:40:27,236 - mmseg - INFO - Iter [25300/80000] lr: 9.817e-07, eta: 9:34:14, time: 0.643, data_time: 0.053, memory: 60248, decode.loss_ce: 0.2254, decode.acc_seg: 74.4871, aux.loss_ce: 0.1551, aux.acc_seg: 70.9839, loss: 0.3805 +2022-05-05 13:40:56,928 - mmseg - INFO - Iter [25350/80000] lr: 9.808e-07, eta: 9:33:39, time: 0.594, data_time: 0.005, memory: 60248, decode.loss_ce: 0.2034, decode.acc_seg: 75.0765, aux.loss_ce: 0.1366, aux.acc_seg: 72.1867, loss: 0.3400 +2022-05-05 13:41:26,380 - mmseg - INFO - Iter [25400/80000] lr: 9.799e-07, eta: 9:33:03, time: 0.589, data_time: 0.004, memory: 60248, decode.loss_ce: 0.2163, decode.acc_seg: 73.4261, aux.loss_ce: 0.1435, aux.acc_seg: 70.4697, loss: 0.3598 +2022-05-05 13:41:55,787 - mmseg - INFO - Iter [25450/80000] lr: 9.791e-07, eta: 9:32:27, time: 0.588, data_time: 0.005, memory: 60248, decode.loss_ce: 0.2317, decode.acc_seg: 73.4806, aux.loss_ce: 0.1552, aux.acc_seg: 70.0319, loss: 0.3869 +2022-05-05 13:42:25,467 - mmseg - INFO - Iter [25500/80000] lr: 9.782e-07, eta: 9:31:51, time: 0.592, data_time: 0.005, memory: 60248, decode.loss_ce: 0.2237, decode.acc_seg: 73.2770, aux.loss_ce: 0.1501, aux.acc_seg: 69.8959, loss: 0.3737 +2022-05-05 13:42:55,096 - mmseg - INFO - Iter [25550/80000] lr: 9.773e-07, eta: 9:31:16, time: 0.595, data_time: 0.006, memory: 60248, decode.loss_ce: 0.2220, decode.acc_seg: 72.9961, aux.loss_ce: 0.1500, aux.acc_seg: 69.5838, loss: 0.3720 +2022-05-05 13:43:24,738 - mmseg - INFO - Iter [25600/80000] lr: 9.764e-07, eta: 9:30:41, time: 0.593, data_time: 0.005, memory: 60248, decode.loss_ce: 0.2200, decode.acc_seg: 72.2788, aux.loss_ce: 0.1501, aux.acc_seg: 68.8385, loss: 0.3701 +2022-05-05 13:43:54,232 - mmseg - INFO - Iter [25650/80000] lr: 9.755e-07, eta: 9:30:05, time: 0.590, data_time: 0.004, memory: 60248, decode.loss_ce: 0.2337, decode.acc_seg: 73.5337, aux.loss_ce: 0.1552, aux.acc_seg: 70.3866, loss: 0.3889 +2022-05-05 13:44:23,700 - mmseg - INFO - Iter [25700/80000] lr: 9.746e-07, eta: 9:29:29, time: 0.590, data_time: 0.005, memory: 60248, decode.loss_ce: 0.2177, decode.acc_seg: 74.3327, aux.loss_ce: 0.1459, aux.acc_seg: 71.2116, loss: 0.3636 +2022-05-05 13:44:53,093 - mmseg - INFO - Iter [25750/80000] lr: 9.737e-07, eta: 9:28:53, time: 0.588, data_time: 0.005, memory: 60248, decode.loss_ce: 0.2219, decode.acc_seg: 73.6505, aux.loss_ce: 0.1474, aux.acc_seg: 70.6922, loss: 0.3693 +2022-05-05 13:45:23,287 - mmseg - INFO - Iter [25800/80000] lr: 9.728e-07, eta: 9:28:19, time: 0.604, data_time: 0.005, memory: 60248, decode.loss_ce: 0.2150, decode.acc_seg: 72.4628, aux.loss_ce: 0.1376, aux.acc_seg: 69.7696, loss: 0.3527 +2022-05-05 13:45:52,742 - mmseg - INFO - Iter [25850/80000] lr: 9.719e-07, eta: 9:27:44, time: 0.589, data_time: 0.005, memory: 60248, decode.loss_ce: 0.2202, decode.acc_seg: 74.6036, aux.loss_ce: 0.1456, aux.acc_seg: 71.5650, loss: 0.3658 +2022-05-05 13:46:25,137 - mmseg - INFO - Iter [25900/80000] lr: 9.710e-07, eta: 9:27:14, time: 0.648, data_time: 0.053, memory: 60248, decode.loss_ce: 0.2253, decode.acc_seg: 73.2538, aux.loss_ce: 0.1468, aux.acc_seg: 70.3578, loss: 0.3721 +2022-05-05 13:46:54,821 - mmseg - INFO - Iter [25950/80000] lr: 9.701e-07, eta: 9:26:39, time: 0.594, data_time: 0.004, memory: 60248, decode.loss_ce: 0.2029, decode.acc_seg: 72.6003, aux.loss_ce: 0.1378, aux.acc_seg: 69.6725, loss: 0.3407 +2022-05-05 13:47:24,487 - mmseg - INFO - Saving checkpoint at 26000 iterations +2022-05-05 13:47:44,685 - mmseg - INFO - Exp name: upernet_beit_adapter_large_512_80k_cocostuff10k_ss.py +2022-05-05 13:47:44,688 - mmseg - INFO - Iter [26000/80000] lr: 9.692e-07, eta: 9:26:46, time: 0.995, data_time: 0.004, memory: 60248, decode.loss_ce: 0.2237, decode.acc_seg: 74.0977, aux.loss_ce: 0.1522, aux.acc_seg: 70.4686, loss: 0.3760 +2022-05-05 13:48:14,446 - mmseg - INFO - Iter [26050/80000] lr: 9.683e-07, eta: 9:26:11, time: 0.597, data_time: 0.007, memory: 60248, decode.loss_ce: 0.2237, decode.acc_seg: 74.7206, aux.loss_ce: 0.1489, aux.acc_seg: 71.7790, loss: 0.3725 +2022-05-05 13:48:44,183 - mmseg - INFO - Iter [26100/80000] lr: 9.674e-07, eta: 9:25:36, time: 0.595, data_time: 0.005, memory: 60248, decode.loss_ce: 0.2245, decode.acc_seg: 73.5094, aux.loss_ce: 0.1504, aux.acc_seg: 70.2288, loss: 0.3749 +2022-05-05 13:49:13,553 - mmseg - INFO - Iter [26150/80000] lr: 9.665e-07, eta: 9:25:00, time: 0.587, data_time: 0.005, memory: 60248, decode.loss_ce: 0.2225, decode.acc_seg: 72.8697, aux.loss_ce: 0.1456, aux.acc_seg: 69.8050, loss: 0.3681 +2022-05-05 13:49:43,027 - mmseg - INFO - Iter [26200/80000] lr: 9.656e-07, eta: 9:24:24, time: 0.590, data_time: 0.005, memory: 60248, decode.loss_ce: 0.2091, decode.acc_seg: 73.1168, aux.loss_ce: 0.1434, aux.acc_seg: 69.8889, loss: 0.3525 +2022-05-05 13:50:12,541 - mmseg - INFO - Iter [26250/80000] lr: 9.647e-07, eta: 9:23:49, time: 0.590, data_time: 0.004, memory: 60248, decode.loss_ce: 0.2249, decode.acc_seg: 73.2306, aux.loss_ce: 0.1501, aux.acc_seg: 69.8495, loss: 0.3751 +2022-05-05 13:50:41,873 - mmseg - INFO - Iter [26300/80000] lr: 9.638e-07, eta: 9:23:13, time: 0.586, data_time: 0.005, memory: 60248, decode.loss_ce: 0.2222, decode.acc_seg: 74.0840, aux.loss_ce: 0.1443, aux.acc_seg: 71.1328, loss: 0.3664 +2022-05-05 13:51:11,496 - mmseg - INFO - Iter [26350/80000] lr: 9.629e-07, eta: 9:22:38, time: 0.593, data_time: 0.005, memory: 60248, decode.loss_ce: 0.2248, decode.acc_seg: 74.7399, aux.loss_ce: 0.1464, aux.acc_seg: 71.7572, loss: 0.3712 +2022-05-05 13:51:41,026 - mmseg - INFO - Iter [26400/80000] lr: 9.620e-07, eta: 9:22:02, time: 0.591, data_time: 0.005, memory: 60248, decode.loss_ce: 0.2185, decode.acc_seg: 74.1307, aux.loss_ce: 0.1458, aux.acc_seg: 70.7739, loss: 0.3642 +2022-05-05 13:52:13,200 - mmseg - INFO - Iter [26450/80000] lr: 9.611e-07, eta: 9:21:32, time: 0.644, data_time: 0.052, memory: 60248, decode.loss_ce: 0.2142, decode.acc_seg: 73.3278, aux.loss_ce: 0.1399, aux.acc_seg: 70.5036, loss: 0.3541 +2022-05-05 13:52:42,903 - mmseg - INFO - Iter [26500/80000] lr: 9.602e-07, eta: 9:20:57, time: 0.594, data_time: 0.004, memory: 60248, decode.loss_ce: 0.2207, decode.acc_seg: 73.5535, aux.loss_ce: 0.1461, aux.acc_seg: 70.5064, loss: 0.3668 +2022-05-05 13:53:12,323 - mmseg - INFO - Iter [26550/80000] lr: 9.593e-07, eta: 9:20:22, time: 0.588, data_time: 0.004, memory: 60248, decode.loss_ce: 0.2106, decode.acc_seg: 72.8729, aux.loss_ce: 0.1431, aux.acc_seg: 69.6979, loss: 0.3537 +2022-05-05 13:53:41,941 - mmseg - INFO - Iter [26600/80000] lr: 9.584e-07, eta: 9:19:47, time: 0.592, data_time: 0.005, memory: 60248, decode.loss_ce: 0.2069, decode.acc_seg: 73.1902, aux.loss_ce: 0.1393, aux.acc_seg: 70.1775, loss: 0.3461 +2022-05-05 13:54:11,810 - mmseg - INFO - Iter [26650/80000] lr: 9.575e-07, eta: 9:19:12, time: 0.597, data_time: 0.006, memory: 60248, decode.loss_ce: 0.2142, decode.acc_seg: 74.7015, aux.loss_ce: 0.1383, aux.acc_seg: 71.8358, loss: 0.3525 +2022-05-05 13:54:41,221 - mmseg - INFO - Iter [26700/80000] lr: 9.566e-07, eta: 9:18:36, time: 0.588, data_time: 0.005, memory: 60248, decode.loss_ce: 0.2098, decode.acc_seg: 74.3907, aux.loss_ce: 0.1407, aux.acc_seg: 71.3945, loss: 0.3506 +2022-05-05 13:55:11,118 - mmseg - INFO - Iter [26750/80000] lr: 9.557e-07, eta: 9:18:02, time: 0.598, data_time: 0.005, memory: 60248, decode.loss_ce: 0.2181, decode.acc_seg: 74.1709, aux.loss_ce: 0.1418, aux.acc_seg: 71.5047, loss: 0.3599 +2022-05-05 13:55:40,695 - mmseg - INFO - Iter [26800/80000] lr: 9.548e-07, eta: 9:17:27, time: 0.592, data_time: 0.005, memory: 60248, decode.loss_ce: 0.2065, decode.acc_seg: 74.0771, aux.loss_ce: 0.1380, aux.acc_seg: 70.9509, loss: 0.3445 +2022-05-05 13:56:10,472 - mmseg - INFO - Iter [26850/80000] lr: 9.539e-07, eta: 9:16:52, time: 0.595, data_time: 0.005, memory: 60248, decode.loss_ce: 0.2207, decode.acc_seg: 73.7637, aux.loss_ce: 0.1501, aux.acc_seg: 70.6152, loss: 0.3709 +2022-05-05 13:56:39,981 - mmseg - INFO - Iter [26900/80000] lr: 9.530e-07, eta: 9:16:17, time: 0.590, data_time: 0.004, memory: 60248, decode.loss_ce: 0.2109, decode.acc_seg: 73.1719, aux.loss_ce: 0.1423, aux.acc_seg: 69.9806, loss: 0.3532 +2022-05-05 13:57:09,578 - mmseg - INFO - Iter [26950/80000] lr: 9.521e-07, eta: 9:15:42, time: 0.592, data_time: 0.005, memory: 60248, decode.loss_ce: 0.2275, decode.acc_seg: 73.5986, aux.loss_ce: 0.1474, aux.acc_seg: 70.3939, loss: 0.3749 +2022-05-05 13:57:41,653 - mmseg - INFO - Saving checkpoint at 27000 iterations +2022-05-05 13:58:01,578 - mmseg - INFO - Exp name: upernet_beit_adapter_large_512_80k_cocostuff10k_ss.py +2022-05-05 13:58:01,580 - mmseg - INFO - Iter [27000/80000] lr: 9.512e-07, eta: 9:15:51, time: 1.038, data_time: 0.056, memory: 60248, decode.loss_ce: 0.2128, decode.acc_seg: 74.6999, aux.loss_ce: 0.1437, aux.acc_seg: 71.6282, loss: 0.3566 +2022-05-05 13:58:31,337 - mmseg - INFO - Iter [27050/80000] lr: 9.503e-07, eta: 9:15:16, time: 0.597, data_time: 0.006, memory: 60248, decode.loss_ce: 0.2099, decode.acc_seg: 73.8051, aux.loss_ce: 0.1401, aux.acc_seg: 70.7218, loss: 0.3500 +2022-05-05 13:59:01,105 - mmseg - INFO - Iter [27100/80000] lr: 9.494e-07, eta: 9:14:41, time: 0.595, data_time: 0.004, memory: 60248, decode.loss_ce: 0.2097, decode.acc_seg: 74.1030, aux.loss_ce: 0.1405, aux.acc_seg: 71.2011, loss: 0.3502 +2022-05-05 13:59:30,688 - mmseg - INFO - Iter [27150/80000] lr: 9.485e-07, eta: 9:14:06, time: 0.592, data_time: 0.004, memory: 60248, decode.loss_ce: 0.2177, decode.acc_seg: 73.3787, aux.loss_ce: 0.1455, aux.acc_seg: 70.3359, loss: 0.3633 +2022-05-05 14:00:00,447 - mmseg - INFO - Iter [27200/80000] lr: 9.476e-07, eta: 9:13:31, time: 0.595, data_time: 0.005, memory: 60248, decode.loss_ce: 0.2052, decode.acc_seg: 73.3377, aux.loss_ce: 0.1389, aux.acc_seg: 70.0763, loss: 0.3441 +2022-05-05 14:00:30,015 - mmseg - INFO - Iter [27250/80000] lr: 9.467e-07, eta: 9:12:56, time: 0.591, data_time: 0.005, memory: 60248, decode.loss_ce: 0.2090, decode.acc_seg: 74.4098, aux.loss_ce: 0.1421, aux.acc_seg: 71.1702, loss: 0.3511 +2022-05-05 14:01:00,001 - mmseg - INFO - Iter [27300/80000] lr: 9.458e-07, eta: 9:12:22, time: 0.600, data_time: 0.005, memory: 60248, decode.loss_ce: 0.2081, decode.acc_seg: 74.6417, aux.loss_ce: 0.1376, aux.acc_seg: 71.7905, loss: 0.3457 +2022-05-05 14:01:29,578 - mmseg - INFO - Iter [27350/80000] lr: 9.450e-07, eta: 9:11:47, time: 0.591, data_time: 0.004, memory: 60248, decode.loss_ce: 0.2004, decode.acc_seg: 74.2490, aux.loss_ce: 0.1316, aux.acc_seg: 71.5241, loss: 0.3320 +2022-05-05 14:01:59,556 - mmseg - INFO - Iter [27400/80000] lr: 9.441e-07, eta: 9:11:13, time: 0.600, data_time: 0.005, memory: 60248, decode.loss_ce: 0.2143, decode.acc_seg: 74.3730, aux.loss_ce: 0.1428, aux.acc_seg: 71.2717, loss: 0.3571 +2022-05-05 14:02:29,265 - mmseg - INFO - Iter [27450/80000] lr: 9.432e-07, eta: 9:10:38, time: 0.594, data_time: 0.005, memory: 60248, decode.loss_ce: 0.2198, decode.acc_seg: 73.1470, aux.loss_ce: 0.1452, aux.acc_seg: 70.1156, loss: 0.3650 +2022-05-05 14:02:59,124 - mmseg - INFO - Iter [27500/80000] lr: 9.423e-07, eta: 9:10:03, time: 0.597, data_time: 0.005, memory: 60248, decode.loss_ce: 0.2243, decode.acc_seg: 74.5498, aux.loss_ce: 0.1466, aux.acc_seg: 71.4188, loss: 0.3709 +2022-05-05 14:03:31,168 - mmseg - INFO - Iter [27550/80000] lr: 9.414e-07, eta: 9:09:33, time: 0.641, data_time: 0.054, memory: 60248, decode.loss_ce: 0.2052, decode.acc_seg: 75.5375, aux.loss_ce: 0.1354, aux.acc_seg: 72.5495, loss: 0.3406 +2022-05-05 14:04:00,791 - mmseg - INFO - Iter [27600/80000] lr: 9.405e-07, eta: 9:08:58, time: 0.592, data_time: 0.005, memory: 60248, decode.loss_ce: 0.2130, decode.acc_seg: 72.6786, aux.loss_ce: 0.1392, aux.acc_seg: 69.8357, loss: 0.3523 +2022-05-05 14:04:30,433 - mmseg - INFO - Iter [27650/80000] lr: 9.396e-07, eta: 9:08:24, time: 0.593, data_time: 0.004, memory: 60248, decode.loss_ce: 0.2086, decode.acc_seg: 73.5752, aux.loss_ce: 0.1426, aux.acc_seg: 70.1874, loss: 0.3513 +2022-05-05 14:05:00,447 - mmseg - INFO - Iter [27700/80000] lr: 9.387e-07, eta: 9:07:49, time: 0.600, data_time: 0.004, memory: 60248, decode.loss_ce: 0.2036, decode.acc_seg: 75.8139, aux.loss_ce: 0.1327, aux.acc_seg: 73.1741, loss: 0.3363 +2022-05-05 14:05:30,262 - mmseg - INFO - Iter [27750/80000] lr: 9.378e-07, eta: 9:07:15, time: 0.596, data_time: 0.005, memory: 60248, decode.loss_ce: 0.2023, decode.acc_seg: 74.1567, aux.loss_ce: 0.1364, aux.acc_seg: 71.2127, loss: 0.3387 +2022-05-05 14:05:59,888 - mmseg - INFO - Iter [27800/80000] lr: 9.369e-07, eta: 9:06:40, time: 0.592, data_time: 0.005, memory: 60248, decode.loss_ce: 0.2059, decode.acc_seg: 72.5055, aux.loss_ce: 0.1367, aux.acc_seg: 69.4764, loss: 0.3427 +2022-05-05 14:06:29,198 - mmseg - INFO - Iter [27850/80000] lr: 9.360e-07, eta: 9:06:05, time: 0.586, data_time: 0.004, memory: 60248, decode.loss_ce: 0.2106, decode.acc_seg: 74.4580, aux.loss_ce: 0.1375, aux.acc_seg: 71.5548, loss: 0.3481 +2022-05-05 14:06:58,791 - mmseg - INFO - Iter [27900/80000] lr: 9.351e-07, eta: 9:05:30, time: 0.592, data_time: 0.005, memory: 60248, decode.loss_ce: 0.2016, decode.acc_seg: 73.8423, aux.loss_ce: 0.1300, aux.acc_seg: 71.4390, loss: 0.3316 +2022-05-05 14:07:28,896 - mmseg - INFO - Iter [27950/80000] lr: 9.342e-07, eta: 9:04:56, time: 0.602, data_time: 0.005, memory: 60248, decode.loss_ce: 0.2034, decode.acc_seg: 74.7289, aux.loss_ce: 0.1383, aux.acc_seg: 71.3921, loss: 0.3417 +2022-05-05 14:07:58,363 - mmseg - INFO - Saving checkpoint at 28000 iterations +2022-05-05 14:08:18,323 - mmseg - INFO - Exp name: upernet_beit_adapter_large_512_80k_cocostuff10k_ss.py +2022-05-05 14:08:18,325 - mmseg - INFO - Iter [28000/80000] lr: 9.333e-07, eta: 9:04:58, time: 0.987, data_time: 0.005, memory: 60248, decode.loss_ce: 0.2118, decode.acc_seg: 73.9646, aux.loss_ce: 0.1370, aux.acc_seg: 71.1696, loss: 0.3488 +2022-05-05 14:08:48,203 - mmseg - INFO - Iter [28050/80000] lr: 9.324e-07, eta: 9:04:24, time: 0.600, data_time: 0.007, memory: 60248, decode.loss_ce: 0.2219, decode.acc_seg: 74.1526, aux.loss_ce: 0.1474, aux.acc_seg: 70.9783, loss: 0.3694 +2022-05-05 14:09:18,012 - mmseg - INFO - Iter [28100/80000] lr: 9.315e-07, eta: 9:03:49, time: 0.596, data_time: 0.005, memory: 60248, decode.loss_ce: 0.2069, decode.acc_seg: 74.5400, aux.loss_ce: 0.1376, aux.acc_seg: 71.5508, loss: 0.3445 +2022-05-05 14:09:50,373 - mmseg - INFO - Iter [28150/80000] lr: 9.306e-07, eta: 9:03:20, time: 0.645, data_time: 0.056, memory: 60248, decode.loss_ce: 0.2196, decode.acc_seg: 74.6762, aux.loss_ce: 0.1430, aux.acc_seg: 71.8978, loss: 0.3626 +2022-05-05 14:10:20,275 - mmseg - INFO - Iter [28200/80000] lr: 9.297e-07, eta: 9:02:45, time: 0.600, data_time: 0.008, memory: 60248, decode.loss_ce: 0.2117, decode.acc_seg: 73.8328, aux.loss_ce: 0.1417, aux.acc_seg: 70.8919, loss: 0.3534 +2022-05-05 14:10:49,611 - mmseg - INFO - Iter [28250/80000] lr: 9.288e-07, eta: 9:02:10, time: 0.587, data_time: 0.004, memory: 60248, decode.loss_ce: 0.2000, decode.acc_seg: 72.8286, aux.loss_ce: 0.1308, aux.acc_seg: 70.0917, loss: 0.3309 +2022-05-05 14:11:19,142 - mmseg - INFO - Iter [28300/80000] lr: 9.279e-07, eta: 9:01:35, time: 0.591, data_time: 0.005, memory: 60248, decode.loss_ce: 0.2183, decode.acc_seg: 73.0949, aux.loss_ce: 0.1376, aux.acc_seg: 70.3959, loss: 0.3558 +2022-05-05 14:11:48,989 - mmseg - INFO - Iter [28350/80000] lr: 9.270e-07, eta: 9:01:01, time: 0.597, data_time: 0.004, memory: 60248, decode.loss_ce: 0.2120, decode.acc_seg: 75.3316, aux.loss_ce: 0.1385, aux.acc_seg: 72.6132, loss: 0.3505 +2022-05-05 14:12:18,464 - mmseg - INFO - Iter [28400/80000] lr: 9.261e-07, eta: 9:00:26, time: 0.590, data_time: 0.004, memory: 60248, decode.loss_ce: 0.2098, decode.acc_seg: 74.5753, aux.loss_ce: 0.1347, aux.acc_seg: 72.0712, loss: 0.3444 +2022-05-05 14:12:47,897 - mmseg - INFO - Iter [28450/80000] lr: 9.252e-07, eta: 8:59:51, time: 0.588, data_time: 0.004, memory: 60248, decode.loss_ce: 0.2113, decode.acc_seg: 74.6801, aux.loss_ce: 0.1388, aux.acc_seg: 71.8816, loss: 0.3501 +2022-05-05 14:13:17,412 - mmseg - INFO - Iter [28500/80000] lr: 9.243e-07, eta: 8:59:16, time: 0.591, data_time: 0.005, memory: 60248, decode.loss_ce: 0.2188, decode.acc_seg: 74.5521, aux.loss_ce: 0.1414, aux.acc_seg: 71.7293, loss: 0.3602 +2022-05-05 14:13:47,731 - mmseg - INFO - Iter [28550/80000] lr: 9.234e-07, eta: 8:58:43, time: 0.606, data_time: 0.005, memory: 60248, decode.loss_ce: 0.2035, decode.acc_seg: 73.4395, aux.loss_ce: 0.1378, aux.acc_seg: 70.3295, loss: 0.3413 +2022-05-05 14:14:17,129 - mmseg - INFO - Iter [28600/80000] lr: 9.225e-07, eta: 8:58:08, time: 0.588, data_time: 0.005, memory: 60248, decode.loss_ce: 0.2135, decode.acc_seg: 74.0757, aux.loss_ce: 0.1337, aux.acc_seg: 71.3733, loss: 0.3471 +2022-05-05 14:14:46,790 - mmseg - INFO - Iter [28650/80000] lr: 9.216e-07, eta: 8:57:33, time: 0.593, data_time: 0.005, memory: 60248, decode.loss_ce: 0.2109, decode.acc_seg: 74.0361, aux.loss_ce: 0.1400, aux.acc_seg: 70.8810, loss: 0.3508 +2022-05-05 14:15:19,647 - mmseg - INFO - Iter [28700/80000] lr: 9.207e-07, eta: 8:57:04, time: 0.657, data_time: 0.058, memory: 60248, decode.loss_ce: 0.2042, decode.acc_seg: 74.4947, aux.loss_ce: 0.1346, aux.acc_seg: 71.4511, loss: 0.3387 +2022-05-05 14:15:49,182 - mmseg - INFO - Iter [28750/80000] lr: 9.198e-07, eta: 8:56:30, time: 0.591, data_time: 0.004, memory: 60248, decode.loss_ce: 0.2029, decode.acc_seg: 74.8336, aux.loss_ce: 0.1349, aux.acc_seg: 71.9383, loss: 0.3378 +2022-05-05 14:16:19,584 - mmseg - INFO - Iter [28800/80000] lr: 9.189e-07, eta: 8:55:56, time: 0.608, data_time: 0.005, memory: 60248, decode.loss_ce: 0.2166, decode.acc_seg: 74.4190, aux.loss_ce: 0.1403, aux.acc_seg: 71.5929, loss: 0.3570 +2022-05-05 14:16:49,117 - mmseg - INFO - Iter [28850/80000] lr: 9.180e-07, eta: 8:55:22, time: 0.591, data_time: 0.004, memory: 60248, decode.loss_ce: 0.2132, decode.acc_seg: 74.1944, aux.loss_ce: 0.1352, aux.acc_seg: 71.4101, loss: 0.3484 +2022-05-05 14:17:18,579 - mmseg - INFO - Iter [28900/80000] lr: 9.171e-07, eta: 8:54:47, time: 0.589, data_time: 0.004, memory: 60248, decode.loss_ce: 0.2084, decode.acc_seg: 75.0048, aux.loss_ce: 0.1353, aux.acc_seg: 72.4219, loss: 0.3437 +2022-05-05 14:17:48,225 - mmseg - INFO - Iter [28950/80000] lr: 9.162e-07, eta: 8:54:12, time: 0.593, data_time: 0.005, memory: 60248, decode.loss_ce: 0.1986, decode.acc_seg: 74.4877, aux.loss_ce: 0.1314, aux.acc_seg: 71.7342, loss: 0.3300 +2022-05-05 14:18:18,360 - mmseg - INFO - Saving checkpoint at 29000 iterations +2022-05-05 14:18:38,396 - mmseg - INFO - Exp name: upernet_beit_adapter_large_512_80k_cocostuff10k_ss.py +2022-05-05 14:18:38,399 - mmseg - INFO - Iter [29000/80000] lr: 9.153e-07, eta: 8:54:14, time: 1.001, data_time: 0.007, memory: 60248, decode.loss_ce: 0.2076, decode.acc_seg: 74.9073, aux.loss_ce: 0.1392, aux.acc_seg: 71.9045, loss: 0.3468 +2022-05-05 14:19:08,258 - mmseg - INFO - Iter [29050/80000] lr: 9.144e-07, eta: 8:53:40, time: 0.598, data_time: 0.006, memory: 60248, decode.loss_ce: 0.2142, decode.acc_seg: 74.1625, aux.loss_ce: 0.1385, aux.acc_seg: 71.2318, loss: 0.3527 +2022-05-05 14:19:37,790 - mmseg - INFO - Iter [29100/80000] lr: 9.135e-07, eta: 8:53:05, time: 0.592, data_time: 0.006, memory: 60248, decode.loss_ce: 0.1964, decode.acc_seg: 73.4379, aux.loss_ce: 0.1289, aux.acc_seg: 70.7742, loss: 0.3252 +2022-05-05 14:20:07,137 - mmseg - INFO - Iter [29150/80000] lr: 9.126e-07, eta: 8:52:30, time: 0.587, data_time: 0.004, memory: 60248, decode.loss_ce: 0.1978, decode.acc_seg: 74.4427, aux.loss_ce: 0.1321, aux.acc_seg: 71.6682, loss: 0.3299 +2022-05-05 14:20:37,595 - mmseg - INFO - Iter [29200/80000] lr: 9.117e-07, eta: 8:51:57, time: 0.609, data_time: 0.006, memory: 60248, decode.loss_ce: 0.1905, decode.acc_seg: 74.9522, aux.loss_ce: 0.1276, aux.acc_seg: 72.1767, loss: 0.3182 +2022-05-05 14:21:09,466 - mmseg - INFO - Iter [29250/80000] lr: 9.109e-07, eta: 8:51:26, time: 0.637, data_time: 0.055, memory: 60248, decode.loss_ce: 0.2088, decode.acc_seg: 74.8330, aux.loss_ce: 0.1373, aux.acc_seg: 72.0773, loss: 0.3461 +2022-05-05 14:21:38,938 - mmseg - INFO - Iter [29300/80000] lr: 9.100e-07, eta: 8:50:52, time: 0.589, data_time: 0.004, memory: 60248, decode.loss_ce: 0.2001, decode.acc_seg: 74.9625, aux.loss_ce: 0.1301, aux.acc_seg: 72.3505, loss: 0.3302 +2022-05-05 14:22:08,664 - mmseg - INFO - Iter [29350/80000] lr: 9.091e-07, eta: 8:50:17, time: 0.595, data_time: 0.005, memory: 60248, decode.loss_ce: 0.1965, decode.acc_seg: 73.7798, aux.loss_ce: 0.1300, aux.acc_seg: 71.1191, loss: 0.3264 +2022-05-05 14:22:38,210 - mmseg - INFO - Iter [29400/80000] lr: 9.082e-07, eta: 8:49:42, time: 0.589, data_time: 0.004, memory: 60248, decode.loss_ce: 0.2074, decode.acc_seg: 75.0284, aux.loss_ce: 0.1347, aux.acc_seg: 72.4374, loss: 0.3420 +2022-05-05 14:23:07,763 - mmseg - INFO - Iter [29450/80000] lr: 9.073e-07, eta: 8:49:08, time: 0.593, data_time: 0.006, memory: 60248, decode.loss_ce: 0.1965, decode.acc_seg: 74.5620, aux.loss_ce: 0.1349, aux.acc_seg: 71.4669, loss: 0.3314 +2022-05-05 14:23:37,178 - mmseg - INFO - Iter [29500/80000] lr: 9.064e-07, eta: 8:48:33, time: 0.588, data_time: 0.004, memory: 60248, decode.loss_ce: 0.1905, decode.acc_seg: 74.3878, aux.loss_ce: 0.1278, aux.acc_seg: 71.7885, loss: 0.3183 +2022-05-05 14:24:06,644 - mmseg - INFO - Iter [29550/80000] lr: 9.055e-07, eta: 8:47:59, time: 0.589, data_time: 0.004, memory: 60248, decode.loss_ce: 0.1973, decode.acc_seg: 73.9941, aux.loss_ce: 0.1275, aux.acc_seg: 71.3263, loss: 0.3248 +2022-05-05 14:24:36,355 - mmseg - INFO - Iter [29600/80000] lr: 9.046e-07, eta: 8:47:24, time: 0.594, data_time: 0.004, memory: 60248, decode.loss_ce: 0.1917, decode.acc_seg: 74.0920, aux.loss_ce: 0.1267, aux.acc_seg: 71.1752, loss: 0.3184 +2022-05-05 14:25:06,143 - mmseg - INFO - Iter [29650/80000] lr: 9.037e-07, eta: 8:46:50, time: 0.595, data_time: 0.004, memory: 60248, decode.loss_ce: 0.2069, decode.acc_seg: 74.7745, aux.loss_ce: 0.1356, aux.acc_seg: 72.0068, loss: 0.3425 +2022-05-05 14:25:35,651 - mmseg - INFO - Iter [29700/80000] lr: 9.028e-07, eta: 8:46:15, time: 0.590, data_time: 0.005, memory: 60248, decode.loss_ce: 0.2085, decode.acc_seg: 73.8391, aux.loss_ce: 0.1379, aux.acc_seg: 70.8877, loss: 0.3463 +2022-05-05 14:26:05,315 - mmseg - INFO - Iter [29750/80000] lr: 9.019e-07, eta: 8:45:41, time: 0.594, data_time: 0.005, memory: 60248, decode.loss_ce: 0.2093, decode.acc_seg: 75.3299, aux.loss_ce: 0.1312, aux.acc_seg: 72.7894, loss: 0.3405 +2022-05-05 14:26:37,210 - mmseg - INFO - Iter [29800/80000] lr: 9.010e-07, eta: 8:45:11, time: 0.638, data_time: 0.055, memory: 60248, decode.loss_ce: 0.1921, decode.acc_seg: 74.2551, aux.loss_ce: 0.1297, aux.acc_seg: 71.1991, loss: 0.3218 +2022-05-05 14:27:06,944 - mmseg - INFO - Iter [29850/80000] lr: 9.001e-07, eta: 8:44:37, time: 0.595, data_time: 0.004, memory: 60248, decode.loss_ce: 0.1968, decode.acc_seg: 74.4374, aux.loss_ce: 0.1325, aux.acc_seg: 71.4482, loss: 0.3293 +2022-05-05 14:27:36,396 - mmseg - INFO - Iter [29900/80000] lr: 8.992e-07, eta: 8:44:02, time: 0.589, data_time: 0.004, memory: 60248, decode.loss_ce: 0.1976, decode.acc_seg: 74.5828, aux.loss_ce: 0.1315, aux.acc_seg: 71.7739, loss: 0.3292 +2022-05-05 14:28:06,119 - mmseg - INFO - Iter [29950/80000] lr: 8.983e-07, eta: 8:43:28, time: 0.594, data_time: 0.004, memory: 60248, decode.loss_ce: 0.1899, decode.acc_seg: 73.7409, aux.loss_ce: 0.1273, aux.acc_seg: 70.9542, loss: 0.3172 +2022-05-05 14:28:35,498 - mmseg - INFO - Saving checkpoint at 30000 iterations +2022-05-05 14:28:56,262 - mmseg - INFO - Exp name: upernet_beit_adapter_large_512_80k_cocostuff10k_ss.py +2022-05-05 14:28:56,269 - mmseg - INFO - Iter [30000/80000] lr: 8.974e-07, eta: 8:43:27, time: 1.000, data_time: 0.004, memory: 60248, decode.loss_ce: 0.2157, decode.acc_seg: 74.3582, aux.loss_ce: 0.1372, aux.acc_seg: 71.7352, loss: 0.3528 +2022-05-05 14:29:26,097 - mmseg - INFO - Iter [30050/80000] lr: 8.965e-07, eta: 8:42:54, time: 0.599, data_time: 0.007, memory: 60248, decode.loss_ce: 0.2018, decode.acc_seg: 72.9349, aux.loss_ce: 0.1335, aux.acc_seg: 70.1215, loss: 0.3352 +2022-05-05 14:29:55,749 - mmseg - INFO - Iter [30100/80000] lr: 8.956e-07, eta: 8:42:19, time: 0.593, data_time: 0.004, memory: 60248, decode.loss_ce: 0.1948, decode.acc_seg: 74.4659, aux.loss_ce: 0.1303, aux.acc_seg: 71.6119, loss: 0.3251 +2022-05-05 14:30:25,309 - mmseg - INFO - Iter [30150/80000] lr: 8.947e-07, eta: 8:41:45, time: 0.591, data_time: 0.004, memory: 60248, decode.loss_ce: 0.2133, decode.acc_seg: 75.6650, aux.loss_ce: 0.1399, aux.acc_seg: 72.8039, loss: 0.3532 +2022-05-05 14:30:54,698 - mmseg - INFO - Iter [30200/80000] lr: 8.938e-07, eta: 8:41:10, time: 0.588, data_time: 0.004, memory: 60248, decode.loss_ce: 0.1971, decode.acc_seg: 73.3004, aux.loss_ce: 0.1295, aux.acc_seg: 70.8313, loss: 0.3265 +2022-05-05 14:31:24,305 - mmseg - INFO - Iter [30250/80000] lr: 8.929e-07, eta: 8:40:36, time: 0.592, data_time: 0.005, memory: 60248, decode.loss_ce: 0.2086, decode.acc_seg: 74.0263, aux.loss_ce: 0.1341, aux.acc_seg: 71.5103, loss: 0.3427 +2022-05-05 14:31:54,550 - mmseg - INFO - Iter [30300/80000] lr: 8.920e-07, eta: 8:40:03, time: 0.605, data_time: 0.005, memory: 60248, decode.loss_ce: 0.2000, decode.acc_seg: 74.5058, aux.loss_ce: 0.1309, aux.acc_seg: 71.8094, loss: 0.3308 +2022-05-05 14:32:26,667 - mmseg - INFO - Iter [30350/80000] lr: 8.911e-07, eta: 8:39:32, time: 0.642, data_time: 0.052, memory: 60248, decode.loss_ce: 0.2050, decode.acc_seg: 73.9830, aux.loss_ce: 0.1322, aux.acc_seg: 71.2815, loss: 0.3372 +2022-05-05 14:32:56,095 - mmseg - INFO - Iter [30400/80000] lr: 8.902e-07, eta: 8:38:58, time: 0.589, data_time: 0.005, memory: 60248, decode.loss_ce: 0.1880, decode.acc_seg: 72.7404, aux.loss_ce: 0.1245, aux.acc_seg: 70.1548, loss: 0.3125 +2022-05-05 14:33:25,523 - mmseg - INFO - Iter [30450/80000] lr: 8.893e-07, eta: 8:38:23, time: 0.588, data_time: 0.005, memory: 60248, decode.loss_ce: 0.1870, decode.acc_seg: 75.2941, aux.loss_ce: 0.1228, aux.acc_seg: 72.7859, loss: 0.3098 +2022-05-05 14:33:54,955 - mmseg - INFO - Iter [30500/80000] lr: 8.884e-07, eta: 8:37:49, time: 0.589, data_time: 0.007, memory: 60248, decode.loss_ce: 0.1961, decode.acc_seg: 75.3796, aux.loss_ce: 0.1287, aux.acc_seg: 72.7168, loss: 0.3248 +2022-05-05 14:34:24,272 - mmseg - INFO - Iter [30550/80000] lr: 8.875e-07, eta: 8:37:14, time: 0.586, data_time: 0.005, memory: 60248, decode.loss_ce: 0.1887, decode.acc_seg: 74.8041, aux.loss_ce: 0.1266, aux.acc_seg: 71.9244, loss: 0.3153 +2022-05-05 14:34:53,815 - mmseg - INFO - Iter [30600/80000] lr: 8.866e-07, eta: 8:36:40, time: 0.591, data_time: 0.005, memory: 60248, decode.loss_ce: 0.1935, decode.acc_seg: 73.3155, aux.loss_ce: 0.1271, aux.acc_seg: 70.6913, loss: 0.3206 +2022-05-05 14:35:23,252 - mmseg - INFO - Iter [30650/80000] lr: 8.857e-07, eta: 8:36:05, time: 0.589, data_time: 0.004, memory: 60248, decode.loss_ce: 0.1967, decode.acc_seg: 75.0038, aux.loss_ce: 0.1287, aux.acc_seg: 72.3460, loss: 0.3253 +2022-05-05 14:35:52,737 - mmseg - INFO - Iter [30700/80000] lr: 8.848e-07, eta: 8:35:31, time: 0.590, data_time: 0.005, memory: 60248, decode.loss_ce: 0.2113, decode.acc_seg: 74.3646, aux.loss_ce: 0.1380, aux.acc_seg: 71.5553, loss: 0.3493 +2022-05-05 14:36:22,018 - mmseg - INFO - Iter [30750/80000] lr: 8.839e-07, eta: 8:34:56, time: 0.586, data_time: 0.005, memory: 60248, decode.loss_ce: 0.1958, decode.acc_seg: 73.9447, aux.loss_ce: 0.1263, aux.acc_seg: 71.5066, loss: 0.3222 +2022-05-05 14:36:51,644 - mmseg - INFO - Iter [30800/80000] lr: 8.830e-07, eta: 8:34:22, time: 0.592, data_time: 0.004, memory: 60248, decode.loss_ce: 0.1899, decode.acc_seg: 74.0799, aux.loss_ce: 0.1258, aux.acc_seg: 71.4693, loss: 0.3156 +2022-05-05 14:37:21,088 - mmseg - INFO - Iter [30850/80000] lr: 8.821e-07, eta: 8:33:47, time: 0.589, data_time: 0.004, memory: 60248, decode.loss_ce: 0.1970, decode.acc_seg: 75.1879, aux.loss_ce: 0.1306, aux.acc_seg: 72.3442, loss: 0.3276 +2022-05-05 14:37:50,711 - mmseg - INFO - Iter [30900/80000] lr: 8.812e-07, eta: 8:33:13, time: 0.592, data_time: 0.005, memory: 60248, decode.loss_ce: 0.1857, decode.acc_seg: 75.3697, aux.loss_ce: 0.1277, aux.acc_seg: 72.3429, loss: 0.3134 +2022-05-05 14:38:22,967 - mmseg - INFO - Iter [30950/80000] lr: 8.803e-07, eta: 8:32:43, time: 0.645, data_time: 0.053, memory: 60248, decode.loss_ce: 0.2012, decode.acc_seg: 74.7796, aux.loss_ce: 0.1298, aux.acc_seg: 72.1773, loss: 0.3310 +2022-05-05 14:38:52,450 - mmseg - INFO - Saving checkpoint at 31000 iterations +2022-05-05 14:39:13,885 - mmseg - INFO - Exp name: upernet_beit_adapter_large_512_80k_cocostuff10k_ss.py +2022-05-05 14:39:13,891 - mmseg - INFO - Iter [31000/80000] lr: 8.794e-07, eta: 8:32:43, time: 1.017, data_time: 0.005, memory: 60248, decode.loss_ce: 0.1998, decode.acc_seg: 74.6902, aux.loss_ce: 0.1310, aux.acc_seg: 71.7585, loss: 0.3308 +2022-05-05 14:39:43,431 - mmseg - INFO - Iter [31050/80000] lr: 8.785e-07, eta: 8:32:09, time: 0.592, data_time: 0.006, memory: 60248, decode.loss_ce: 0.1890, decode.acc_seg: 73.3043, aux.loss_ce: 0.1237, aux.acc_seg: 70.6553, loss: 0.3127 +2022-05-05 14:40:13,023 - mmseg - INFO - Iter [31100/80000] lr: 8.776e-07, eta: 8:31:34, time: 0.592, data_time: 0.005, memory: 60248, decode.loss_ce: 0.1862, decode.acc_seg: 75.1946, aux.loss_ce: 0.1262, aux.acc_seg: 72.4283, loss: 0.3124 +2022-05-05 14:40:42,414 - mmseg - INFO - Iter [31150/80000] lr: 8.768e-07, eta: 8:31:00, time: 0.588, data_time: 0.004, memory: 60248, decode.loss_ce: 0.2018, decode.acc_seg: 73.0863, aux.loss_ce: 0.1326, aux.acc_seg: 70.5921, loss: 0.3344 +2022-05-05 14:41:12,033 - mmseg - INFO - Iter [31200/80000] lr: 8.759e-07, eta: 8:30:26, time: 0.592, data_time: 0.004, memory: 60248, decode.loss_ce: 0.1943, decode.acc_seg: 76.4583, aux.loss_ce: 0.1278, aux.acc_seg: 73.8076, loss: 0.3220 +2022-05-05 14:41:41,475 - mmseg - INFO - Iter [31250/80000] lr: 8.750e-07, eta: 8:29:51, time: 0.589, data_time: 0.005, memory: 60248, decode.loss_ce: 0.1888, decode.acc_seg: 74.4878, aux.loss_ce: 0.1231, aux.acc_seg: 72.0495, loss: 0.3119 +2022-05-05 14:42:10,950 - mmseg - INFO - Iter [31300/80000] lr: 8.741e-07, eta: 8:29:17, time: 0.590, data_time: 0.005, memory: 60248, decode.loss_ce: 0.1973, decode.acc_seg: 73.1313, aux.loss_ce: 0.1255, aux.acc_seg: 70.5453, loss: 0.3228 +2022-05-05 14:42:40,496 - mmseg - INFO - Iter [31350/80000] lr: 8.732e-07, eta: 8:28:43, time: 0.591, data_time: 0.005, memory: 60248, decode.loss_ce: 0.1773, decode.acc_seg: 74.7851, aux.loss_ce: 0.1202, aux.acc_seg: 72.1190, loss: 0.2974 +2022-05-05 14:43:09,830 - mmseg - INFO - Iter [31400/80000] lr: 8.723e-07, eta: 8:28:08, time: 0.587, data_time: 0.005, memory: 60248, decode.loss_ce: 0.1928, decode.acc_seg: 75.8948, aux.loss_ce: 0.1235, aux.acc_seg: 73.4991, loss: 0.3163 +2022-05-05 14:43:39,372 - mmseg - INFO - Iter [31450/80000] lr: 8.714e-07, eta: 8:27:34, time: 0.590, data_time: 0.004, memory: 60248, decode.loss_ce: 0.2041, decode.acc_seg: 74.2926, aux.loss_ce: 0.1314, aux.acc_seg: 71.7025, loss: 0.3355 +2022-05-05 14:44:11,543 - mmseg - INFO - Iter [31500/80000] lr: 8.705e-07, eta: 8:27:04, time: 0.644, data_time: 0.054, memory: 60248, decode.loss_ce: 0.2181, decode.acc_seg: 73.7806, aux.loss_ce: 0.1349, aux.acc_seg: 71.1779, loss: 0.3530 +2022-05-05 14:44:41,200 - mmseg - INFO - Iter [31550/80000] lr: 8.696e-07, eta: 8:26:30, time: 0.593, data_time: 0.005, memory: 60248, decode.loss_ce: 0.2031, decode.acc_seg: 73.8650, aux.loss_ce: 0.1301, aux.acc_seg: 71.2600, loss: 0.3332 +2022-05-05 14:45:10,849 - mmseg - INFO - Iter [31600/80000] lr: 8.687e-07, eta: 8:25:56, time: 0.593, data_time: 0.005, memory: 60248, decode.loss_ce: 0.1921, decode.acc_seg: 73.2478, aux.loss_ce: 0.1199, aux.acc_seg: 71.0078, loss: 0.3120 +2022-05-05 14:45:40,341 - mmseg - INFO - Iter [31650/80000] lr: 8.678e-07, eta: 8:25:22, time: 0.590, data_time: 0.004, memory: 60248, decode.loss_ce: 0.1969, decode.acc_seg: 73.5252, aux.loss_ce: 0.1297, aux.acc_seg: 70.8944, loss: 0.3266 +2022-05-05 14:46:10,050 - mmseg - INFO - Iter [31700/80000] lr: 8.669e-07, eta: 8:24:48, time: 0.594, data_time: 0.004, memory: 60248, decode.loss_ce: 0.1950, decode.acc_seg: 75.6227, aux.loss_ce: 0.1236, aux.acc_seg: 73.3451, loss: 0.3186 +2022-05-05 14:46:39,746 - mmseg - INFO - Iter [31750/80000] lr: 8.660e-07, eta: 8:24:14, time: 0.594, data_time: 0.005, memory: 60248, decode.loss_ce: 0.1983, decode.acc_seg: 74.6457, aux.loss_ce: 0.1329, aux.acc_seg: 71.7858, loss: 0.3313 +2022-05-05 14:47:09,393 - mmseg - INFO - Iter [31800/80000] lr: 8.651e-07, eta: 8:23:40, time: 0.593, data_time: 0.005, memory: 60248, decode.loss_ce: 0.1924, decode.acc_seg: 74.4769, aux.loss_ce: 0.1259, aux.acc_seg: 71.9430, loss: 0.3183 +2022-05-05 14:47:39,156 - mmseg - INFO - Iter [31850/80000] lr: 8.642e-07, eta: 8:23:06, time: 0.595, data_time: 0.006, memory: 60248, decode.loss_ce: 0.2022, decode.acc_seg: 75.6404, aux.loss_ce: 0.1329, aux.acc_seg: 72.8508, loss: 0.3352 +2022-05-05 14:48:08,615 - mmseg - INFO - Iter [31900/80000] lr: 8.633e-07, eta: 8:22:32, time: 0.589, data_time: 0.005, memory: 60248, decode.loss_ce: 0.1959, decode.acc_seg: 74.8243, aux.loss_ce: 0.1284, aux.acc_seg: 71.9777, loss: 0.3243 +2022-05-05 14:48:38,116 - mmseg - INFO - Iter [31950/80000] lr: 8.624e-07, eta: 8:21:58, time: 0.590, data_time: 0.004, memory: 60248, decode.loss_ce: 0.1968, decode.acc_seg: 75.1763, aux.loss_ce: 0.1294, aux.acc_seg: 72.5215, loss: 0.3263 +2022-05-05 14:49:07,460 - mmseg - INFO - Saving checkpoint at 32000 iterations +2022-05-05 14:49:27,293 - mmseg - INFO - Exp name: upernet_beit_adapter_large_512_80k_cocostuff10k_ss.py +2022-05-05 14:49:27,295 - mmseg - INFO - Iter [32000/80000] lr: 8.615e-07, eta: 8:21:53, time: 0.982, data_time: 0.004, memory: 60248, decode.loss_ce: 0.1827, decode.acc_seg: 75.3611, aux.loss_ce: 0.1188, aux.acc_seg: 72.9934, loss: 0.3015 +2022-05-05 14:49:56,982 - mmseg - INFO - per class results: +2022-05-05 14:49:56,992 - mmseg - INFO - ++------------------+-------+-------+ +| Class | IoU | Acc | ++------------------+-------+-------+ +| person | 87.74 | 94.62 | +| bicycle | 72.99 | 89.47 | +| car | 62.81 | 69.24 | +| motorcycle | 86.91 | 96.24 | +| airplane | 87.16 | 95.96 | +| bus | 85.1 | 94.31 | +| train | 83.14 | 93.82 | +| truck | 74.35 | 88.95 | +| boat | 73.42 | 87.6 | +| traffic light | 71.76 | 91.08 | +| fire hydrant | 85.89 | 98.18 | +| stop sign | 91.01 | 97.94 | +| parking meter | 79.18 | 82.69 | +| bench | 52.69 | 68.11 | +| bird | 76.14 | 83.95 | +| cat | 91.23 | 95.97 | +| dog | 91.13 | 96.98 | +| horse | 89.36 | 95.64 | +| sheep | 87.22 | 91.02 | +| cow | 93.86 | 99.0 | +| elephant | 91.4 | 97.9 | +| bear | 92.23 | 96.78 | +| zebra | 90.34 | 96.52 | +| giraffe | 85.86 | 95.65 | +| backpack | 24.19 | 52.58 | +| umbrella | 79.34 | 89.88 | +| handbag | 17.51 | 22.59 | +| tie | 46.5 | 46.5 | +| suitcase | 76.32 | 96.36 | +| frisbee | 93.34 | 97.1 | +| skis | 28.91 | 39.2 | +| snowboard | 64.81 | 77.69 | +| sports ball | 81.4 | 88.37 | +| kite | 63.37 | 85.24 | +| baseball bat | 56.49 | 72.91 | +| baseball glove | 0.18 | 0.18 | +| skateboard | 65.67 | 86.28 | +| surfboard | 83.81 | 95.01 | +| tennis racket | 77.6 | 82.48 | +| bottle | 73.3 | 86.54 | +| wine glass | 82.34 | 93.24 | +| cup | 65.82 | 90.37 | +| fork | 41.81 | 67.45 | +| knife | 73.72 | 81.01 | +| spoon | 42.32 | 64.43 | +| bowl | 51.82 | 65.31 | +| banana | 79.1 | 88.23 | +| apple | 72.11 | 89.19 | +| sandwich | 83.52 | 96.47 | +| orange | 67.57 | 87.94 | +| broccoli | 92.73 | 94.4 | +| carrot | 36.25 | 64.53 | +| hot dog | 51.44 | 94.5 | +| pizza | 92.61 | 94.67 | +| donut | 68.91 | 95.48 | +| cake | 76.43 | 90.77 | +| chair | 60.85 | 78.48 | +| couch | 75.08 | 90.52 | +| potted plant | 34.02 | 46.89 | +| bed | 73.25 | 84.68 | +| dining table | 60.28 | 76.43 | +| toilet | 88.03 | 96.52 | +| tv | 73.27 | 90.74 | +| laptop | 87.5 | 97.6 | +| mouse | 63.29 | 71.2 | +| remote | 69.54 | 92.69 | +| keyboard | 83.53 | 98.48 | +| cell phone | 76.91 | 96.04 | +| microwave | 59.22 | 73.01 | +| oven | 61.63 | 86.31 | +| toaster | 12.26 | 12.37 | +| sink | 70.8 | 79.36 | +| refrigerator | 89.17 | 95.26 | +| book | 79.07 | 89.36 | +| clock | 78.1 | 86.89 | +| vase | 62.17 | 94.64 | +| scissors | 76.06 | 95.52 | +| teddy bear | 84.7 | 95.08 | +| hair drier | 0.0 | 0.0 | +| toothbrush | 14.55 | 21.74 | +| banner | 22.63 | 40.73 | +| blanket | 20.21 | 20.46 | +| branch | 0.0 | 0.0 | +| bridge | 3.25 | 4.49 | +| building-other | 55.17 | 73.81 | +| bush | 24.3 | 30.02 | +| cabinet | 18.91 | 44.55 | +| cage | 5.21 | 10.93 | +| cardboard | 24.35 | 29.4 | +| carpet | 50.09 | 71.29 | +| ceiling-other | 69.17 | 86.28 | +| ceiling-tile | 11.14 | 12.98 | +| cloth | 6.95 | 10.74 | +| clothes | 22.16 | 36.36 | +| clouds | 54.91 | 74.7 | +| counter | 34.07 | 44.91 | +| cupboard | 48.47 | 59.39 | +| curtain | 64.51 | 79.82 | +| desk-stuff | 34.14 | 38.03 | +| dirt | 32.27 | 52.93 | +| door-stuff | 47.36 | 59.24 | +| fence | 43.35 | 72.97 | +| floor-marble | 0.13 | 0.24 | +| floor-other | 38.73 | 56.6 | +| floor-stone | 22.05 | 31.68 | +| floor-tile | 64.03 | 75.23 | +| floor-wood | 69.42 | 84.48 | +| flower | 18.7 | 45.87 | +| fog | 0.0 | 0.0 | +| food-other | 36.46 | 49.44 | +| fruit | 60.29 | 73.62 | +| furniture-other | 14.97 | 20.8 | +| grass | 74.18 | 84.87 | +| gravel | 24.11 | 29.31 | +| ground-other | 7.71 | 14.61 | +| hill | 29.2 | 40.22 | +| house | 27.74 | 43.99 | +| leaves | 13.22 | 18.82 | +| light | 39.35 | 51.1 | +| mat | 9.5 | 14.79 | +| metal | 14.92 | 19.01 | +| mirror-stuff | 45.66 | 65.05 | +| moss | 0.0 | 0.0 | +| mountain | 36.51 | 55.28 | +| mud | 9.34 | 17.12 | +| napkin | 68.97 | 91.33 | +| net | 17.6 | 18.58 | +| paper | 46.77 | 58.77 | +| pavement | 55.5 | 72.34 | +| pillow | 0.0 | 0.0 | +| plant-other | 27.81 | 40.29 | +| plastic | 18.94 | 26.22 | +| platform | 32.29 | 50.3 | +| playingfield | 69.14 | 81.55 | +| railing | 17.73 | 26.07 | +| railroad | 63.45 | 92.65 | +| river | 2.1 | 2.45 | +| road | 66.65 | 76.89 | +| rock | 49.93 | 74.95 | +| roof | 6.38 | 11.1 | +| rug | 38.5 | 54.11 | +| salad | 15.61 | 17.09 | +| sand | 74.77 | 86.58 | +| sea | 74.74 | 87.37 | +| shelf | 27.38 | 38.37 | +| sky-other | 60.58 | 70.88 | +| skyscraper | 6.22 | 8.73 | +| snow | 88.48 | 96.08 | +| solid-other | 0.0 | nan | +| stairs | 29.5 | 47.52 | +| stone | 5.8 | 7.21 | +| straw | 13.74 | 32.92 | +| structural-other | 17.35 | 26.21 | +| table | 19.74 | 29.42 | +| tent | 79.61 | 86.12 | +| textile-other | 15.39 | 19.17 | +| towel | 38.98 | 47.83 | +| tree | 77.16 | 89.52 | +| vegetable | 43.42 | 65.23 | +| wall-brick | 39.15 | 46.89 | +| wall-concrete | 24.23 | 31.46 | +| wall-other | 60.1 | 79.78 | +| wall-panel | 5.96 | 6.59 | +| wall-stone | 29.15 | 36.43 | +| wall-tile | 60.76 | 91.57 | +| wall-wood | 36.9 | 61.61 | +| water-other | 32.75 | 55.05 | +| waterdrops | nan | nan | +| window-blind | 25.44 | 54.5 | +| window-other | 44.62 | 56.86 | +| wood | 13.33 | 29.52 | ++------------------+-------+-------+ +2022-05-05 14:49:56,992 - mmseg - INFO - Summary: +2022-05-05 14:49:56,992 - mmseg - INFO - ++-------+-------+-------+ +| aAcc | mIoU | mAcc | ++-------+-------+-------+ +| 75.09 | 50.11 | 62.45 | ++-------+-------+-------+ +2022-05-05 14:49:56,995 - mmseg - INFO - The previous best checkpoint /mnt/lustre/chenzhe.vendor/workspace/ViT-Adapter/segmentation/work_dirs/upernet_beit_adapter_large_512_80k_cocostuff10k_ss/best_mIoU_iter_24000.pth was removed +2022-05-05 14:50:17,898 - mmseg - INFO - Now best checkpoint is saved as best_mIoU_iter_32000.pth. +2022-05-05 14:50:17,908 - mmseg - INFO - Best mIoU is 0.5011 at 32000 iter. +2022-05-05 14:50:17,917 - mmseg - INFO - Exp name: upernet_beit_adapter_large_512_80k_cocostuff10k_ss.py +2022-05-05 14:50:17,918 - mmseg - INFO - Iter(val) [125] aAcc: 0.7509, mIoU: 0.5011, mAcc: 0.6245, IoU.person: 0.8774, IoU.bicycle: 0.7299, IoU.car: 0.6281, IoU.motorcycle: 0.8691, IoU.airplane: 0.8716, IoU.bus: 0.8510, IoU.train: 0.8314, IoU.truck: 0.7435, IoU.boat: 0.7342, IoU.traffic light: 0.7176, IoU.fire hydrant: 0.8589, IoU.stop sign: 0.9101, IoU.parking meter: 0.7918, IoU.bench: 0.5269, IoU.bird: 0.7614, IoU.cat: 0.9123, IoU.dog: 0.9113, IoU.horse: 0.8936, IoU.sheep: 0.8722, IoU.cow: 0.9386, IoU.elephant: 0.9140, IoU.bear: 0.9223, IoU.zebra: 0.9034, IoU.giraffe: 0.8586, IoU.backpack: 0.2419, IoU.umbrella: 0.7934, IoU.handbag: 0.1751, IoU.tie: 0.4650, IoU.suitcase: 0.7632, IoU.frisbee: 0.9334, IoU.skis: 0.2891, IoU.snowboard: 0.6481, IoU.sports ball: 0.8140, IoU.kite: 0.6337, IoU.baseball bat: 0.5649, IoU.baseball glove: 0.0018, IoU.skateboard: 0.6567, IoU.surfboard: 0.8381, IoU.tennis racket: 0.7760, IoU.bottle: 0.7330, IoU.wine glass: 0.8234, IoU.cup: 0.6582, IoU.fork: 0.4181, IoU.knife: 0.7372, IoU.spoon: 0.4232, IoU.bowl: 0.5182, IoU.banana: 0.7910, IoU.apple: 0.7211, IoU.sandwich: 0.8352, IoU.orange: 0.6757, IoU.broccoli: 0.9273, IoU.carrot: 0.3625, IoU.hot dog: 0.5144, IoU.pizza: 0.9261, IoU.donut: 0.6891, IoU.cake: 0.7643, IoU.chair: 0.6085, IoU.couch: 0.7508, IoU.potted plant: 0.3402, IoU.bed: 0.7325, IoU.dining table: 0.6028, IoU.toilet: 0.8803, IoU.tv: 0.7327, IoU.laptop: 0.8750, IoU.mouse: 0.6329, IoU.remote: 0.6954, IoU.keyboard: 0.8353, IoU.cell phone: 0.7691, IoU.microwave: 0.5922, IoU.oven: 0.6163, IoU.toaster: 0.1226, IoU.sink: 0.7080, IoU.refrigerator: 0.8917, IoU.book: 0.7907, IoU.clock: 0.7810, IoU.vase: 0.6217, IoU.scissors: 0.7606, IoU.teddy bear: 0.8470, IoU.hair drier: 0.0000, IoU.toothbrush: 0.1455, IoU.banner: 0.2263, IoU.blanket: 0.2021, IoU.branch: 0.0000, IoU.bridge: 0.0325, IoU.building-other: 0.5517, IoU.bush: 0.2430, IoU.cabinet: 0.1891, IoU.cage: 0.0521, IoU.cardboard: 0.2435, IoU.carpet: 0.5009, IoU.ceiling-other: 0.6917, IoU.ceiling-tile: 0.1114, IoU.cloth: 0.0695, IoU.clothes: 0.2216, IoU.clouds: 0.5491, IoU.counter: 0.3407, IoU.cupboard: 0.4847, IoU.curtain: 0.6451, IoU.desk-stuff: 0.3414, IoU.dirt: 0.3227, IoU.door-stuff: 0.4736, IoU.fence: 0.4335, IoU.floor-marble: 0.0013, IoU.floor-other: 0.3873, IoU.floor-stone: 0.2205, IoU.floor-tile: 0.6403, IoU.floor-wood: 0.6942, IoU.flower: 0.1870, IoU.fog: 0.0000, IoU.food-other: 0.3646, IoU.fruit: 0.6029, IoU.furniture-other: 0.1497, IoU.grass: 0.7418, IoU.gravel: 0.2411, IoU.ground-other: 0.0771, IoU.hill: 0.2920, IoU.house: 0.2774, IoU.leaves: 0.1322, IoU.light: 0.3935, IoU.mat: 0.0950, IoU.metal: 0.1492, IoU.mirror-stuff: 0.4566, IoU.moss: 0.0000, IoU.mountain: 0.3651, IoU.mud: 0.0934, IoU.napkin: 0.6897, IoU.net: 0.1760, IoU.paper: 0.4677, IoU.pavement: 0.5550, IoU.pillow: 0.0000, IoU.plant-other: 0.2781, IoU.plastic: 0.1894, IoU.platform: 0.3229, IoU.playingfield: 0.6914, IoU.railing: 0.1773, IoU.railroad: 0.6345, IoU.river: 0.0210, IoU.road: 0.6665, IoU.rock: 0.4993, IoU.roof: 0.0638, IoU.rug: 0.3850, IoU.salad: 0.1561, IoU.sand: 0.7477, IoU.sea: 0.7474, IoU.shelf: 0.2738, IoU.sky-other: 0.6058, IoU.skyscraper: 0.0622, IoU.snow: 0.8848, IoU.solid-other: 0.0000, IoU.stairs: 0.2950, IoU.stone: 0.0580, IoU.straw: 0.1374, IoU.structural-other: 0.1735, IoU.table: 0.1974, IoU.tent: 0.7961, IoU.textile-other: 0.1539, IoU.towel: 0.3898, IoU.tree: 0.7716, IoU.vegetable: 0.4342, IoU.wall-brick: 0.3915, IoU.wall-concrete: 0.2423, IoU.wall-other: 0.6010, IoU.wall-panel: 0.0596, IoU.wall-stone: 0.2915, IoU.wall-tile: 0.6076, IoU.wall-wood: 0.3690, IoU.water-other: 0.3275, IoU.waterdrops: nan, IoU.window-blind: 0.2544, IoU.window-other: 0.4462, IoU.wood: 0.1333, Acc.person: 0.9462, Acc.bicycle: 0.8947, Acc.car: 0.6924, Acc.motorcycle: 0.9624, Acc.airplane: 0.9596, Acc.bus: 0.9431, Acc.train: 0.9382, Acc.truck: 0.8895, Acc.boat: 0.8760, Acc.traffic light: 0.9108, Acc.fire hydrant: 0.9818, Acc.stop sign: 0.9794, Acc.parking meter: 0.8269, Acc.bench: 0.6811, Acc.bird: 0.8395, Acc.cat: 0.9597, Acc.dog: 0.9698, Acc.horse: 0.9564, Acc.sheep: 0.9102, Acc.cow: 0.9900, Acc.elephant: 0.9790, Acc.bear: 0.9678, Acc.zebra: 0.9652, Acc.giraffe: 0.9565, Acc.backpack: 0.5258, Acc.umbrella: 0.8988, Acc.handbag: 0.2259, Acc.tie: 0.4650, Acc.suitcase: 0.9636, Acc.frisbee: 0.9710, Acc.skis: 0.3920, Acc.snowboard: 0.7769, Acc.sports ball: 0.8837, Acc.kite: 0.8524, Acc.baseball bat: 0.7291, Acc.baseball glove: 0.0018, Acc.skateboard: 0.8628, Acc.surfboard: 0.9501, Acc.tennis racket: 0.8248, Acc.bottle: 0.8654, Acc.wine glass: 0.9324, Acc.cup: 0.9037, Acc.fork: 0.6745, Acc.knife: 0.8101, Acc.spoon: 0.6443, Acc.bowl: 0.6531, Acc.banana: 0.8823, Acc.apple: 0.8919, Acc.sandwich: 0.9647, Acc.orange: 0.8794, Acc.broccoli: 0.9440, Acc.carrot: 0.6453, Acc.hot dog: 0.9450, Acc.pizza: 0.9467, Acc.donut: 0.9548, Acc.cake: 0.9077, Acc.chair: 0.7848, Acc.couch: 0.9052, Acc.potted plant: 0.4689, Acc.bed: 0.8468, Acc.dining table: 0.7643, Acc.toilet: 0.9652, Acc.tv: 0.9074, Acc.laptop: 0.9760, Acc.mouse: 0.7120, Acc.remote: 0.9269, Acc.keyboard: 0.9848, Acc.cell phone: 0.9604, Acc.microwave: 0.7301, Acc.oven: 0.8631, Acc.toaster: 0.1237, Acc.sink: 0.7936, Acc.refrigerator: 0.9526, Acc.book: 0.8936, Acc.clock: 0.8689, Acc.vase: 0.9464, Acc.scissors: 0.9552, Acc.teddy bear: 0.9508, Acc.hair drier: 0.0000, Acc.toothbrush: 0.2174, Acc.banner: 0.4073, Acc.blanket: 0.2046, Acc.branch: 0.0000, Acc.bridge: 0.0449, Acc.building-other: 0.7381, Acc.bush: 0.3002, Acc.cabinet: 0.4455, Acc.cage: 0.1093, Acc.cardboard: 0.2940, Acc.carpet: 0.7129, Acc.ceiling-other: 0.8628, Acc.ceiling-tile: 0.1298, Acc.cloth: 0.1074, Acc.clothes: 0.3636, Acc.clouds: 0.7470, Acc.counter: 0.4491, Acc.cupboard: 0.5939, Acc.curtain: 0.7982, Acc.desk-stuff: 0.3803, Acc.dirt: 0.5293, Acc.door-stuff: 0.5924, Acc.fence: 0.7297, Acc.floor-marble: 0.0024, Acc.floor-other: 0.5660, Acc.floor-stone: 0.3168, Acc.floor-tile: 0.7523, Acc.floor-wood: 0.8448, Acc.flower: 0.4587, Acc.fog: 0.0000, Acc.food-other: 0.4944, Acc.fruit: 0.7362, Acc.furniture-other: 0.2080, Acc.grass: 0.8487, Acc.gravel: 0.2931, Acc.ground-other: 0.1461, Acc.hill: 0.4022, Acc.house: 0.4399, Acc.leaves: 0.1882, Acc.light: 0.5110, Acc.mat: 0.1479, Acc.metal: 0.1901, Acc.mirror-stuff: 0.6505, Acc.moss: 0.0000, Acc.mountain: 0.5528, Acc.mud: 0.1712, Acc.napkin: 0.9133, Acc.net: 0.1858, Acc.paper: 0.5877, Acc.pavement: 0.7234, Acc.pillow: 0.0000, Acc.plant-other: 0.4029, Acc.plastic: 0.2622, Acc.platform: 0.5030, Acc.playingfield: 0.8155, Acc.railing: 0.2607, Acc.railroad: 0.9265, Acc.river: 0.0245, Acc.road: 0.7689, Acc.rock: 0.7495, Acc.roof: 0.1110, Acc.rug: 0.5411, Acc.salad: 0.1709, Acc.sand: 0.8658, Acc.sea: 0.8737, Acc.shelf: 0.3837, Acc.sky-other: 0.7088, Acc.skyscraper: 0.0873, Acc.snow: 0.9608, Acc.solid-other: nan, Acc.stairs: 0.4752, Acc.stone: 0.0721, Acc.straw: 0.3292, Acc.structural-other: 0.2621, Acc.table: 0.2942, Acc.tent: 0.8612, Acc.textile-other: 0.1917, Acc.towel: 0.4783, Acc.tree: 0.8952, Acc.vegetable: 0.6523, Acc.wall-brick: 0.4689, Acc.wall-concrete: 0.3146, Acc.wall-other: 0.7978, Acc.wall-panel: 0.0659, Acc.wall-stone: 0.3643, Acc.wall-tile: 0.9157, Acc.wall-wood: 0.6161, Acc.water-other: 0.5505, Acc.waterdrops: nan, Acc.window-blind: 0.5450, Acc.window-other: 0.5686, Acc.wood: 0.2952 +2022-05-05 14:50:50,451 - mmseg - INFO - Iter [32050/80000] lr: 8.606e-07, eta: 8:22:39, time: 1.665, data_time: 1.072, memory: 60248, decode.loss_ce: 0.2031, decode.acc_seg: 74.9493, aux.loss_ce: 0.1269, aux.acc_seg: 72.5864, loss: 0.3299 +2022-05-05 14:51:20,205 - mmseg - INFO - Iter [32100/80000] lr: 8.597e-07, eta: 8:22:05, time: 0.595, data_time: 0.005, memory: 60248, decode.loss_ce: 0.2020, decode.acc_seg: 74.6960, aux.loss_ce: 0.1298, aux.acc_seg: 72.3123, loss: 0.3318 +2022-05-05 14:51:49,544 - mmseg - INFO - Iter [32150/80000] lr: 8.588e-07, eta: 8:21:31, time: 0.587, data_time: 0.004, memory: 60248, decode.loss_ce: 0.1937, decode.acc_seg: 75.8003, aux.loss_ce: 0.1261, aux.acc_seg: 73.2727, loss: 0.3198 +2022-05-05 14:52:19,121 - mmseg - INFO - Iter [32200/80000] lr: 8.579e-07, eta: 8:20:57, time: 0.592, data_time: 0.004, memory: 60248, decode.loss_ce: 0.1879, decode.acc_seg: 75.9780, aux.loss_ce: 0.1262, aux.acc_seg: 73.2657, loss: 0.3141 +2022-05-05 14:52:48,623 - mmseg - INFO - Iter [32250/80000] lr: 8.570e-07, eta: 8:20:22, time: 0.590, data_time: 0.005, memory: 60248, decode.loss_ce: 0.1903, decode.acc_seg: 73.9404, aux.loss_ce: 0.1268, aux.acc_seg: 71.2282, loss: 0.3172 +2022-05-05 14:53:18,548 - mmseg - INFO - Iter [32300/80000] lr: 8.561e-07, eta: 8:19:49, time: 0.599, data_time: 0.006, memory: 60248, decode.loss_ce: 0.1900, decode.acc_seg: 74.0017, aux.loss_ce: 0.1230, aux.acc_seg: 71.5073, loss: 0.3130 +2022-05-05 14:53:48,714 - mmseg - INFO - Iter [32350/80000] lr: 8.552e-07, eta: 8:19:15, time: 0.601, data_time: 0.004, memory: 60248, decode.loss_ce: 0.2003, decode.acc_seg: 73.5485, aux.loss_ce: 0.1316, aux.acc_seg: 70.6434, loss: 0.3319 +2022-05-05 14:54:18,039 - mmseg - INFO - Iter [32400/80000] lr: 8.543e-07, eta: 8:18:41, time: 0.588, data_time: 0.006, memory: 60248, decode.loss_ce: 0.1769, decode.acc_seg: 74.3222, aux.loss_ce: 0.1152, aux.acc_seg: 71.8558, loss: 0.2921 +2022-05-05 14:54:47,576 - mmseg - INFO - Iter [32450/80000] lr: 8.534e-07, eta: 8:18:07, time: 0.591, data_time: 0.005, memory: 60248, decode.loss_ce: 0.1905, decode.acc_seg: 74.4142, aux.loss_ce: 0.1258, aux.acc_seg: 71.5646, loss: 0.3164 +2022-05-05 14:55:17,241 - mmseg - INFO - Iter [32500/80000] lr: 8.525e-07, eta: 8:17:33, time: 0.593, data_time: 0.004, memory: 60248, decode.loss_ce: 0.1995, decode.acc_seg: 75.6802, aux.loss_ce: 0.1282, aux.acc_seg: 73.0538, loss: 0.3278 +2022-05-05 14:55:46,675 - mmseg - INFO - Iter [32550/80000] lr: 8.516e-07, eta: 8:16:58, time: 0.589, data_time: 0.004, memory: 60248, decode.loss_ce: 0.1845, decode.acc_seg: 73.8650, aux.loss_ce: 0.1216, aux.acc_seg: 71.2303, loss: 0.3062 +2022-05-05 14:56:18,483 - mmseg - INFO - Iter [32600/80000] lr: 8.507e-07, eta: 8:16:27, time: 0.636, data_time: 0.056, memory: 60248, decode.loss_ce: 0.1895, decode.acc_seg: 73.9798, aux.loss_ce: 0.1207, aux.acc_seg: 71.4642, loss: 0.3102 +2022-05-05 14:56:47,987 - mmseg - INFO - Iter [32650/80000] lr: 8.498e-07, eta: 8:15:53, time: 0.590, data_time: 0.004, memory: 60248, decode.loss_ce: 0.1888, decode.acc_seg: 75.5524, aux.loss_ce: 0.1240, aux.acc_seg: 72.8544, loss: 0.3128 +2022-05-05 14:57:17,643 - mmseg - INFO - Iter [32700/80000] lr: 8.489e-07, eta: 8:15:19, time: 0.593, data_time: 0.005, memory: 60248, decode.loss_ce: 0.1946, decode.acc_seg: 74.4017, aux.loss_ce: 0.1255, aux.acc_seg: 71.9581, loss: 0.3201 +2022-05-05 14:57:47,146 - mmseg - INFO - Iter [32750/80000] lr: 8.480e-07, eta: 8:14:45, time: 0.590, data_time: 0.004, memory: 60248, decode.loss_ce: 0.1842, decode.acc_seg: 75.4398, aux.loss_ce: 0.1217, aux.acc_seg: 72.8688, loss: 0.3059 +2022-05-05 14:58:16,506 - mmseg - INFO - Iter [32800/80000] lr: 8.471e-07, eta: 8:14:11, time: 0.587, data_time: 0.004, memory: 60248, decode.loss_ce: 0.1936, decode.acc_seg: 73.8388, aux.loss_ce: 0.1232, aux.acc_seg: 71.5333, loss: 0.3168 +2022-05-05 14:58:46,049 - mmseg - INFO - Iter [32850/80000] lr: 8.462e-07, eta: 8:13:37, time: 0.591, data_time: 0.004, memory: 60248, decode.loss_ce: 0.1961, decode.acc_seg: 75.6890, aux.loss_ce: 0.1266, aux.acc_seg: 73.1788, loss: 0.3228 +2022-05-05 14:59:15,362 - mmseg - INFO - Iter [32900/80000] lr: 8.453e-07, eta: 8:13:02, time: 0.587, data_time: 0.004, memory: 60248, decode.loss_ce: 0.1899, decode.acc_seg: 74.7888, aux.loss_ce: 0.1249, aux.acc_seg: 72.1332, loss: 0.3148 +2022-05-05 14:59:45,053 - mmseg - INFO - Iter [32950/80000] lr: 8.444e-07, eta: 8:12:28, time: 0.594, data_time: 0.004, memory: 60248, decode.loss_ce: 0.2000, decode.acc_seg: 74.8435, aux.loss_ce: 0.1306, aux.acc_seg: 72.2140, loss: 0.3306 +2022-05-05 15:00:14,438 - mmseg - INFO - Saving checkpoint at 33000 iterations +2022-05-05 15:00:34,254 - mmseg - INFO - Exp name: upernet_beit_adapter_large_512_80k_cocostuff10k_ss.py +2022-05-05 15:00:34,257 - mmseg - INFO - Iter [33000/80000] lr: 8.435e-07, eta: 8:12:22, time: 0.983, data_time: 0.004, memory: 60248, decode.loss_ce: 0.1832, decode.acc_seg: 73.7095, aux.loss_ce: 0.1194, aux.acc_seg: 71.1817, loss: 0.3026 +2022-05-05 15:01:04,136 - mmseg - INFO - Iter [33050/80000] lr: 8.427e-07, eta: 8:11:49, time: 0.599, data_time: 0.006, memory: 60248, decode.loss_ce: 0.1949, decode.acc_seg: 75.7295, aux.loss_ce: 0.1288, aux.acc_seg: 73.1056, loss: 0.3237 +2022-05-05 15:01:33,693 - mmseg - INFO - Iter [33100/80000] lr: 8.418e-07, eta: 8:11:15, time: 0.592, data_time: 0.005, memory: 60248, decode.loss_ce: 0.1990, decode.acc_seg: 74.8603, aux.loss_ce: 0.1303, aux.acc_seg: 72.0698, loss: 0.3293 +2022-05-05 15:02:03,059 - mmseg - INFO - Iter [33150/80000] lr: 8.409e-07, eta: 8:10:40, time: 0.587, data_time: 0.004, memory: 60248, decode.loss_ce: 0.1895, decode.acc_seg: 75.1175, aux.loss_ce: 0.1224, aux.acc_seg: 72.6601, loss: 0.3119 +2022-05-05 15:02:35,127 - mmseg - INFO - Iter [33200/80000] lr: 8.400e-07, eta: 8:10:10, time: 0.641, data_time: 0.051, memory: 60248, decode.loss_ce: 0.1922, decode.acc_seg: 74.5507, aux.loss_ce: 0.1248, aux.acc_seg: 72.0138, loss: 0.3170 +2022-05-05 15:03:04,582 - mmseg - INFO - Iter [33250/80000] lr: 8.391e-07, eta: 8:09:36, time: 0.589, data_time: 0.005, memory: 60248, decode.loss_ce: 0.1812, decode.acc_seg: 74.5728, aux.loss_ce: 0.1227, aux.acc_seg: 71.9411, loss: 0.3038 +2022-05-05 15:03:34,244 - mmseg - INFO - Iter [33300/80000] lr: 8.382e-07, eta: 8:09:02, time: 0.593, data_time: 0.004, memory: 60248, decode.loss_ce: 0.1795, decode.acc_seg: 74.9559, aux.loss_ce: 0.1201, aux.acc_seg: 72.2992, loss: 0.2996 +2022-05-05 15:04:03,613 - mmseg - INFO - Iter [33350/80000] lr: 8.373e-07, eta: 8:08:27, time: 0.587, data_time: 0.006, memory: 60248, decode.loss_ce: 0.1913, decode.acc_seg: 75.1193, aux.loss_ce: 0.1202, aux.acc_seg: 72.8739, loss: 0.3115 +2022-05-05 15:04:33,023 - mmseg - INFO - Iter [33400/80000] lr: 8.364e-07, eta: 8:07:53, time: 0.588, data_time: 0.005, memory: 60248, decode.loss_ce: 0.2028, decode.acc_seg: 73.5059, aux.loss_ce: 0.1311, aux.acc_seg: 70.8220, loss: 0.3339 +2022-05-05 15:05:02,444 - mmseg - INFO - Iter [33450/80000] lr: 8.355e-07, eta: 8:07:19, time: 0.588, data_time: 0.005, memory: 60248, decode.loss_ce: 0.1976, decode.acc_seg: 74.9059, aux.loss_ce: 0.1261, aux.acc_seg: 72.5512, loss: 0.3237 +2022-05-05 15:05:31,996 - mmseg - INFO - Iter [33500/80000] lr: 8.346e-07, eta: 8:06:45, time: 0.591, data_time: 0.004, memory: 60248, decode.loss_ce: 0.1939, decode.acc_seg: 74.3845, aux.loss_ce: 0.1225, aux.acc_seg: 72.0807, loss: 0.3164 +2022-05-05 15:06:01,508 - mmseg - INFO - Iter [33550/80000] lr: 8.337e-07, eta: 8:06:11, time: 0.590, data_time: 0.004, memory: 60248, decode.loss_ce: 0.1849, decode.acc_seg: 75.0795, aux.loss_ce: 0.1212, aux.acc_seg: 72.3495, loss: 0.3061 +2022-05-05 15:06:30,952 - mmseg - INFO - Iter [33600/80000] lr: 8.328e-07, eta: 8:05:37, time: 0.589, data_time: 0.005, memory: 60248, decode.loss_ce: 0.1823, decode.acc_seg: 75.5170, aux.loss_ce: 0.1189, aux.acc_seg: 73.1342, loss: 0.3011 +2022-05-05 15:07:01,053 - mmseg - INFO - Iter [33650/80000] lr: 8.319e-07, eta: 8:05:04, time: 0.600, data_time: 0.004, memory: 60248, decode.loss_ce: 0.1980, decode.acc_seg: 74.3483, aux.loss_ce: 0.1255, aux.acc_seg: 71.8214, loss: 0.3235 +2022-05-05 15:07:30,891 - mmseg - INFO - Iter [33700/80000] lr: 8.310e-07, eta: 8:04:30, time: 0.599, data_time: 0.006, memory: 60248, decode.loss_ce: 0.1874, decode.acc_seg: 75.4420, aux.loss_ce: 0.1204, aux.acc_seg: 73.0991, loss: 0.3079 +2022-05-05 15:08:02,859 - mmseg - INFO - Iter [33750/80000] lr: 8.301e-07, eta: 8:04:00, time: 0.640, data_time: 0.054, memory: 60248, decode.loss_ce: 0.1857, decode.acc_seg: 74.5577, aux.loss_ce: 0.1225, aux.acc_seg: 71.9790, loss: 0.3082 +2022-05-05 15:08:32,363 - mmseg - INFO - Iter [33800/80000] lr: 8.292e-07, eta: 8:03:26, time: 0.590, data_time: 0.004, memory: 60248, decode.loss_ce: 0.1781, decode.acc_seg: 75.3336, aux.loss_ce: 0.1141, aux.acc_seg: 72.9387, loss: 0.2922 +2022-05-05 15:09:01,697 - mmseg - INFO - Iter [33850/80000] lr: 8.283e-07, eta: 8:02:51, time: 0.587, data_time: 0.004, memory: 60248, decode.loss_ce: 0.1892, decode.acc_seg: 74.6537, aux.loss_ce: 0.1210, aux.acc_seg: 72.3782, loss: 0.3103 +2022-05-05 15:09:34,400 - mmseg - INFO - Iter [33900/80000] lr: 8.274e-07, eta: 8:02:22, time: 0.654, data_time: 0.006, memory: 60248, decode.loss_ce: 0.1821, decode.acc_seg: 74.6905, aux.loss_ce: 0.1194, aux.acc_seg: 72.2339, loss: 0.3015 +2022-05-05 15:10:03,712 - mmseg - INFO - Iter [33950/80000] lr: 8.265e-07, eta: 8:01:48, time: 0.586, data_time: 0.004, memory: 60248, decode.loss_ce: 0.1910, decode.acc_seg: 76.4187, aux.loss_ce: 0.1235, aux.acc_seg: 74.0748, loss: 0.3145 +2022-05-05 15:10:33,734 - mmseg - INFO - Saving checkpoint at 34000 iterations +2022-05-05 15:10:55,176 - mmseg - INFO - Exp name: upernet_beit_adapter_large_512_80k_cocostuff10k_ss.py +2022-05-05 15:10:55,178 - mmseg - INFO - Iter [34000/80000] lr: 8.256e-07, eta: 8:01:43, time: 1.027, data_time: 0.006, memory: 60248, decode.loss_ce: 0.1884, decode.acc_seg: 75.8324, aux.loss_ce: 0.1237, aux.acc_seg: 73.2204, loss: 0.3121 +2022-05-05 15:11:24,890 - mmseg - INFO - Iter [34050/80000] lr: 8.247e-07, eta: 8:01:10, time: 0.596, data_time: 0.007, memory: 60248, decode.loss_ce: 0.1812, decode.acc_seg: 75.8610, aux.loss_ce: 0.1172, aux.acc_seg: 73.6946, loss: 0.2984 +2022-05-05 15:11:54,658 - mmseg - INFO - Iter [34100/80000] lr: 8.238e-07, eta: 8:00:36, time: 0.595, data_time: 0.005, memory: 60248, decode.loss_ce: 0.1779, decode.acc_seg: 72.9926, aux.loss_ce: 0.1184, aux.acc_seg: 70.4373, loss: 0.2964 +2022-05-05 15:12:24,292 - mmseg - INFO - Iter [34150/80000] lr: 8.229e-07, eta: 8:00:02, time: 0.592, data_time: 0.004, memory: 60248, decode.loss_ce: 0.1869, decode.acc_seg: 73.3193, aux.loss_ce: 0.1189, aux.acc_seg: 71.0770, loss: 0.3058 +2022-05-05 15:12:53,802 - mmseg - INFO - Iter [34200/80000] lr: 8.220e-07, eta: 7:59:28, time: 0.591, data_time: 0.005, memory: 60248, decode.loss_ce: 0.1791, decode.acc_seg: 74.3733, aux.loss_ce: 0.1163, aux.acc_seg: 72.1166, loss: 0.2954 +2022-05-05 15:13:23,237 - mmseg - INFO - Iter [34250/80000] lr: 8.211e-07, eta: 7:58:54, time: 0.589, data_time: 0.004, memory: 60248, decode.loss_ce: 0.1817, decode.acc_seg: 74.7883, aux.loss_ce: 0.1210, aux.acc_seg: 72.3692, loss: 0.3027 +2022-05-05 15:13:55,521 - mmseg - INFO - Iter [34300/80000] lr: 8.202e-07, eta: 7:58:24, time: 0.645, data_time: 0.054, memory: 60248, decode.loss_ce: 0.1860, decode.acc_seg: 74.3457, aux.loss_ce: 0.1190, aux.acc_seg: 71.9631, loss: 0.3050 +2022-05-05 15:14:25,225 - mmseg - INFO - Iter [34350/80000] lr: 8.193e-07, eta: 7:57:50, time: 0.594, data_time: 0.005, memory: 60248, decode.loss_ce: 0.1779, decode.acc_seg: 74.4930, aux.loss_ce: 0.1184, aux.acc_seg: 72.0180, loss: 0.2963 +2022-05-05 15:14:54,592 - mmseg - INFO - Iter [34400/80000] lr: 8.184e-07, eta: 7:57:16, time: 0.588, data_time: 0.005, memory: 60248, decode.loss_ce: 0.1972, decode.acc_seg: 74.7139, aux.loss_ce: 0.1284, aux.acc_seg: 72.0645, loss: 0.3256 +2022-05-05 15:15:24,098 - mmseg - INFO - Iter [34450/80000] lr: 8.175e-07, eta: 7:56:42, time: 0.590, data_time: 0.004, memory: 60248, decode.loss_ce: 0.1839, decode.acc_seg: 74.9092, aux.loss_ce: 0.1189, aux.acc_seg: 72.5180, loss: 0.3027 +2022-05-05 15:15:53,704 - mmseg - INFO - Iter [34500/80000] lr: 8.166e-07, eta: 7:56:09, time: 0.592, data_time: 0.004, memory: 60248, decode.loss_ce: 0.1855, decode.acc_seg: 74.4927, aux.loss_ce: 0.1206, aux.acc_seg: 71.9182, loss: 0.3061 +2022-05-05 15:16:23,704 - mmseg - INFO - Iter [34550/80000] lr: 8.157e-07, eta: 7:55:35, time: 0.598, data_time: 0.004, memory: 60248, decode.loss_ce: 0.1974, decode.acc_seg: 75.1803, aux.loss_ce: 0.1277, aux.acc_seg: 72.5208, loss: 0.3251 +2022-05-05 15:16:53,229 - mmseg - INFO - Iter [34600/80000] lr: 8.148e-07, eta: 7:55:02, time: 0.592, data_time: 0.006, memory: 60248, decode.loss_ce: 0.1786, decode.acc_seg: 75.2003, aux.loss_ce: 0.1182, aux.acc_seg: 72.6952, loss: 0.2968 +2022-05-05 15:17:22,658 - mmseg - INFO - Iter [34650/80000] lr: 8.139e-07, eta: 7:54:28, time: 0.588, data_time: 0.004, memory: 60248, decode.loss_ce: 0.1839, decode.acc_seg: 74.7721, aux.loss_ce: 0.1150, aux.acc_seg: 72.5632, loss: 0.2989 +2022-05-05 15:17:52,011 - mmseg - INFO - Iter [34700/80000] lr: 8.130e-07, eta: 7:53:54, time: 0.587, data_time: 0.005, memory: 60248, decode.loss_ce: 0.1861, decode.acc_seg: 75.2067, aux.loss_ce: 0.1206, aux.acc_seg: 72.6686, loss: 0.3066 +2022-05-05 15:18:21,435 - mmseg - INFO - Iter [34750/80000] lr: 8.121e-07, eta: 7:53:20, time: 0.588, data_time: 0.005, memory: 60248, decode.loss_ce: 0.1817, decode.acc_seg: 76.3347, aux.loss_ce: 0.1210, aux.acc_seg: 73.7759, loss: 0.3028 +2022-05-05 15:18:50,998 - mmseg - INFO - Iter [34800/80000] lr: 8.112e-07, eta: 7:52:46, time: 0.591, data_time: 0.005, memory: 60248, decode.loss_ce: 0.1899, decode.acc_seg: 75.1345, aux.loss_ce: 0.1263, aux.acc_seg: 72.3962, loss: 0.3162 +2022-05-05 15:19:23,186 - mmseg - INFO - Iter [34850/80000] lr: 8.103e-07, eta: 7:52:16, time: 0.644, data_time: 0.051, memory: 60248, decode.loss_ce: 0.1847, decode.acc_seg: 75.2925, aux.loss_ce: 0.1199, aux.acc_seg: 72.7787, loss: 0.3046 +2022-05-05 15:19:53,229 - mmseg - INFO - Iter [34900/80000] lr: 8.094e-07, eta: 7:51:42, time: 0.601, data_time: 0.005, memory: 60248, decode.loss_ce: 0.1809, decode.acc_seg: 74.9601, aux.loss_ce: 0.1167, aux.acc_seg: 72.7049, loss: 0.2976 +2022-05-05 15:20:22,974 - mmseg - INFO - Iter [34950/80000] lr: 8.086e-07, eta: 7:51:09, time: 0.595, data_time: 0.005, memory: 60248, decode.loss_ce: 0.1862, decode.acc_seg: 73.8386, aux.loss_ce: 0.1196, aux.acc_seg: 71.5601, loss: 0.3058 +2022-05-05 15:20:53,034 - mmseg - INFO - Saving checkpoint at 35000 iterations +2022-05-05 15:21:13,086 - mmseg - INFO - Exp name: upernet_beit_adapter_large_512_80k_cocostuff10k_ss.py +2022-05-05 15:21:13,089 - mmseg - INFO - Iter [35000/80000] lr: 8.077e-07, eta: 7:51:01, time: 1.000, data_time: 0.006, memory: 60248, decode.loss_ce: 0.1743, decode.acc_seg: 75.6441, aux.loss_ce: 0.1163, aux.acc_seg: 73.1920, loss: 0.2905 +2022-05-05 15:21:42,914 - mmseg - INFO - Iter [35050/80000] lr: 8.068e-07, eta: 7:50:28, time: 0.599, data_time: 0.007, memory: 60248, decode.loss_ce: 0.1759, decode.acc_seg: 74.7298, aux.loss_ce: 0.1145, aux.acc_seg: 72.4850, loss: 0.2904 +2022-05-05 15:22:12,562 - mmseg - INFO - Iter [35100/80000] lr: 8.059e-07, eta: 7:49:55, time: 0.593, data_time: 0.005, memory: 60248, decode.loss_ce: 0.1779, decode.acc_seg: 75.2904, aux.loss_ce: 0.1173, aux.acc_seg: 72.7709, loss: 0.2951 +2022-05-05 15:22:42,139 - mmseg - INFO - Iter [35150/80000] lr: 8.050e-07, eta: 7:49:21, time: 0.592, data_time: 0.004, memory: 60248, decode.loss_ce: 0.1707, decode.acc_seg: 75.3142, aux.loss_ce: 0.1149, aux.acc_seg: 73.0073, loss: 0.2856 +2022-05-05 15:23:11,582 - mmseg - INFO - Iter [35200/80000] lr: 8.041e-07, eta: 7:48:47, time: 0.589, data_time: 0.004, memory: 60248, decode.loss_ce: 0.1902, decode.acc_seg: 74.3604, aux.loss_ce: 0.1238, aux.acc_seg: 71.7699, loss: 0.3140 +2022-05-05 15:23:41,429 - mmseg - INFO - Iter [35250/80000] lr: 8.032e-07, eta: 7:48:14, time: 0.597, data_time: 0.004, memory: 60248, decode.loss_ce: 0.1717, decode.acc_seg: 73.8129, aux.loss_ce: 0.1100, aux.acc_seg: 71.6924, loss: 0.2817 +2022-05-05 15:24:10,985 - mmseg - INFO - Iter [35300/80000] lr: 8.023e-07, eta: 7:47:40, time: 0.591, data_time: 0.004, memory: 60248, decode.loss_ce: 0.1687, decode.acc_seg: 74.7906, aux.loss_ce: 0.1154, aux.acc_seg: 72.1389, loss: 0.2841 +2022-05-05 15:24:40,441 - mmseg - INFO - Iter [35350/80000] lr: 8.014e-07, eta: 7:47:06, time: 0.589, data_time: 0.005, memory: 60248, decode.loss_ce: 0.1798, decode.acc_seg: 74.7416, aux.loss_ce: 0.1169, aux.acc_seg: 72.4241, loss: 0.2967 +2022-05-05 15:25:10,306 - mmseg - INFO - Iter [35400/80000] lr: 8.005e-07, eta: 7:46:33, time: 0.597, data_time: 0.005, memory: 60248, decode.loss_ce: 0.1715, decode.acc_seg: 74.5263, aux.loss_ce: 0.1137, aux.acc_seg: 72.0662, loss: 0.2852 +2022-05-05 15:25:42,222 - mmseg - INFO - Iter [35450/80000] lr: 7.996e-07, eta: 7:46:02, time: 0.638, data_time: 0.052, memory: 60248, decode.loss_ce: 0.1777, decode.acc_seg: 75.7011, aux.loss_ce: 0.1182, aux.acc_seg: 73.0824, loss: 0.2959 +2022-05-05 15:26:11,638 - mmseg - INFO - Iter [35500/80000] lr: 7.987e-07, eta: 7:45:28, time: 0.588, data_time: 0.005, memory: 60248, decode.loss_ce: 0.1859, decode.acc_seg: 73.6718, aux.loss_ce: 0.1177, aux.acc_seg: 71.2629, loss: 0.3036 +2022-05-05 15:26:40,948 - mmseg - INFO - Iter [35550/80000] lr: 7.978e-07, eta: 7:44:54, time: 0.586, data_time: 0.004, memory: 60248, decode.loss_ce: 0.1768, decode.acc_seg: 76.1170, aux.loss_ce: 0.1146, aux.acc_seg: 73.8980, loss: 0.2914 +2022-05-05 15:27:10,680 - mmseg - INFO - Iter [35600/80000] lr: 7.969e-07, eta: 7:44:21, time: 0.595, data_time: 0.005, memory: 60248, decode.loss_ce: 0.1786, decode.acc_seg: 74.4560, aux.loss_ce: 0.1171, aux.acc_seg: 72.1655, loss: 0.2957 +2022-05-05 15:27:40,060 - mmseg - INFO - Iter [35650/80000] lr: 7.960e-07, eta: 7:43:47, time: 0.588, data_time: 0.004, memory: 60248, decode.loss_ce: 0.1628, decode.acc_seg: 75.5855, aux.loss_ce: 0.1070, aux.acc_seg: 73.3643, loss: 0.2699 +2022-05-05 15:28:09,534 - mmseg - INFO - Iter [35700/80000] lr: 7.951e-07, eta: 7:43:13, time: 0.589, data_time: 0.004, memory: 60248, decode.loss_ce: 0.1714, decode.acc_seg: 75.8048, aux.loss_ce: 0.1120, aux.acc_seg: 73.4579, loss: 0.2834 +2022-05-05 15:28:38,896 - mmseg - INFO - Iter [35750/80000] lr: 7.942e-07, eta: 7:42:39, time: 0.587, data_time: 0.004, memory: 60248, decode.loss_ce: 0.1926, decode.acc_seg: 73.8504, aux.loss_ce: 0.1225, aux.acc_seg: 71.4308, loss: 0.3152 +2022-05-05 15:29:08,387 - mmseg - INFO - Iter [35800/80000] lr: 7.933e-07, eta: 7:42:06, time: 0.590, data_time: 0.005, memory: 60248, decode.loss_ce: 0.1855, decode.acc_seg: 75.2944, aux.loss_ce: 0.1172, aux.acc_seg: 72.9468, loss: 0.3026 +2022-05-05 15:29:37,781 - mmseg - INFO - Iter [35850/80000] lr: 7.924e-07, eta: 7:41:32, time: 0.588, data_time: 0.004, memory: 60248, decode.loss_ce: 0.1831, decode.acc_seg: 74.9772, aux.loss_ce: 0.1171, aux.acc_seg: 72.6365, loss: 0.3002 +2022-05-05 15:30:07,288 - mmseg - INFO - Iter [35900/80000] lr: 7.915e-07, eta: 7:40:58, time: 0.590, data_time: 0.005, memory: 60248, decode.loss_ce: 0.1698, decode.acc_seg: 73.3945, aux.loss_ce: 0.1113, aux.acc_seg: 71.1163, loss: 0.2812 +2022-05-05 15:30:36,748 - mmseg - INFO - Iter [35950/80000] lr: 7.906e-07, eta: 7:40:25, time: 0.589, data_time: 0.005, memory: 60248, decode.loss_ce: 0.1853, decode.acc_seg: 75.0908, aux.loss_ce: 0.1190, aux.acc_seg: 72.7762, loss: 0.3044 +2022-05-05 15:31:08,809 - mmseg - INFO - Saving checkpoint at 36000 iterations +2022-05-05 15:31:28,463 - mmseg - INFO - Exp name: upernet_beit_adapter_large_512_80k_cocostuff10k_ss.py +2022-05-05 15:31:28,465 - mmseg - INFO - Iter [36000/80000] lr: 7.897e-07, eta: 7:40:18, time: 1.033, data_time: 0.056, memory: 60248, decode.loss_ce: 0.1889, decode.acc_seg: 75.0044, aux.loss_ce: 0.1220, aux.acc_seg: 72.6412, loss: 0.3109 +2022-05-05 15:31:58,114 - mmseg - INFO - Iter [36050/80000] lr: 7.888e-07, eta: 7:39:45, time: 0.594, data_time: 0.005, memory: 60248, decode.loss_ce: 0.1623, decode.acc_seg: 74.9234, aux.loss_ce: 0.1065, aux.acc_seg: 72.8070, loss: 0.2688 +2022-05-05 15:32:27,658 - mmseg - INFO - Iter [36100/80000] lr: 7.879e-07, eta: 7:39:11, time: 0.591, data_time: 0.005, memory: 60248, decode.loss_ce: 0.1774, decode.acc_seg: 74.5198, aux.loss_ce: 0.1149, aux.acc_seg: 72.2990, loss: 0.2923 +2022-05-05 15:32:56,994 - mmseg - INFO - Iter [36150/80000] lr: 7.870e-07, eta: 7:38:37, time: 0.587, data_time: 0.004, memory: 60248, decode.loss_ce: 0.1855, decode.acc_seg: 74.4392, aux.loss_ce: 0.1164, aux.acc_seg: 72.1540, loss: 0.3019 +2022-05-05 15:33:26,599 - mmseg - INFO - Iter [36200/80000] lr: 7.861e-07, eta: 7:38:04, time: 0.592, data_time: 0.005, memory: 60248, decode.loss_ce: 0.1727, decode.acc_seg: 73.7468, aux.loss_ce: 0.1077, aux.acc_seg: 71.6680, loss: 0.2804 +2022-05-05 15:33:55,995 - mmseg - INFO - Iter [36250/80000] lr: 7.852e-07, eta: 7:37:30, time: 0.588, data_time: 0.005, memory: 60248, decode.loss_ce: 0.1609, decode.acc_seg: 75.6386, aux.loss_ce: 0.1096, aux.acc_seg: 73.0132, loss: 0.2705 +2022-05-05 15:34:25,404 - mmseg - INFO - Iter [36300/80000] lr: 7.843e-07, eta: 7:36:56, time: 0.588, data_time: 0.004, memory: 60248, decode.loss_ce: 0.1754, decode.acc_seg: 75.2644, aux.loss_ce: 0.1164, aux.acc_seg: 72.6955, loss: 0.2918 +2022-05-05 15:34:54,900 - mmseg - INFO - Iter [36350/80000] lr: 7.834e-07, eta: 7:36:22, time: 0.589, data_time: 0.004, memory: 60248, decode.loss_ce: 0.1902, decode.acc_seg: 74.1756, aux.loss_ce: 0.1231, aux.acc_seg: 71.6333, loss: 0.3134 +2022-05-05 15:35:24,583 - mmseg - INFO - Iter [36400/80000] lr: 7.825e-07, eta: 7:35:49, time: 0.594, data_time: 0.006, memory: 60248, decode.loss_ce: 0.1763, decode.acc_seg: 74.2518, aux.loss_ce: 0.1102, aux.acc_seg: 72.2259, loss: 0.2864 +2022-05-05 15:35:54,764 - mmseg - INFO - Iter [36450/80000] lr: 7.816e-07, eta: 7:35:16, time: 0.602, data_time: 0.004, memory: 60248, decode.loss_ce: 0.1823, decode.acc_seg: 74.6345, aux.loss_ce: 0.1160, aux.acc_seg: 72.3741, loss: 0.2983 +2022-05-05 15:36:24,432 - mmseg - INFO - Iter [36500/80000] lr: 7.807e-07, eta: 7:34:43, time: 0.595, data_time: 0.006, memory: 60248, decode.loss_ce: 0.1989, decode.acc_seg: 76.4663, aux.loss_ce: 0.1284, aux.acc_seg: 73.8586, loss: 0.3272 +2022-05-05 15:36:56,705 - mmseg - INFO - Iter [36550/80000] lr: 7.798e-07, eta: 7:34:13, time: 0.644, data_time: 0.057, memory: 60248, decode.loss_ce: 0.1759, decode.acc_seg: 73.8276, aux.loss_ce: 0.1151, aux.acc_seg: 71.1383, loss: 0.2911 +2022-05-05 15:37:26,246 - mmseg - INFO - Iter [36600/80000] lr: 7.789e-07, eta: 7:33:39, time: 0.592, data_time: 0.006, memory: 60248, decode.loss_ce: 0.1847, decode.acc_seg: 74.8409, aux.loss_ce: 0.1210, aux.acc_seg: 72.3911, loss: 0.3057 +2022-05-05 15:37:55,729 - mmseg - INFO - Iter [36650/80000] lr: 7.780e-07, eta: 7:33:06, time: 0.590, data_time: 0.005, memory: 60248, decode.loss_ce: 0.1868, decode.acc_seg: 74.8371, aux.loss_ce: 0.1237, aux.acc_seg: 72.2053, loss: 0.3105 +2022-05-05 15:38:25,584 - mmseg - INFO - Iter [36700/80000] lr: 7.771e-07, eta: 7:32:32, time: 0.597, data_time: 0.005, memory: 60248, decode.loss_ce: 0.1692, decode.acc_seg: 75.8591, aux.loss_ce: 0.1111, aux.acc_seg: 73.6615, loss: 0.2803 +2022-05-05 15:38:55,432 - mmseg - INFO - Iter [36750/80000] lr: 7.762e-07, eta: 7:31:59, time: 0.597, data_time: 0.005, memory: 60248, decode.loss_ce: 0.1739, decode.acc_seg: 74.5483, aux.loss_ce: 0.1130, aux.acc_seg: 72.3849, loss: 0.2869 +2022-05-05 15:39:25,106 - mmseg - INFO - Iter [36800/80000] lr: 7.753e-07, eta: 7:31:26, time: 0.593, data_time: 0.004, memory: 60248, decode.loss_ce: 0.1700, decode.acc_seg: 76.2944, aux.loss_ce: 0.1137, aux.acc_seg: 73.9542, loss: 0.2837 +2022-05-05 15:39:54,798 - mmseg - INFO - Iter [36850/80000] lr: 7.745e-07, eta: 7:30:53, time: 0.594, data_time: 0.005, memory: 60248, decode.loss_ce: 0.1721, decode.acc_seg: 74.6217, aux.loss_ce: 0.1098, aux.acc_seg: 72.2071, loss: 0.2819 +2022-05-05 15:40:24,317 - mmseg - INFO - Iter [36900/80000] lr: 7.736e-07, eta: 7:30:19, time: 0.591, data_time: 0.005, memory: 60248, decode.loss_ce: 0.1757, decode.acc_seg: 74.6548, aux.loss_ce: 0.1119, aux.acc_seg: 72.4025, loss: 0.2876 +2022-05-05 15:40:53,598 - mmseg - INFO - Iter [36950/80000] lr: 7.727e-07, eta: 7:29:45, time: 0.585, data_time: 0.004, memory: 60248, decode.loss_ce: 0.1759, decode.acc_seg: 76.4743, aux.loss_ce: 0.1126, aux.acc_seg: 74.2249, loss: 0.2885 +2022-05-05 15:41:23,044 - mmseg - INFO - Saving checkpoint at 37000 iterations +2022-05-05 15:41:43,038 - mmseg - INFO - Exp name: upernet_beit_adapter_large_512_80k_cocostuff10k_ss.py +2022-05-05 15:41:43,046 - mmseg - INFO - Iter [37000/80000] lr: 7.718e-07, eta: 7:29:35, time: 0.988, data_time: 0.004, memory: 60248, decode.loss_ce: 0.1692, decode.acc_seg: 75.2899, aux.loss_ce: 0.1115, aux.acc_seg: 73.0028, loss: 0.2806 +2022-05-05 15:42:12,750 - mmseg - INFO - Iter [37050/80000] lr: 7.709e-07, eta: 7:29:02, time: 0.596, data_time: 0.006, memory: 60248, decode.loss_ce: 0.1840, decode.acc_seg: 75.7400, aux.loss_ce: 0.1190, aux.acc_seg: 73.3088, loss: 0.3031 +2022-05-05 15:42:45,013 - mmseg - INFO - Iter [37100/80000] lr: 7.700e-07, eta: 7:28:32, time: 0.645, data_time: 0.057, memory: 60248, decode.loss_ce: 0.1736, decode.acc_seg: 74.7654, aux.loss_ce: 0.1144, aux.acc_seg: 72.4421, loss: 0.2880 +2022-05-05 15:43:15,023 - mmseg - INFO - Iter [37150/80000] lr: 7.691e-07, eta: 7:27:59, time: 0.600, data_time: 0.004, memory: 60248, decode.loss_ce: 0.1569, decode.acc_seg: 75.3052, aux.loss_ce: 0.1041, aux.acc_seg: 73.0051, loss: 0.2610 +2022-05-05 15:43:44,771 - mmseg - INFO - Iter [37200/80000] lr: 7.682e-07, eta: 7:27:25, time: 0.595, data_time: 0.004, memory: 60248, decode.loss_ce: 0.1771, decode.acc_seg: 75.5616, aux.loss_ce: 0.1154, aux.acc_seg: 73.2629, loss: 0.2925 +2022-05-05 15:44:14,271 - mmseg - INFO - Iter [37250/80000] lr: 7.673e-07, eta: 7:26:52, time: 0.590, data_time: 0.004, memory: 60248, decode.loss_ce: 0.1742, decode.acc_seg: 75.1491, aux.loss_ce: 0.1120, aux.acc_seg: 73.0276, loss: 0.2862 +2022-05-05 15:44:43,955 - mmseg - INFO - Iter [37300/80000] lr: 7.664e-07, eta: 7:26:19, time: 0.594, data_time: 0.004, memory: 60248, decode.loss_ce: 0.1760, decode.acc_seg: 75.8068, aux.loss_ce: 0.1132, aux.acc_seg: 73.5788, loss: 0.2892 +2022-05-05 15:45:13,432 - mmseg - INFO - Iter [37350/80000] lr: 7.655e-07, eta: 7:25:45, time: 0.590, data_time: 0.004, memory: 60248, decode.loss_ce: 0.1670, decode.acc_seg: 74.1612, aux.loss_ce: 0.1076, aux.acc_seg: 72.0721, loss: 0.2746 +2022-05-05 15:45:43,113 - mmseg - INFO - Iter [37400/80000] lr: 7.646e-07, eta: 7:25:12, time: 0.594, data_time: 0.004, memory: 60248, decode.loss_ce: 0.1685, decode.acc_seg: 75.4075, aux.loss_ce: 0.1094, aux.acc_seg: 73.1511, loss: 0.2779 +2022-05-05 15:46:12,646 - mmseg - INFO - Iter [37450/80000] lr: 7.637e-07, eta: 7:24:38, time: 0.590, data_time: 0.004, memory: 60248, decode.loss_ce: 0.1695, decode.acc_seg: 74.6573, aux.loss_ce: 0.1127, aux.acc_seg: 72.3115, loss: 0.2821 +2022-05-05 15:46:42,580 - mmseg - INFO - Iter [37500/80000] lr: 7.628e-07, eta: 7:24:05, time: 0.599, data_time: 0.005, memory: 60248, decode.loss_ce: 0.1815, decode.acc_seg: 75.0648, aux.loss_ce: 0.1152, aux.acc_seg: 72.8522, loss: 0.2967 +2022-05-05 15:47:12,352 - mmseg - INFO - Iter [37550/80000] lr: 7.619e-07, eta: 7:23:32, time: 0.596, data_time: 0.005, memory: 60248, decode.loss_ce: 0.1747, decode.acc_seg: 74.4814, aux.loss_ce: 0.1132, aux.acc_seg: 72.1816, loss: 0.2879 +2022-05-05 15:47:41,959 - mmseg - INFO - Iter [37600/80000] lr: 7.610e-07, eta: 7:22:59, time: 0.592, data_time: 0.005, memory: 60248, decode.loss_ce: 0.1759, decode.acc_seg: 77.0357, aux.loss_ce: 0.1192, aux.acc_seg: 74.4564, loss: 0.2951 +2022-05-05 15:48:11,438 - mmseg - INFO - Iter [37650/80000] lr: 7.601e-07, eta: 7:22:26, time: 0.589, data_time: 0.004, memory: 60248, decode.loss_ce: 0.1624, decode.acc_seg: 75.0121, aux.loss_ce: 0.1049, aux.acc_seg: 72.8492, loss: 0.2673 +2022-05-05 15:48:43,576 - mmseg - INFO - Iter [37700/80000] lr: 7.592e-07, eta: 7:21:55, time: 0.643, data_time: 0.053, memory: 60248, decode.loss_ce: 0.1708, decode.acc_seg: 74.5847, aux.loss_ce: 0.1110, aux.acc_seg: 72.3624, loss: 0.2818 +2022-05-05 15:49:13,288 - mmseg - INFO - Iter [37750/80000] lr: 7.583e-07, eta: 7:21:22, time: 0.594, data_time: 0.004, memory: 60248, decode.loss_ce: 0.1632, decode.acc_seg: 75.2189, aux.loss_ce: 0.1061, aux.acc_seg: 73.0522, loss: 0.2693 +2022-05-05 15:49:42,913 - mmseg - INFO - Iter [37800/80000] lr: 7.574e-07, eta: 7:20:49, time: 0.592, data_time: 0.004, memory: 60248, decode.loss_ce: 0.1858, decode.acc_seg: 74.0294, aux.loss_ce: 0.1188, aux.acc_seg: 71.6436, loss: 0.3047 +2022-05-05 15:50:12,673 - mmseg - INFO - Iter [37850/80000] lr: 7.565e-07, eta: 7:20:16, time: 0.595, data_time: 0.005, memory: 60248, decode.loss_ce: 0.1838, decode.acc_seg: 75.6229, aux.loss_ce: 0.1183, aux.acc_seg: 73.2015, loss: 0.3021 +2022-05-05 15:50:42,136 - mmseg - INFO - Iter [37900/80000] lr: 7.556e-07, eta: 7:19:42, time: 0.589, data_time: 0.005, memory: 60248, decode.loss_ce: 0.1781, decode.acc_seg: 73.9517, aux.loss_ce: 0.1127, aux.acc_seg: 71.6948, loss: 0.2908 +2022-05-05 15:51:11,571 - mmseg - INFO - Iter [37950/80000] lr: 7.547e-07, eta: 7:19:09, time: 0.589, data_time: 0.004, memory: 60248, decode.loss_ce: 0.1749, decode.acc_seg: 75.2786, aux.loss_ce: 0.1133, aux.acc_seg: 72.9795, loss: 0.2882 +2022-05-05 15:51:41,093 - mmseg - INFO - Saving checkpoint at 38000 iterations +2022-05-05 15:52:02,431 - mmseg - INFO - Exp name: upernet_beit_adapter_large_512_80k_cocostuff10k_ss.py +2022-05-05 15:52:02,434 - mmseg - INFO - Iter [38000/80000] lr: 7.538e-07, eta: 7:18:59, time: 1.016, data_time: 0.004, memory: 60248, decode.loss_ce: 0.1760, decode.acc_seg: 76.4660, aux.loss_ce: 0.1176, aux.acc_seg: 73.9530, loss: 0.2936 +2022-05-05 15:52:32,388 - mmseg - INFO - Iter [38050/80000] lr: 7.529e-07, eta: 7:18:26, time: 0.599, data_time: 0.006, memory: 60248, decode.loss_ce: 0.1762, decode.acc_seg: 74.4083, aux.loss_ce: 0.1167, aux.acc_seg: 71.8485, loss: 0.2930 +2022-05-05 15:53:01,801 - mmseg - INFO - Iter [38100/80000] lr: 7.520e-07, eta: 7:17:53, time: 0.590, data_time: 0.006, memory: 60248, decode.loss_ce: 0.1616, decode.acc_seg: 75.4226, aux.loss_ce: 0.1033, aux.acc_seg: 73.4029, loss: 0.2650 +2022-05-05 15:53:31,331 - mmseg - INFO - Iter [38150/80000] lr: 7.511e-07, eta: 7:17:19, time: 0.590, data_time: 0.004, memory: 60248, decode.loss_ce: 0.1658, decode.acc_seg: 75.2566, aux.loss_ce: 0.1089, aux.acc_seg: 73.0327, loss: 0.2747 +2022-05-05 15:54:00,750 - mmseg - INFO - Iter [38200/80000] lr: 7.502e-07, eta: 7:16:46, time: 0.588, data_time: 0.005, memory: 60248, decode.loss_ce: 0.1719, decode.acc_seg: 76.2728, aux.loss_ce: 0.1096, aux.acc_seg: 74.3210, loss: 0.2815 +2022-05-05 15:54:32,503 - mmseg - INFO - Iter [38250/80000] lr: 7.493e-07, eta: 7:16:15, time: 0.635, data_time: 0.053, memory: 60248, decode.loss_ce: 0.1700, decode.acc_seg: 75.7024, aux.loss_ce: 0.1100, aux.acc_seg: 73.5608, loss: 0.2800 +2022-05-05 15:55:02,097 - mmseg - INFO - Iter [38300/80000] lr: 7.484e-07, eta: 7:15:42, time: 0.592, data_time: 0.005, memory: 60248, decode.loss_ce: 0.1576, decode.acc_seg: 75.1895, aux.loss_ce: 0.1013, aux.acc_seg: 73.1181, loss: 0.2589 +2022-05-05 15:55:31,649 - mmseg - INFO - Iter [38350/80000] lr: 7.475e-07, eta: 7:15:08, time: 0.591, data_time: 0.005, memory: 60248, decode.loss_ce: 0.1837, decode.acc_seg: 75.7179, aux.loss_ce: 0.1205, aux.acc_seg: 73.2023, loss: 0.3042 +2022-05-05 15:56:01,311 - mmseg - INFO - Iter [38400/80000] lr: 7.466e-07, eta: 7:14:35, time: 0.593, data_time: 0.004, memory: 60248, decode.loss_ce: 0.1828, decode.acc_seg: 73.7667, aux.loss_ce: 0.1169, aux.acc_seg: 71.4462, loss: 0.2997 +2022-05-05 15:56:30,879 - mmseg - INFO - Iter [38450/80000] lr: 7.457e-07, eta: 7:14:02, time: 0.591, data_time: 0.005, memory: 60248, decode.loss_ce: 0.1656, decode.acc_seg: 74.0711, aux.loss_ce: 0.1042, aux.acc_seg: 72.0511, loss: 0.2698 +2022-05-05 15:57:00,580 - mmseg - INFO - Iter [38500/80000] lr: 7.448e-07, eta: 7:13:29, time: 0.594, data_time: 0.005, memory: 60248, decode.loss_ce: 0.1706, decode.acc_seg: 75.4981, aux.loss_ce: 0.1122, aux.acc_seg: 73.1372, loss: 0.2828 +2022-05-05 15:57:30,001 - mmseg - INFO - Iter [38550/80000] lr: 7.439e-07, eta: 7:12:55, time: 0.588, data_time: 0.004, memory: 60248, decode.loss_ce: 0.1693, decode.acc_seg: 74.3100, aux.loss_ce: 0.1118, aux.acc_seg: 71.9405, loss: 0.2810 +2022-05-05 15:57:59,329 - mmseg - INFO - Iter [38600/80000] lr: 7.430e-07, eta: 7:12:22, time: 0.587, data_time: 0.004, memory: 60248, decode.loss_ce: 0.1731, decode.acc_seg: 75.8647, aux.loss_ce: 0.1125, aux.acc_seg: 73.7267, loss: 0.2857 +2022-05-05 15:58:29,034 - mmseg - INFO - Iter [38650/80000] lr: 7.421e-07, eta: 7:11:49, time: 0.594, data_time: 0.005, memory: 60248, decode.loss_ce: 0.1794, decode.acc_seg: 75.8017, aux.loss_ce: 0.1138, aux.acc_seg: 73.6116, loss: 0.2932 +2022-05-05 15:58:58,682 - mmseg - INFO - Iter [38700/80000] lr: 7.412e-07, eta: 7:11:16, time: 0.593, data_time: 0.004, memory: 60248, decode.loss_ce: 0.1617, decode.acc_seg: 74.8488, aux.loss_ce: 0.1041, aux.acc_seg: 72.7061, loss: 0.2658 +2022-05-05 15:59:28,281 - mmseg - INFO - Iter [38750/80000] lr: 7.404e-07, eta: 7:10:43, time: 0.592, data_time: 0.006, memory: 60248, decode.loss_ce: 0.1610, decode.acc_seg: 75.0461, aux.loss_ce: 0.1053, aux.acc_seg: 72.7807, loss: 0.2664 +2022-05-05 16:00:00,369 - mmseg - INFO - Iter [38800/80000] lr: 7.395e-07, eta: 7:10:12, time: 0.642, data_time: 0.053, memory: 60248, decode.loss_ce: 0.1792, decode.acc_seg: 74.9164, aux.loss_ce: 0.1177, aux.acc_seg: 72.3760, loss: 0.2969 +2022-05-05 16:00:29,878 - mmseg - INFO - Iter [38850/80000] lr: 7.386e-07, eta: 7:09:39, time: 0.590, data_time: 0.005, memory: 60248, decode.loss_ce: 0.1790, decode.acc_seg: 75.7167, aux.loss_ce: 0.1143, aux.acc_seg: 73.3781, loss: 0.2932 +2022-05-05 16:00:59,349 - mmseg - INFO - Iter [38900/80000] lr: 7.377e-07, eta: 7:09:05, time: 0.589, data_time: 0.004, memory: 60248, decode.loss_ce: 0.1662, decode.acc_seg: 75.6544, aux.loss_ce: 0.1065, aux.acc_seg: 73.6012, loss: 0.2727 +2022-05-05 16:01:28,928 - mmseg - INFO - Iter [38950/80000] lr: 7.368e-07, eta: 7:08:32, time: 0.592, data_time: 0.005, memory: 60248, decode.loss_ce: 0.1695, decode.acc_seg: 75.0810, aux.loss_ce: 0.1110, aux.acc_seg: 72.7551, loss: 0.2806 +2022-05-05 16:01:58,499 - mmseg - INFO - Saving checkpoint at 39000 iterations +2022-05-05 16:02:18,803 - mmseg - INFO - Exp name: upernet_beit_adapter_large_512_80k_cocostuff10k_ss.py +2022-05-05 16:02:18,806 - mmseg - INFO - Iter [39000/80000] lr: 7.359e-07, eta: 7:08:20, time: 0.995, data_time: 0.004, memory: 60248, decode.loss_ce: 0.1809, decode.acc_seg: 73.7339, aux.loss_ce: 0.1154, aux.acc_seg: 71.4191, loss: 0.2963 +2022-05-05 16:02:48,936 - mmseg - INFO - Iter [39050/80000] lr: 7.350e-07, eta: 7:07:48, time: 0.602, data_time: 0.006, memory: 60248, decode.loss_ce: 0.1678, decode.acc_seg: 75.4218, aux.loss_ce: 0.1073, aux.acc_seg: 73.2490, loss: 0.2751 +2022-05-05 16:03:18,634 - mmseg - INFO - Iter [39100/80000] lr: 7.341e-07, eta: 7:07:15, time: 0.597, data_time: 0.008, memory: 60248, decode.loss_ce: 0.1744, decode.acc_seg: 75.0558, aux.loss_ce: 0.1110, aux.acc_seg: 72.9337, loss: 0.2855 +2022-05-05 16:03:48,206 - mmseg - INFO - Iter [39150/80000] lr: 7.332e-07, eta: 7:06:42, time: 0.591, data_time: 0.004, memory: 60248, decode.loss_ce: 0.1725, decode.acc_seg: 74.3235, aux.loss_ce: 0.1112, aux.acc_seg: 71.9575, loss: 0.2838 +2022-05-05 16:04:17,623 - mmseg - INFO - Iter [39200/80000] lr: 7.323e-07, eta: 7:06:08, time: 0.588, data_time: 0.004, memory: 60248, decode.loss_ce: 0.1700, decode.acc_seg: 74.2664, aux.loss_ce: 0.1097, aux.acc_seg: 72.0088, loss: 0.2797 +2022-05-05 16:04:47,126 - mmseg - INFO - Iter [39250/80000] lr: 7.314e-07, eta: 7:05:35, time: 0.590, data_time: 0.005, memory: 60248, decode.loss_ce: 0.1695, decode.acc_seg: 74.2007, aux.loss_ce: 0.1071, aux.acc_seg: 72.0943, loss: 0.2767 +2022-05-05 16:05:16,626 - mmseg - INFO - Iter [39300/80000] lr: 7.305e-07, eta: 7:05:02, time: 0.590, data_time: 0.005, memory: 60248, decode.loss_ce: 0.1692, decode.acc_seg: 75.1563, aux.loss_ce: 0.1064, aux.acc_seg: 73.0963, loss: 0.2756 +2022-05-05 16:05:48,731 - mmseg - INFO - Iter [39350/80000] lr: 7.296e-07, eta: 7:04:31, time: 0.642, data_time: 0.053, memory: 60248, decode.loss_ce: 0.1725, decode.acc_seg: 74.5395, aux.loss_ce: 0.1130, aux.acc_seg: 72.0076, loss: 0.2855 +2022-05-05 16:06:18,211 - mmseg - INFO - Iter [39400/80000] lr: 7.287e-07, eta: 7:03:58, time: 0.590, data_time: 0.004, memory: 60248, decode.loss_ce: 0.1682, decode.acc_seg: 75.4425, aux.loss_ce: 0.1097, aux.acc_seg: 73.2026, loss: 0.2778 +2022-05-05 16:06:47,983 - mmseg - INFO - Iter [39450/80000] lr: 7.278e-07, eta: 7:03:25, time: 0.595, data_time: 0.004, memory: 60248, decode.loss_ce: 0.1628, decode.acc_seg: 74.7737, aux.loss_ce: 0.1059, aux.acc_seg: 72.6141, loss: 0.2687 +2022-05-05 16:07:17,396 - mmseg - INFO - Iter [39500/80000] lr: 7.269e-07, eta: 7:02:52, time: 0.589, data_time: 0.005, memory: 60248, decode.loss_ce: 0.1706, decode.acc_seg: 76.3178, aux.loss_ce: 0.1106, aux.acc_seg: 74.0114, loss: 0.2812 +2022-05-05 16:07:46,857 - mmseg - INFO - Iter [39550/80000] lr: 7.260e-07, eta: 7:02:19, time: 0.589, data_time: 0.004, memory: 60248, decode.loss_ce: 0.1683, decode.acc_seg: 74.2053, aux.loss_ce: 0.1076, aux.acc_seg: 72.0503, loss: 0.2759 +2022-05-05 16:08:16,324 - mmseg - INFO - Iter [39600/80000] lr: 7.251e-07, eta: 7:01:45, time: 0.589, data_time: 0.005, memory: 60248, decode.loss_ce: 0.1716, decode.acc_seg: 76.0662, aux.loss_ce: 0.1106, aux.acc_seg: 73.9161, loss: 0.2822 +2022-05-05 16:08:45,908 - mmseg - INFO - Iter [39650/80000] lr: 7.242e-07, eta: 7:01:12, time: 0.592, data_time: 0.005, memory: 60248, decode.loss_ce: 0.1643, decode.acc_seg: 75.6638, aux.loss_ce: 0.1013, aux.acc_seg: 73.6933, loss: 0.2655 +2022-05-05 16:09:15,537 - mmseg - INFO - Iter [39700/80000] lr: 7.233e-07, eta: 7:00:39, time: 0.593, data_time: 0.005, memory: 60248, decode.loss_ce: 0.1565, decode.acc_seg: 75.4558, aux.loss_ce: 0.1039, aux.acc_seg: 73.2297, loss: 0.2604 +2022-05-05 16:09:45,629 - mmseg - INFO - Iter [39750/80000] lr: 7.224e-07, eta: 7:00:07, time: 0.601, data_time: 0.005, memory: 60248, decode.loss_ce: 0.1676, decode.acc_seg: 75.7081, aux.loss_ce: 0.1123, aux.acc_seg: 73.1161, loss: 0.2799 +2022-05-05 16:10:15,408 - mmseg - INFO - Iter [39800/80000] lr: 7.215e-07, eta: 6:59:34, time: 0.596, data_time: 0.005, memory: 60248, decode.loss_ce: 0.1733, decode.acc_seg: 75.1963, aux.loss_ce: 0.1117, aux.acc_seg: 72.9205, loss: 0.2851 +2022-05-05 16:10:45,296 - mmseg - INFO - Iter [39850/80000] lr: 7.206e-07, eta: 6:59:01, time: 0.598, data_time: 0.005, memory: 60248, decode.loss_ce: 0.1740, decode.acc_seg: 74.9047, aux.loss_ce: 0.1129, aux.acc_seg: 72.6033, loss: 0.2869 +2022-05-05 16:11:14,665 - mmseg - INFO - Iter [39900/80000] lr: 7.197e-07, eta: 6:58:28, time: 0.587, data_time: 0.005, memory: 60248, decode.loss_ce: 0.1624, decode.acc_seg: 73.9091, aux.loss_ce: 0.1058, aux.acc_seg: 71.7027, loss: 0.2682 +2022-05-05 16:11:46,831 - mmseg - INFO - Iter [39950/80000] lr: 7.188e-07, eta: 6:57:57, time: 0.643, data_time: 0.053, memory: 60248, decode.loss_ce: 0.1735, decode.acc_seg: 75.0789, aux.loss_ce: 0.1104, aux.acc_seg: 72.9368, loss: 0.2839 +2022-05-05 16:12:16,156 - mmseg - INFO - Saving checkpoint at 40000 iterations +2022-05-05 16:12:36,928 - mmseg - INFO - Exp name: upernet_beit_adapter_large_512_80k_cocostuff10k_ss.py +2022-05-05 16:12:36,931 - mmseg - INFO - Iter [40000/80000] lr: 7.179e-07, eta: 6:57:45, time: 0.999, data_time: 0.004, memory: 60248, decode.loss_ce: 0.1649, decode.acc_seg: 75.9514, aux.loss_ce: 0.1068, aux.acc_seg: 73.7667, loss: 0.2717 +2022-05-05 16:13:06,811 - mmseg - INFO - per class results: +2022-05-05 16:13:06,821 - mmseg - INFO - ++------------------+-------+-------+ +| Class | IoU | Acc | ++------------------+-------+-------+ +| person | 87.7 | 94.96 | +| bicycle | 73.37 | 91.99 | +| car | 63.25 | 71.84 | +| motorcycle | 87.4 | 95.75 | +| airplane | 87.53 | 96.16 | +| bus | 75.53 | 85.0 | +| train | 68.31 | 97.88 | +| truck | 80.19 | 87.33 | +| boat | 71.78 | 90.28 | +| traffic light | 70.81 | 92.67 | +| fire hydrant | 83.83 | 98.43 | +| stop sign | 90.14 | 98.46 | +| parking meter | 75.46 | 79.54 | +| bench | 55.25 | 69.35 | +| bird | 75.59 | 83.29 | +| cat | 92.41 | 97.21 | +| dog | 91.21 | 96.78 | +| horse | 89.41 | 96.2 | +| sheep | 87.51 | 91.2 | +| cow | 94.25 | 98.82 | +| elephant | 91.88 | 97.43 | +| bear | 89.66 | 96.01 | +| zebra | 90.28 | 97.13 | +| giraffe | 85.84 | 95.76 | +| backpack | 23.38 | 51.23 | +| umbrella | 72.31 | 81.89 | +| handbag | 17.14 | 25.95 | +| tie | 55.41 | 55.41 | +| suitcase | 77.87 | 96.32 | +| frisbee | 93.83 | 96.98 | +| skis | 37.42 | 51.9 | +| snowboard | 66.41 | 77.68 | +| sports ball | 84.28 | 87.28 | +| kite | 69.07 | 90.89 | +| baseball bat | 48.97 | 62.18 | +| baseball glove | 1.11 | 1.12 | +| skateboard | 65.89 | 87.44 | +| surfboard | 89.61 | 95.07 | +| tennis racket | 59.48 | 63.17 | +| bottle | 73.45 | 85.85 | +| wine glass | 82.19 | 90.6 | +| cup | 64.2 | 89.27 | +| fork | 51.08 | 62.65 | +| knife | 76.67 | 86.8 | +| spoon | 47.36 | 60.05 | +| bowl | 54.97 | 67.55 | +| banana | 78.12 | 87.22 | +| apple | 76.65 | 90.83 | +| sandwich | 86.52 | 95.2 | +| orange | 68.65 | 92.25 | +| broccoli | 94.28 | 96.78 | +| carrot | 41.31 | 74.71 | +| hot dog | 51.24 | 96.85 | +| pizza | 93.98 | 95.54 | +| donut | 68.88 | 89.08 | +| cake | 61.85 | 71.54 | +| chair | 59.98 | 78.22 | +| couch | 76.03 | 94.16 | +| potted plant | 34.3 | 43.31 | +| bed | 73.32 | 83.91 | +| dining table | 62.6 | 79.38 | +| toilet | 88.81 | 96.54 | +| tv | 68.75 | 90.89 | +| laptop | 86.28 | 97.02 | +| mouse | 71.25 | 76.83 | +| remote | 68.65 | 92.91 | +| keyboard | 83.07 | 98.31 | +| cell phone | 72.48 | 96.94 | +| microwave | 51.08 | 73.96 | +| oven | 62.97 | 84.38 | +| toaster | 17.13 | 28.14 | +| sink | 70.64 | 77.63 | +| refrigerator | 79.24 | 91.24 | +| book | 79.22 | 88.81 | +| clock | 77.4 | 86.62 | +| vase | 63.82 | 92.42 | +| scissors | 76.1 | 95.73 | +| teddy bear | 85.78 | 95.66 | +| hair drier | 0.0 | 0.0 | +| toothbrush | 13.84 | 25.75 | +| banner | 23.59 | 39.34 | +| blanket | 7.63 | 7.77 | +| branch | 5.14 | 5.22 | +| bridge | 2.92 | 4.02 | +| building-other | 53.52 | 71.11 | +| bush | 29.0 | 37.31 | +| cabinet | 16.46 | 32.69 | +| cage | 0.0 | 0.0 | +| cardboard | 21.65 | 29.33 | +| carpet | 57.95 | 78.89 | +| ceiling-other | 69.07 | 85.13 | +| ceiling-tile | 11.78 | 14.26 | +| cloth | 4.28 | 6.34 | +| clothes | 20.3 | 30.0 | +| clouds | 53.49 | 69.78 | +| counter | 38.04 | 47.19 | +| cupboard | 49.02 | 63.86 | +| curtain | 66.29 | 83.1 | +| desk-stuff | 35.17 | 41.05 | +| dirt | 34.02 | 56.25 | +| door-stuff | 50.34 | 64.5 | +| fence | 44.08 | 73.33 | +| floor-marble | 0.01 | 0.03 | +| floor-other | 41.11 | 56.91 | +| floor-stone | 25.47 | 39.23 | +| floor-tile | 57.92 | 73.81 | +| floor-wood | 70.59 | 85.59 | +| flower | 18.57 | 43.76 | +| fog | 0.0 | 0.0 | +| food-other | 35.53 | 49.24 | +| fruit | 56.22 | 62.9 | +| furniture-other | 14.35 | 19.84 | +| grass | 72.65 | 82.26 | +| gravel | 27.54 | 32.49 | +| ground-other | 8.24 | 15.49 | +| hill | 28.13 | 38.37 | +| house | 26.98 | 44.98 | +| leaves | 14.95 | 18.73 | +| light | 38.15 | 52.26 | +| mat | 12.64 | 17.4 | +| metal | 15.72 | 18.54 | +| mirror-stuff | 46.55 | 65.11 | +| moss | 0.0 | 0.0 | +| mountain | 37.69 | 57.05 | +| mud | 6.13 | 13.16 | +| napkin | 22.11 | 32.18 | +| net | 27.21 | 31.57 | +| paper | 50.79 | 70.91 | +| pavement | 53.14 | 69.14 | +| pillow | 0.0 | 0.0 | +| plant-other | 26.92 | 41.68 | +| plastic | 17.61 | 22.82 | +| platform | 40.42 | 59.18 | +| playingfield | 68.33 | 81.8 | +| railing | 19.53 | 34.57 | +| railroad | 61.91 | 89.8 | +| river | 12.57 | 16.77 | +| road | 69.8 | 80.48 | +| rock | 47.3 | 67.77 | +| roof | 7.03 | 14.02 | +| rug | 48.95 | 70.85 | +| salad | 24.04 | 24.84 | +| sand | 73.39 | 87.83 | +| sea | 76.37 | 90.44 | +| shelf | 24.4 | 43.69 | +| sky-other | 61.35 | 75.41 | +| skyscraper | 6.86 | 9.72 | +| snow | 91.8 | 95.28 | +| solid-other | nan | nan | +| stairs | 34.42 | 53.23 | +| stone | 8.15 | 12.88 | +| straw | 13.73 | 33.08 | +| structural-other | 16.93 | 23.16 | +| table | 18.34 | 26.33 | +| tent | 70.98 | 84.85 | +| textile-other | 15.82 | 19.56 | +| towel | 40.59 | 48.6 | +| tree | 77.54 | 89.15 | +| vegetable | 40.29 | 60.85 | +| wall-brick | 37.28 | 50.44 | +| wall-concrete | 18.61 | 24.87 | +| wall-other | 60.65 | 80.32 | +| wall-panel | 6.24 | 6.62 | +| wall-stone | 27.48 | 33.32 | +| wall-tile | 56.11 | 83.95 | +| wall-wood | 39.97 | 61.94 | +| water-other | 29.88 | 42.83 | +| waterdrops | 0.0 | nan | +| window-blind | 25.88 | 52.07 | +| window-other | 45.23 | 59.67 | +| wood | 15.09 | 31.97 | ++------------------+-------+-------+ +2022-05-05 16:13:06,821 - mmseg - INFO - Summary: +2022-05-05 16:13:06,822 - mmseg - INFO - ++------+-------+-------+ +| aAcc | mIoU | mAcc | ++------+-------+-------+ +| 75.2 | 49.97 | 62.39 | ++------+-------+-------+ +2022-05-05 16:13:06,826 - mmseg - INFO - Exp name: upernet_beit_adapter_large_512_80k_cocostuff10k_ss.py +2022-05-05 16:13:06,826 - mmseg - INFO - Iter(val) [125] aAcc: 0.7520, mIoU: 0.4997, mAcc: 0.6239, IoU.person: 0.8770, IoU.bicycle: 0.7337, IoU.car: 0.6325, IoU.motorcycle: 0.8740, IoU.airplane: 0.8753, IoU.bus: 0.7553, IoU.train: 0.6831, IoU.truck: 0.8019, IoU.boat: 0.7178, IoU.traffic light: 0.7081, IoU.fire hydrant: 0.8383, IoU.stop sign: 0.9014, IoU.parking meter: 0.7546, IoU.bench: 0.5525, IoU.bird: 0.7559, IoU.cat: 0.9241, IoU.dog: 0.9121, IoU.horse: 0.8941, IoU.sheep: 0.8751, IoU.cow: 0.9425, IoU.elephant: 0.9188, IoU.bear: 0.8966, IoU.zebra: 0.9028, IoU.giraffe: 0.8584, IoU.backpack: 0.2338, IoU.umbrella: 0.7231, IoU.handbag: 0.1714, IoU.tie: 0.5541, IoU.suitcase: 0.7787, IoU.frisbee: 0.9383, IoU.skis: 0.3742, IoU.snowboard: 0.6641, IoU.sports ball: 0.8428, IoU.kite: 0.6907, IoU.baseball bat: 0.4897, IoU.baseball glove: 0.0111, IoU.skateboard: 0.6589, IoU.surfboard: 0.8961, IoU.tennis racket: 0.5948, IoU.bottle: 0.7345, IoU.wine glass: 0.8219, IoU.cup: 0.6420, IoU.fork: 0.5108, IoU.knife: 0.7667, IoU.spoon: 0.4736, IoU.bowl: 0.5497, IoU.banana: 0.7812, IoU.apple: 0.7665, IoU.sandwich: 0.8652, IoU.orange: 0.6865, IoU.broccoli: 0.9428, IoU.carrot: 0.4131, IoU.hot dog: 0.5124, IoU.pizza: 0.9398, IoU.donut: 0.6888, IoU.cake: 0.6185, IoU.chair: 0.5998, IoU.couch: 0.7603, IoU.potted plant: 0.3430, IoU.bed: 0.7332, IoU.dining table: 0.6260, IoU.toilet: 0.8881, IoU.tv: 0.6875, IoU.laptop: 0.8628, IoU.mouse: 0.7125, IoU.remote: 0.6865, IoU.keyboard: 0.8307, IoU.cell phone: 0.7248, IoU.microwave: 0.5108, IoU.oven: 0.6297, IoU.toaster: 0.1713, IoU.sink: 0.7064, IoU.refrigerator: 0.7924, IoU.book: 0.7922, IoU.clock: 0.7740, IoU.vase: 0.6382, IoU.scissors: 0.7610, IoU.teddy bear: 0.8578, IoU.hair drier: 0.0000, IoU.toothbrush: 0.1384, IoU.banner: 0.2359, IoU.blanket: 0.0763, IoU.branch: 0.0514, IoU.bridge: 0.0292, IoU.building-other: 0.5352, IoU.bush: 0.2900, IoU.cabinet: 0.1646, IoU.cage: 0.0000, IoU.cardboard: 0.2165, IoU.carpet: 0.5795, IoU.ceiling-other: 0.6907, IoU.ceiling-tile: 0.1178, IoU.cloth: 0.0428, IoU.clothes: 0.2030, IoU.clouds: 0.5349, IoU.counter: 0.3804, IoU.cupboard: 0.4902, IoU.curtain: 0.6629, IoU.desk-stuff: 0.3517, IoU.dirt: 0.3402, IoU.door-stuff: 0.5034, IoU.fence: 0.4408, IoU.floor-marble: 0.0001, IoU.floor-other: 0.4111, IoU.floor-stone: 0.2547, IoU.floor-tile: 0.5792, IoU.floor-wood: 0.7059, IoU.flower: 0.1857, IoU.fog: 0.0000, IoU.food-other: 0.3553, IoU.fruit: 0.5622, IoU.furniture-other: 0.1435, IoU.grass: 0.7265, IoU.gravel: 0.2754, IoU.ground-other: 0.0824, IoU.hill: 0.2813, IoU.house: 0.2698, IoU.leaves: 0.1495, IoU.light: 0.3815, IoU.mat: 0.1264, IoU.metal: 0.1572, IoU.mirror-stuff: 0.4655, IoU.moss: 0.0000, IoU.mountain: 0.3769, IoU.mud: 0.0613, IoU.napkin: 0.2211, IoU.net: 0.2721, IoU.paper: 0.5079, IoU.pavement: 0.5314, IoU.pillow: 0.0000, IoU.plant-other: 0.2692, IoU.plastic: 0.1761, IoU.platform: 0.4042, IoU.playingfield: 0.6833, IoU.railing: 0.1953, IoU.railroad: 0.6191, IoU.river: 0.1257, IoU.road: 0.6980, IoU.rock: 0.4730, IoU.roof: 0.0703, IoU.rug: 0.4895, IoU.salad: 0.2404, IoU.sand: 0.7339, IoU.sea: 0.7637, IoU.shelf: 0.2440, IoU.sky-other: 0.6135, IoU.skyscraper: 0.0686, IoU.snow: 0.9180, IoU.solid-other: nan, IoU.stairs: 0.3442, IoU.stone: 0.0815, IoU.straw: 0.1373, IoU.structural-other: 0.1693, IoU.table: 0.1834, IoU.tent: 0.7098, IoU.textile-other: 0.1582, IoU.towel: 0.4059, IoU.tree: 0.7754, IoU.vegetable: 0.4029, IoU.wall-brick: 0.3728, IoU.wall-concrete: 0.1861, IoU.wall-other: 0.6065, IoU.wall-panel: 0.0624, IoU.wall-stone: 0.2748, IoU.wall-tile: 0.5611, IoU.wall-wood: 0.3997, IoU.water-other: 0.2988, IoU.waterdrops: 0.0000, IoU.window-blind: 0.2588, IoU.window-other: 0.4523, IoU.wood: 0.1509, Acc.person: 0.9496, Acc.bicycle: 0.9199, Acc.car: 0.7184, Acc.motorcycle: 0.9575, Acc.airplane: 0.9616, Acc.bus: 0.8500, Acc.train: 0.9788, Acc.truck: 0.8733, Acc.boat: 0.9028, Acc.traffic light: 0.9267, Acc.fire hydrant: 0.9843, Acc.stop sign: 0.9846, Acc.parking meter: 0.7954, Acc.bench: 0.6935, Acc.bird: 0.8329, Acc.cat: 0.9721, Acc.dog: 0.9678, Acc.horse: 0.9620, Acc.sheep: 0.9120, Acc.cow: 0.9882, Acc.elephant: 0.9743, Acc.bear: 0.9601, Acc.zebra: 0.9713, Acc.giraffe: 0.9576, Acc.backpack: 0.5123, Acc.umbrella: 0.8189, Acc.handbag: 0.2595, Acc.tie: 0.5541, Acc.suitcase: 0.9632, Acc.frisbee: 0.9698, Acc.skis: 0.5190, Acc.snowboard: 0.7768, Acc.sports ball: 0.8728, Acc.kite: 0.9089, Acc.baseball bat: 0.6218, Acc.baseball glove: 0.0112, Acc.skateboard: 0.8744, Acc.surfboard: 0.9507, Acc.tennis racket: 0.6317, Acc.bottle: 0.8585, Acc.wine glass: 0.9060, Acc.cup: 0.8927, Acc.fork: 0.6265, Acc.knife: 0.8680, Acc.spoon: 0.6005, Acc.bowl: 0.6755, Acc.banana: 0.8722, Acc.apple: 0.9083, Acc.sandwich: 0.9520, Acc.orange: 0.9225, Acc.broccoli: 0.9678, Acc.carrot: 0.7471, Acc.hot dog: 0.9685, Acc.pizza: 0.9554, Acc.donut: 0.8908, Acc.cake: 0.7154, Acc.chair: 0.7822, Acc.couch: 0.9416, Acc.potted plant: 0.4331, Acc.bed: 0.8391, Acc.dining table: 0.7938, Acc.toilet: 0.9654, Acc.tv: 0.9089, Acc.laptop: 0.9702, Acc.mouse: 0.7683, Acc.remote: 0.9291, Acc.keyboard: 0.9831, Acc.cell phone: 0.9694, Acc.microwave: 0.7396, Acc.oven: 0.8438, Acc.toaster: 0.2814, Acc.sink: 0.7763, Acc.refrigerator: 0.9124, Acc.book: 0.8881, Acc.clock: 0.8662, Acc.vase: 0.9242, Acc.scissors: 0.9573, Acc.teddy bear: 0.9566, Acc.hair drier: 0.0000, Acc.toothbrush: 0.2575, Acc.banner: 0.3934, Acc.blanket: 0.0777, Acc.branch: 0.0522, Acc.bridge: 0.0402, Acc.building-other: 0.7111, Acc.bush: 0.3731, Acc.cabinet: 0.3269, Acc.cage: 0.0000, Acc.cardboard: 0.2933, Acc.carpet: 0.7889, Acc.ceiling-other: 0.8513, Acc.ceiling-tile: 0.1426, Acc.cloth: 0.0634, Acc.clothes: 0.3000, Acc.clouds: 0.6978, Acc.counter: 0.4719, Acc.cupboard: 0.6386, Acc.curtain: 0.8310, Acc.desk-stuff: 0.4105, Acc.dirt: 0.5625, Acc.door-stuff: 0.6450, Acc.fence: 0.7333, Acc.floor-marble: 0.0003, Acc.floor-other: 0.5691, Acc.floor-stone: 0.3923, Acc.floor-tile: 0.7381, Acc.floor-wood: 0.8559, Acc.flower: 0.4376, Acc.fog: 0.0000, Acc.food-other: 0.4924, Acc.fruit: 0.6290, Acc.furniture-other: 0.1984, Acc.grass: 0.8226, Acc.gravel: 0.3249, Acc.ground-other: 0.1549, Acc.hill: 0.3837, Acc.house: 0.4498, Acc.leaves: 0.1873, Acc.light: 0.5226, Acc.mat: 0.1740, Acc.metal: 0.1854, Acc.mirror-stuff: 0.6511, Acc.moss: 0.0000, Acc.mountain: 0.5705, Acc.mud: 0.1316, Acc.napkin: 0.3218, Acc.net: 0.3157, Acc.paper: 0.7091, Acc.pavement: 0.6914, Acc.pillow: 0.0000, Acc.plant-other: 0.4168, Acc.plastic: 0.2282, Acc.platform: 0.5918, Acc.playingfield: 0.8180, Acc.railing: 0.3457, Acc.railroad: 0.8980, Acc.river: 0.1677, Acc.road: 0.8048, Acc.rock: 0.6777, Acc.roof: 0.1402, Acc.rug: 0.7085, Acc.salad: 0.2484, Acc.sand: 0.8783, Acc.sea: 0.9044, Acc.shelf: 0.4369, Acc.sky-other: 0.7541, Acc.skyscraper: 0.0972, Acc.snow: 0.9528, Acc.solid-other: nan, Acc.stairs: 0.5323, Acc.stone: 0.1288, Acc.straw: 0.3308, Acc.structural-other: 0.2316, Acc.table: 0.2633, Acc.tent: 0.8485, Acc.textile-other: 0.1956, Acc.towel: 0.4860, Acc.tree: 0.8915, Acc.vegetable: 0.6085, Acc.wall-brick: 0.5044, Acc.wall-concrete: 0.2487, Acc.wall-other: 0.8032, Acc.wall-panel: 0.0662, Acc.wall-stone: 0.3332, Acc.wall-tile: 0.8395, Acc.wall-wood: 0.6194, Acc.water-other: 0.4283, Acc.waterdrops: nan, Acc.window-blind: 0.5207, Acc.window-other: 0.5967, Acc.wood: 0.3197 +2022-05-05 16:13:36,615 - mmseg - INFO - Iter [40050/80000] lr: 7.170e-07, eta: 6:57:42, time: 1.194, data_time: 0.605, memory: 60248, decode.loss_ce: 0.1881, decode.acc_seg: 75.2330, aux.loss_ce: 0.1123, aux.acc_seg: 73.2971, loss: 0.3004 +2022-05-05 16:14:06,138 - mmseg - INFO - Iter [40100/80000] lr: 7.161e-07, eta: 6:57:09, time: 0.592, data_time: 0.007, memory: 60248, decode.loss_ce: 0.1669, decode.acc_seg: 74.9795, aux.loss_ce: 0.1062, aux.acc_seg: 73.0148, loss: 0.2730 +2022-05-05 16:14:35,679 - mmseg - INFO - Iter [40150/80000] lr: 7.152e-07, eta: 6:56:36, time: 0.591, data_time: 0.005, memory: 60248, decode.loss_ce: 0.1652, decode.acc_seg: 75.0709, aux.loss_ce: 0.1085, aux.acc_seg: 72.7132, loss: 0.2737 +2022-05-05 16:15:05,118 - mmseg - INFO - Iter [40200/80000] lr: 7.143e-07, eta: 6:56:02, time: 0.589, data_time: 0.005, memory: 60248, decode.loss_ce: 0.1656, decode.acc_seg: 74.5511, aux.loss_ce: 0.1083, aux.acc_seg: 72.3949, loss: 0.2739 +2022-05-05 16:15:34,509 - mmseg - INFO - Iter [40250/80000] lr: 7.134e-07, eta: 6:55:29, time: 0.588, data_time: 0.005, memory: 60248, decode.loss_ce: 0.1615, decode.acc_seg: 75.2165, aux.loss_ce: 0.1054, aux.acc_seg: 72.9280, loss: 0.2669 +2022-05-05 16:16:04,208 - mmseg - INFO - Iter [40300/80000] lr: 7.125e-07, eta: 6:54:56, time: 0.594, data_time: 0.005, memory: 60248, decode.loss_ce: 0.1623, decode.acc_seg: 74.5653, aux.loss_ce: 0.1059, aux.acc_seg: 72.4194, loss: 0.2682 +2022-05-05 16:16:33,608 - mmseg - INFO - Iter [40350/80000] lr: 7.116e-07, eta: 6:54:23, time: 0.588, data_time: 0.004, memory: 60248, decode.loss_ce: 0.1690, decode.acc_seg: 75.2231, aux.loss_ce: 0.1065, aux.acc_seg: 73.1339, loss: 0.2755 +2022-05-05 16:17:02,896 - mmseg - INFO - Iter [40400/80000] lr: 7.107e-07, eta: 6:53:49, time: 0.586, data_time: 0.005, memory: 60248, decode.loss_ce: 0.1599, decode.acc_seg: 75.5934, aux.loss_ce: 0.1018, aux.acc_seg: 73.5872, loss: 0.2617 +2022-05-05 16:17:32,271 - mmseg - INFO - Iter [40450/80000] lr: 7.098e-07, eta: 6:53:16, time: 0.588, data_time: 0.004, memory: 60248, decode.loss_ce: 0.1694, decode.acc_seg: 74.4480, aux.loss_ce: 0.1102, aux.acc_seg: 72.1358, loss: 0.2796 +2022-05-05 16:18:04,546 - mmseg - INFO - Iter [40500/80000] lr: 7.089e-07, eta: 6:52:46, time: 0.645, data_time: 0.053, memory: 60248, decode.loss_ce: 0.1617, decode.acc_seg: 76.2433, aux.loss_ce: 0.1056, aux.acc_seg: 74.1830, loss: 0.2672 +2022-05-05 16:18:33,985 - mmseg - INFO - Iter [40550/80000] lr: 7.080e-07, eta: 6:52:12, time: 0.589, data_time: 0.004, memory: 60248, decode.loss_ce: 0.1669, decode.acc_seg: 75.2366, aux.loss_ce: 0.1079, aux.acc_seg: 72.9276, loss: 0.2748 +2022-05-05 16:19:03,572 - mmseg - INFO - Iter [40600/80000] lr: 7.071e-07, eta: 6:51:39, time: 0.592, data_time: 0.004, memory: 60248, decode.loss_ce: 0.1590, decode.acc_seg: 74.6832, aux.loss_ce: 0.1015, aux.acc_seg: 72.6993, loss: 0.2605 +2022-05-05 16:19:33,133 - mmseg - INFO - Iter [40650/80000] lr: 7.063e-07, eta: 6:51:06, time: 0.591, data_time: 0.006, memory: 60248, decode.loss_ce: 0.1618, decode.acc_seg: 75.7689, aux.loss_ce: 0.1037, aux.acc_seg: 73.6344, loss: 0.2655 +2022-05-05 16:20:02,573 - mmseg - INFO - Iter [40700/80000] lr: 7.054e-07, eta: 6:50:33, time: 0.589, data_time: 0.005, memory: 60248, decode.loss_ce: 0.1706, decode.acc_seg: 74.2531, aux.loss_ce: 0.1099, aux.acc_seg: 71.9661, loss: 0.2806 +2022-05-05 16:20:32,591 - mmseg - INFO - Iter [40750/80000] lr: 7.045e-07, eta: 6:50:00, time: 0.599, data_time: 0.005, memory: 60248, decode.loss_ce: 0.1647, decode.acc_seg: 74.9069, aux.loss_ce: 0.1072, aux.acc_seg: 72.7045, loss: 0.2719 +2022-05-05 16:21:02,332 - mmseg - INFO - Iter [40800/80000] lr: 7.036e-07, eta: 6:49:28, time: 0.597, data_time: 0.006, memory: 60248, decode.loss_ce: 0.1700, decode.acc_seg: 75.2740, aux.loss_ce: 0.1095, aux.acc_seg: 73.0309, loss: 0.2795 +2022-05-05 16:21:31,861 - mmseg - INFO - Iter [40850/80000] lr: 7.027e-07, eta: 6:48:54, time: 0.590, data_time: 0.004, memory: 60248, decode.loss_ce: 0.1671, decode.acc_seg: 75.3783, aux.loss_ce: 0.1109, aux.acc_seg: 73.0432, loss: 0.2779 +2022-05-05 16:22:01,318 - mmseg - INFO - Iter [40900/80000] lr: 7.018e-07, eta: 6:48:21, time: 0.589, data_time: 0.005, memory: 60248, decode.loss_ce: 0.1662, decode.acc_seg: 75.8869, aux.loss_ce: 0.1070, aux.acc_seg: 73.6738, loss: 0.2732 +2022-05-05 16:22:30,714 - mmseg - INFO - Iter [40950/80000] lr: 7.009e-07, eta: 6:47:48, time: 0.588, data_time: 0.004, memory: 60248, decode.loss_ce: 0.1585, decode.acc_seg: 74.8091, aux.loss_ce: 0.1009, aux.acc_seg: 72.8717, loss: 0.2594 +2022-05-05 16:23:00,577 - mmseg - INFO - Saving checkpoint at 41000 iterations +2022-05-05 16:23:20,562 - mmseg - INFO - Exp name: upernet_beit_adapter_large_512_80k_cocostuff10k_ss.py +2022-05-05 16:23:20,570 - mmseg - INFO - Iter [41000/80000] lr: 7.000e-07, eta: 6:47:34, time: 0.994, data_time: 0.004, memory: 60248, decode.loss_ce: 0.1662, decode.acc_seg: 75.2894, aux.loss_ce: 0.1029, aux.acc_seg: 73.5103, loss: 0.2692 +2022-05-05 16:23:53,129 - mmseg - INFO - Iter [41050/80000] lr: 6.991e-07, eta: 6:47:04, time: 0.651, data_time: 0.057, memory: 60248, decode.loss_ce: 0.1593, decode.acc_seg: 74.7479, aux.loss_ce: 0.1022, aux.acc_seg: 72.8202, loss: 0.2615 +2022-05-05 16:24:22,769 - mmseg - INFO - Iter [41100/80000] lr: 6.982e-07, eta: 6:46:31, time: 0.595, data_time: 0.007, memory: 60248, decode.loss_ce: 0.1737, decode.acc_seg: 75.5715, aux.loss_ce: 0.1104, aux.acc_seg: 73.2867, loss: 0.2841 +2022-05-05 16:24:52,306 - mmseg - INFO - Iter [41150/80000] lr: 6.973e-07, eta: 6:45:58, time: 0.591, data_time: 0.005, memory: 60248, decode.loss_ce: 0.1570, decode.acc_seg: 76.0590, aux.loss_ce: 0.1029, aux.acc_seg: 73.8803, loss: 0.2600 +2022-05-05 16:25:22,044 - mmseg - INFO - Iter [41200/80000] lr: 6.964e-07, eta: 6:45:25, time: 0.595, data_time: 0.004, memory: 60248, decode.loss_ce: 0.1574, decode.acc_seg: 74.7771, aux.loss_ce: 0.1021, aux.acc_seg: 72.6548, loss: 0.2596 +2022-05-05 16:25:51,479 - mmseg - INFO - Iter [41250/80000] lr: 6.955e-07, eta: 6:44:52, time: 0.589, data_time: 0.004, memory: 60248, decode.loss_ce: 0.1586, decode.acc_seg: 75.3021, aux.loss_ce: 0.0996, aux.acc_seg: 73.2750, loss: 0.2582 +2022-05-05 16:26:20,828 - mmseg - INFO - Iter [41300/80000] lr: 6.946e-07, eta: 6:44:19, time: 0.587, data_time: 0.005, memory: 60248, decode.loss_ce: 0.1629, decode.acc_seg: 73.5731, aux.loss_ce: 0.1066, aux.acc_seg: 71.2584, loss: 0.2695 +2022-05-05 16:26:50,426 - mmseg - INFO - Iter [41350/80000] lr: 6.937e-07, eta: 6:43:46, time: 0.592, data_time: 0.005, memory: 60248, decode.loss_ce: 0.1602, decode.acc_seg: 75.9552, aux.loss_ce: 0.1034, aux.acc_seg: 73.9797, loss: 0.2636 +2022-05-05 16:27:19,921 - mmseg - INFO - Iter [41400/80000] lr: 6.928e-07, eta: 6:43:13, time: 0.589, data_time: 0.005, memory: 60248, decode.loss_ce: 0.1607, decode.acc_seg: 75.5284, aux.loss_ce: 0.1024, aux.acc_seg: 73.4981, loss: 0.2631 +2022-05-05 16:27:49,280 - mmseg - INFO - Iter [41450/80000] lr: 6.919e-07, eta: 6:42:40, time: 0.587, data_time: 0.005, memory: 60248, decode.loss_ce: 0.1665, decode.acc_seg: 76.3061, aux.loss_ce: 0.1080, aux.acc_seg: 74.0402, loss: 0.2745 +2022-05-05 16:28:18,733 - mmseg - INFO - Iter [41500/80000] lr: 6.910e-07, eta: 6:42:07, time: 0.589, data_time: 0.005, memory: 60248, decode.loss_ce: 0.1650, decode.acc_seg: 75.3719, aux.loss_ce: 0.1044, aux.acc_seg: 73.2716, loss: 0.2694 +2022-05-05 16:28:48,105 - mmseg - INFO - Iter [41550/80000] lr: 6.901e-07, eta: 6:41:34, time: 0.588, data_time: 0.005, memory: 60248, decode.loss_ce: 0.1667, decode.acc_seg: 76.0978, aux.loss_ce: 0.1054, aux.acc_seg: 73.9985, loss: 0.2722 +2022-05-05 16:29:20,065 - mmseg - INFO - Iter [41600/80000] lr: 6.892e-07, eta: 6:41:03, time: 0.639, data_time: 0.052, memory: 60248, decode.loss_ce: 0.1722, decode.acc_seg: 75.5092, aux.loss_ce: 0.1101, aux.acc_seg: 73.2755, loss: 0.2823 +2022-05-05 16:29:49,401 - mmseg - INFO - Iter [41650/80000] lr: 6.883e-07, eta: 6:40:30, time: 0.587, data_time: 0.005, memory: 60248, decode.loss_ce: 0.1727, decode.acc_seg: 75.2879, aux.loss_ce: 0.1096, aux.acc_seg: 73.1215, loss: 0.2823 +2022-05-05 16:30:18,982 - mmseg - INFO - Iter [41700/80000] lr: 6.874e-07, eta: 6:39:57, time: 0.591, data_time: 0.006, memory: 60248, decode.loss_ce: 0.1610, decode.acc_seg: 76.8362, aux.loss_ce: 0.1061, aux.acc_seg: 74.5611, loss: 0.2671 +2022-05-05 16:30:48,704 - mmseg - INFO - Iter [41750/80000] lr: 6.865e-07, eta: 6:39:24, time: 0.595, data_time: 0.005, memory: 60248, decode.loss_ce: 0.1590, decode.acc_seg: 74.4975, aux.loss_ce: 0.1052, aux.acc_seg: 72.3118, loss: 0.2642 +2022-05-05 16:31:18,558 - mmseg - INFO - Iter [41800/80000] lr: 6.856e-07, eta: 6:38:51, time: 0.597, data_time: 0.006, memory: 60248, decode.loss_ce: 0.1566, decode.acc_seg: 75.7715, aux.loss_ce: 0.1033, aux.acc_seg: 73.5279, loss: 0.2598 +2022-05-05 16:31:47,856 - mmseg - INFO - Iter [41850/80000] lr: 6.847e-07, eta: 6:38:18, time: 0.586, data_time: 0.005, memory: 60248, decode.loss_ce: 0.1636, decode.acc_seg: 76.3642, aux.loss_ce: 0.1052, aux.acc_seg: 74.2466, loss: 0.2688 +2022-05-05 16:32:17,248 - mmseg - INFO - Iter [41900/80000] lr: 6.838e-07, eta: 6:37:45, time: 0.588, data_time: 0.005, memory: 60248, decode.loss_ce: 0.1682, decode.acc_seg: 75.2677, aux.loss_ce: 0.1069, aux.acc_seg: 73.2050, loss: 0.2750 +2022-05-05 16:32:46,859 - mmseg - INFO - Iter [41950/80000] lr: 6.829e-07, eta: 6:37:12, time: 0.592, data_time: 0.005, memory: 60248, decode.loss_ce: 0.1688, decode.acc_seg: 75.0566, aux.loss_ce: 0.1067, aux.acc_seg: 72.9363, loss: 0.2754 +2022-05-05 16:33:16,278 - mmseg - INFO - Saving checkpoint at 42000 iterations +2022-05-05 16:33:36,243 - mmseg - INFO - Exp name: upernet_beit_adapter_large_512_80k_cocostuff10k_ss.py +2022-05-05 16:33:36,245 - mmseg - INFO - Iter [42000/80000] lr: 6.820e-07, eta: 6:36:57, time: 0.985, data_time: 0.004, memory: 60248, decode.loss_ce: 0.1678, decode.acc_seg: 76.4866, aux.loss_ce: 0.1085, aux.acc_seg: 74.2621, loss: 0.2763 +2022-05-05 16:34:05,958 - mmseg - INFO - Iter [42050/80000] lr: 6.811e-07, eta: 6:36:24, time: 0.596, data_time: 0.007, memory: 60248, decode.loss_ce: 0.1601, decode.acc_seg: 74.6936, aux.loss_ce: 0.1035, aux.acc_seg: 72.4227, loss: 0.2636 +2022-05-05 16:34:35,534 - mmseg - INFO - Iter [42100/80000] lr: 6.802e-07, eta: 6:35:51, time: 0.592, data_time: 0.005, memory: 60248, decode.loss_ce: 0.1634, decode.acc_seg: 74.7836, aux.loss_ce: 0.1066, aux.acc_seg: 72.5681, loss: 0.2700 +2022-05-05 16:35:05,254 - mmseg - INFO - Iter [42150/80000] lr: 6.793e-07, eta: 6:35:19, time: 0.594, data_time: 0.004, memory: 60248, decode.loss_ce: 0.1539, decode.acc_seg: 75.4300, aux.loss_ce: 0.0999, aux.acc_seg: 73.4822, loss: 0.2538 +2022-05-05 16:35:37,324 - mmseg - INFO - Iter [42200/80000] lr: 6.784e-07, eta: 6:34:48, time: 0.641, data_time: 0.056, memory: 60248, decode.loss_ce: 0.1679, decode.acc_seg: 75.5226, aux.loss_ce: 0.1056, aux.acc_seg: 73.5297, loss: 0.2735 +2022-05-05 16:36:06,925 - mmseg - INFO - Iter [42250/80000] lr: 6.775e-07, eta: 6:34:15, time: 0.592, data_time: 0.004, memory: 60248, decode.loss_ce: 0.1574, decode.acc_seg: 75.7883, aux.loss_ce: 0.1032, aux.acc_seg: 73.6135, loss: 0.2606 +2022-05-05 16:36:36,746 - mmseg - INFO - Iter [42300/80000] lr: 6.766e-07, eta: 6:33:42, time: 0.596, data_time: 0.006, memory: 60248, decode.loss_ce: 0.1581, decode.acc_seg: 75.7958, aux.loss_ce: 0.1013, aux.acc_seg: 73.7233, loss: 0.2594 +2022-05-05 16:37:06,342 - mmseg - INFO - Iter [42350/80000] lr: 6.757e-07, eta: 6:33:09, time: 0.592, data_time: 0.004, memory: 60248, decode.loss_ce: 0.1633, decode.acc_seg: 74.8482, aux.loss_ce: 0.1038, aux.acc_seg: 72.8303, loss: 0.2671 +2022-05-05 16:37:36,267 - mmseg - INFO - Iter [42400/80000] lr: 6.748e-07, eta: 6:32:37, time: 0.598, data_time: 0.004, memory: 60248, decode.loss_ce: 0.1608, decode.acc_seg: 74.8224, aux.loss_ce: 0.1034, aux.acc_seg: 72.7307, loss: 0.2642 +2022-05-05 16:38:05,630 - mmseg - INFO - Iter [42450/80000] lr: 6.739e-07, eta: 6:32:04, time: 0.587, data_time: 0.005, memory: 60248, decode.loss_ce: 0.1582, decode.acc_seg: 73.9568, aux.loss_ce: 0.1031, aux.acc_seg: 71.8985, loss: 0.2613 +2022-05-05 16:38:35,063 - mmseg - INFO - Iter [42500/80000] lr: 6.730e-07, eta: 6:31:31, time: 0.589, data_time: 0.004, memory: 60248, decode.loss_ce: 0.1714, decode.acc_seg: 75.4082, aux.loss_ce: 0.1108, aux.acc_seg: 73.1863, loss: 0.2822 +2022-05-05 16:39:04,514 - mmseg - INFO - Iter [42550/80000] lr: 6.721e-07, eta: 6:30:58, time: 0.589, data_time: 0.004, memory: 60248, decode.loss_ce: 0.1595, decode.acc_seg: 74.3934, aux.loss_ce: 0.1027, aux.acc_seg: 72.2811, loss: 0.2622 +2022-05-05 16:39:33,938 - mmseg - INFO - Iter [42600/80000] lr: 6.713e-07, eta: 6:30:25, time: 0.588, data_time: 0.005, memory: 60248, decode.loss_ce: 0.1638, decode.acc_seg: 73.9418, aux.loss_ce: 0.1002, aux.acc_seg: 72.0104, loss: 0.2640 +2022-05-05 16:40:03,672 - mmseg - INFO - Iter [42650/80000] lr: 6.704e-07, eta: 6:29:52, time: 0.595, data_time: 0.005, memory: 60248, decode.loss_ce: 0.1558, decode.acc_seg: 75.7341, aux.loss_ce: 0.1008, aux.acc_seg: 73.5522, loss: 0.2565 +2022-05-05 16:40:33,237 - mmseg - INFO - Iter [42700/80000] lr: 6.695e-07, eta: 6:29:19, time: 0.591, data_time: 0.004, memory: 60248, decode.loss_ce: 0.1623, decode.acc_seg: 75.7575, aux.loss_ce: 0.1059, aux.acc_seg: 73.5845, loss: 0.2682 +2022-05-05 16:41:05,180 - mmseg - INFO - Iter [42750/80000] lr: 6.686e-07, eta: 6:28:49, time: 0.639, data_time: 0.052, memory: 60248, decode.loss_ce: 0.1674, decode.acc_seg: 75.3215, aux.loss_ce: 0.1076, aux.acc_seg: 73.1076, loss: 0.2750 +2022-05-05 16:41:34,800 - mmseg - INFO - Iter [42800/80000] lr: 6.677e-07, eta: 6:28:16, time: 0.592, data_time: 0.005, memory: 60248, decode.loss_ce: 0.1616, decode.acc_seg: 76.3884, aux.loss_ce: 0.1044, aux.acc_seg: 74.3228, loss: 0.2660 +2022-05-05 16:42:04,146 - mmseg - INFO - Iter [42850/80000] lr: 6.668e-07, eta: 6:27:43, time: 0.587, data_time: 0.005, memory: 60248, decode.loss_ce: 0.1597, decode.acc_seg: 75.6516, aux.loss_ce: 0.1018, aux.acc_seg: 73.4270, loss: 0.2615 +2022-05-05 16:42:33,675 - mmseg - INFO - Iter [42900/80000] lr: 6.659e-07, eta: 6:27:10, time: 0.590, data_time: 0.005, memory: 60248, decode.loss_ce: 0.1564, decode.acc_seg: 75.0720, aux.loss_ce: 0.0991, aux.acc_seg: 73.1897, loss: 0.2556 +2022-05-05 16:43:03,096 - mmseg - INFO - Iter [42950/80000] lr: 6.650e-07, eta: 6:26:37, time: 0.588, data_time: 0.005, memory: 60248, decode.loss_ce: 0.1562, decode.acc_seg: 74.4499, aux.loss_ce: 0.0990, aux.acc_seg: 72.5882, loss: 0.2553 +2022-05-05 16:43:32,876 - mmseg - INFO - Saving checkpoint at 43000 iterations +2022-05-05 16:43:52,944 - mmseg - INFO - Exp name: upernet_beit_adapter_large_512_80k_cocostuff10k_ss.py +2022-05-05 16:43:52,951 - mmseg - INFO - Iter [43000/80000] lr: 6.641e-07, eta: 6:26:22, time: 0.994, data_time: 0.004, memory: 60248, decode.loss_ce: 0.1512, decode.acc_seg: 75.6309, aux.loss_ce: 0.0976, aux.acc_seg: 73.6782, loss: 0.2487 +2022-05-05 16:44:22,783 - mmseg - INFO - Iter [43050/80000] lr: 6.632e-07, eta: 6:25:49, time: 0.599, data_time: 0.007, memory: 60248, decode.loss_ce: 0.1639, decode.acc_seg: 74.7754, aux.loss_ce: 0.1055, aux.acc_seg: 72.7506, loss: 0.2694 +2022-05-05 16:44:52,229 - mmseg - INFO - Iter [43100/80000] lr: 6.623e-07, eta: 6:25:16, time: 0.589, data_time: 0.005, memory: 60248, decode.loss_ce: 0.1604, decode.acc_seg: 74.6619, aux.loss_ce: 0.1036, aux.acc_seg: 72.6778, loss: 0.2640 +2022-05-05 16:45:21,733 - mmseg - INFO - Iter [43150/80000] lr: 6.614e-07, eta: 6:24:43, time: 0.590, data_time: 0.005, memory: 60248, decode.loss_ce: 0.1612, decode.acc_seg: 75.2258, aux.loss_ce: 0.1025, aux.acc_seg: 73.2468, loss: 0.2637 +2022-05-05 16:45:51,490 - mmseg - INFO - Iter [43200/80000] lr: 6.605e-07, eta: 6:24:11, time: 0.595, data_time: 0.005, memory: 60248, decode.loss_ce: 0.1652, decode.acc_seg: 76.2575, aux.loss_ce: 0.1091, aux.acc_seg: 74.0578, loss: 0.2743 +2022-05-05 16:46:20,855 - mmseg - INFO - Iter [43250/80000] lr: 6.596e-07, eta: 6:23:38, time: 0.587, data_time: 0.004, memory: 60248, decode.loss_ce: 0.1624, decode.acc_seg: 77.1896, aux.loss_ce: 0.1047, aux.acc_seg: 75.1411, loss: 0.2670 +2022-05-05 16:46:53,530 - mmseg - INFO - Iter [43300/80000] lr: 6.587e-07, eta: 6:23:07, time: 0.653, data_time: 0.056, memory: 60248, decode.loss_ce: 0.1736, decode.acc_seg: 74.9465, aux.loss_ce: 0.1091, aux.acc_seg: 72.8865, loss: 0.2827 +2022-05-05 16:47:22,860 - mmseg - INFO - Iter [43350/80000] lr: 6.578e-07, eta: 6:22:34, time: 0.587, data_time: 0.005, memory: 60248, decode.loss_ce: 0.1579, decode.acc_seg: 75.5608, aux.loss_ce: 0.0983, aux.acc_seg: 73.7126, loss: 0.2561 +2022-05-05 16:47:52,612 - mmseg - INFO - Iter [43400/80000] lr: 6.569e-07, eta: 6:22:02, time: 0.595, data_time: 0.004, memory: 60248, decode.loss_ce: 0.1655, decode.acc_seg: 74.6611, aux.loss_ce: 0.1049, aux.acc_seg: 72.5894, loss: 0.2704 +2022-05-05 16:48:22,101 - mmseg - INFO - Iter [43450/80000] lr: 6.560e-07, eta: 6:21:29, time: 0.590, data_time: 0.004, memory: 60248, decode.loss_ce: 0.1602, decode.acc_seg: 75.1961, aux.loss_ce: 0.1044, aux.acc_seg: 72.9866, loss: 0.2646 +2022-05-05 16:48:51,943 - mmseg - INFO - Iter [43500/80000] lr: 6.551e-07, eta: 6:20:56, time: 0.597, data_time: 0.005, memory: 60248, decode.loss_ce: 0.1553, decode.acc_seg: 74.9872, aux.loss_ce: 0.1011, aux.acc_seg: 72.9079, loss: 0.2564 +2022-05-05 16:49:21,361 - mmseg - INFO - Iter [43550/80000] lr: 6.542e-07, eta: 6:20:23, time: 0.588, data_time: 0.005, memory: 60248, decode.loss_ce: 0.1604, decode.acc_seg: 75.1268, aux.loss_ce: 0.1039, aux.acc_seg: 73.1436, loss: 0.2643 +2022-05-05 16:49:51,263 - mmseg - INFO - Iter [43600/80000] lr: 6.533e-07, eta: 6:19:51, time: 0.598, data_time: 0.005, memory: 60248, decode.loss_ce: 0.1621, decode.acc_seg: 74.4536, aux.loss_ce: 0.1021, aux.acc_seg: 72.3372, loss: 0.2643 +2022-05-05 16:50:20,999 - mmseg - INFO - Iter [43650/80000] lr: 6.524e-07, eta: 6:19:18, time: 0.595, data_time: 0.004, memory: 60248, decode.loss_ce: 0.1813, decode.acc_seg: 73.8599, aux.loss_ce: 0.1157, aux.acc_seg: 71.4838, loss: 0.2970 +2022-05-05 16:50:50,636 - mmseg - INFO - Iter [43700/80000] lr: 6.515e-07, eta: 6:18:46, time: 0.592, data_time: 0.004, memory: 60248, decode.loss_ce: 0.1586, decode.acc_seg: 76.0925, aux.loss_ce: 0.1012, aux.acc_seg: 73.9892, loss: 0.2599 +2022-05-05 16:51:20,154 - mmseg - INFO - Iter [43750/80000] lr: 6.506e-07, eta: 6:18:13, time: 0.591, data_time: 0.005, memory: 60248, decode.loss_ce: 0.1622, decode.acc_seg: 76.4795, aux.loss_ce: 0.1043, aux.acc_seg: 74.4804, loss: 0.2665 +2022-05-05 16:51:49,637 - mmseg - INFO - Iter [43800/80000] lr: 6.497e-07, eta: 6:17:40, time: 0.590, data_time: 0.005, memory: 60248, decode.loss_ce: 0.1570, decode.acc_seg: 75.6312, aux.loss_ce: 0.1027, aux.acc_seg: 73.4702, loss: 0.2596 +2022-05-05 16:52:21,678 - mmseg - INFO - Iter [43850/80000] lr: 6.488e-07, eta: 6:17:09, time: 0.641, data_time: 0.052, memory: 60248, decode.loss_ce: 0.1594, decode.acc_seg: 75.5862, aux.loss_ce: 0.1044, aux.acc_seg: 73.4496, loss: 0.2637 +2022-05-05 16:52:51,070 - mmseg - INFO - Iter [43900/80000] lr: 6.479e-07, eta: 6:16:37, time: 0.588, data_time: 0.005, memory: 60248, decode.loss_ce: 0.1589, decode.acc_seg: 75.6713, aux.loss_ce: 0.1033, aux.acc_seg: 73.4405, loss: 0.2622 +2022-05-05 16:53:20,553 - mmseg - INFO - Iter [43950/80000] lr: 6.470e-07, eta: 6:16:04, time: 0.590, data_time: 0.005, memory: 60248, decode.loss_ce: 0.1552, decode.acc_seg: 73.9142, aux.loss_ce: 0.1036, aux.acc_seg: 71.6444, loss: 0.2588 +2022-05-05 16:53:49,913 - mmseg - INFO - Saving checkpoint at 44000 iterations +2022-05-05 16:54:09,699 - mmseg - INFO - Exp name: upernet_beit_adapter_large_512_80k_cocostuff10k_ss.py +2022-05-05 16:54:09,701 - mmseg - INFO - Iter [44000/80000] lr: 6.461e-07, eta: 6:15:47, time: 0.983, data_time: 0.005, memory: 60248, decode.loss_ce: 0.1567, decode.acc_seg: 76.2419, aux.loss_ce: 0.0993, aux.acc_seg: 74.2851, loss: 0.2560 +2022-05-05 16:54:39,208 - mmseg - INFO - Iter [44050/80000] lr: 6.452e-07, eta: 6:15:14, time: 0.590, data_time: 0.004, memory: 60248, decode.loss_ce: 0.1483, decode.acc_seg: 75.5272, aux.loss_ce: 0.0996, aux.acc_seg: 73.4175, loss: 0.2479 +2022-05-05 16:55:08,751 - mmseg - INFO - Iter [44100/80000] lr: 6.443e-07, eta: 6:14:42, time: 0.591, data_time: 0.004, memory: 60248, decode.loss_ce: 0.1615, decode.acc_seg: 76.4199, aux.loss_ce: 0.1018, aux.acc_seg: 74.4259, loss: 0.2633 +2022-05-05 16:55:38,606 - mmseg - INFO - Iter [44150/80000] lr: 6.434e-07, eta: 6:14:09, time: 0.597, data_time: 0.004, memory: 60248, decode.loss_ce: 0.1590, decode.acc_seg: 75.5208, aux.loss_ce: 0.1011, aux.acc_seg: 73.3696, loss: 0.2600 +2022-05-05 16:56:08,220 - mmseg - INFO - Iter [44200/80000] lr: 6.425e-07, eta: 6:13:36, time: 0.592, data_time: 0.004, memory: 60248, decode.loss_ce: 0.1573, decode.acc_seg: 74.8460, aux.loss_ce: 0.1017, aux.acc_seg: 72.7022, loss: 0.2589 +2022-05-05 16:56:37,986 - mmseg - INFO - Iter [44250/80000] lr: 6.416e-07, eta: 6:13:04, time: 0.595, data_time: 0.006, memory: 60248, decode.loss_ce: 0.1592, decode.acc_seg: 75.7272, aux.loss_ce: 0.1017, aux.acc_seg: 73.7843, loss: 0.2609 +2022-05-05 16:57:07,379 - mmseg - INFO - Iter [44300/80000] lr: 6.407e-07, eta: 6:12:31, time: 0.588, data_time: 0.004, memory: 60248, decode.loss_ce: 0.1546, decode.acc_seg: 76.7999, aux.loss_ce: 0.0993, aux.acc_seg: 74.9203, loss: 0.2539 +2022-05-05 16:57:36,741 - mmseg - INFO - Iter [44350/80000] lr: 6.398e-07, eta: 6:11:58, time: 0.587, data_time: 0.004, memory: 60248, decode.loss_ce: 0.1582, decode.acc_seg: 76.5280, aux.loss_ce: 0.1009, aux.acc_seg: 74.5663, loss: 0.2591 +2022-05-05 16:58:08,796 - mmseg - INFO - Iter [44400/80000] lr: 6.389e-07, eta: 6:11:27, time: 0.641, data_time: 0.052, memory: 60248, decode.loss_ce: 0.1688, decode.acc_seg: 74.9911, aux.loss_ce: 0.1075, aux.acc_seg: 72.8336, loss: 0.2763 +2022-05-05 16:58:38,365 - mmseg - INFO - Iter [44450/80000] lr: 6.380e-07, eta: 6:10:55, time: 0.591, data_time: 0.006, memory: 60248, decode.loss_ce: 0.1551, decode.acc_seg: 76.0248, aux.loss_ce: 0.1006, aux.acc_seg: 73.9213, loss: 0.2557 +2022-05-05 16:59:07,815 - mmseg - INFO - Iter [44500/80000] lr: 6.372e-07, eta: 6:10:22, time: 0.589, data_time: 0.004, memory: 60248, decode.loss_ce: 0.1581, decode.acc_seg: 75.7382, aux.loss_ce: 0.1005, aux.acc_seg: 73.7185, loss: 0.2586 +2022-05-05 16:59:37,290 - mmseg - INFO - Iter [44550/80000] lr: 6.363e-07, eta: 6:09:49, time: 0.588, data_time: 0.005, memory: 60248, decode.loss_ce: 0.1598, decode.acc_seg: 77.0381, aux.loss_ce: 0.1038, aux.acc_seg: 74.8887, loss: 0.2636 +2022-05-05 17:00:07,155 - mmseg - INFO - Iter [44600/80000] lr: 6.354e-07, eta: 6:09:17, time: 0.599, data_time: 0.008, memory: 60248, decode.loss_ce: 0.1572, decode.acc_seg: 75.6012, aux.loss_ce: 0.1021, aux.acc_seg: 73.5425, loss: 0.2593 +2022-05-05 17:00:37,323 - mmseg - INFO - Iter [44650/80000] lr: 6.345e-07, eta: 6:08:45, time: 0.603, data_time: 0.005, memory: 60248, decode.loss_ce: 0.1608, decode.acc_seg: 73.6716, aux.loss_ce: 0.1044, aux.acc_seg: 71.5561, loss: 0.2652 +2022-05-05 17:01:06,852 - mmseg - INFO - Iter [44700/80000] lr: 6.336e-07, eta: 6:08:12, time: 0.591, data_time: 0.005, memory: 60248, decode.loss_ce: 0.1552, decode.acc_seg: 75.2793, aux.loss_ce: 0.0999, aux.acc_seg: 73.2610, loss: 0.2551 +2022-05-05 17:01:36,207 - mmseg - INFO - Iter [44750/80000] lr: 6.327e-07, eta: 6:07:39, time: 0.587, data_time: 0.004, memory: 60248, decode.loss_ce: 0.1501, decode.acc_seg: 75.9137, aux.loss_ce: 0.0982, aux.acc_seg: 73.9168, loss: 0.2483 +2022-05-05 17:02:05,630 - mmseg - INFO - Iter [44800/80000] lr: 6.318e-07, eta: 6:07:06, time: 0.588, data_time: 0.004, memory: 60248, decode.loss_ce: 0.1469, decode.acc_seg: 76.6789, aux.loss_ce: 0.0976, aux.acc_seg: 74.6029, loss: 0.2445 +2022-05-05 17:02:35,088 - mmseg - INFO - Iter [44850/80000] lr: 6.309e-07, eta: 6:06:34, time: 0.589, data_time: 0.004, memory: 60248, decode.loss_ce: 0.1515, decode.acc_seg: 76.1235, aux.loss_ce: 0.0963, aux.acc_seg: 74.2407, loss: 0.2478 +2022-05-05 17:03:04,512 - mmseg - INFO - Iter [44900/80000] lr: 6.300e-07, eta: 6:06:01, time: 0.588, data_time: 0.005, memory: 60248, decode.loss_ce: 0.1686, decode.acc_seg: 75.0225, aux.loss_ce: 0.1065, aux.acc_seg: 72.8706, loss: 0.2751 +2022-05-05 17:03:34,116 - mmseg - INFO - Iter [44950/80000] lr: 6.291e-07, eta: 6:05:28, time: 0.592, data_time: 0.004, memory: 60248, decode.loss_ce: 0.1486, decode.acc_seg: 74.5955, aux.loss_ce: 0.0948, aux.acc_seg: 72.7809, loss: 0.2434 +2022-05-05 17:04:06,390 - mmseg - INFO - Saving checkpoint at 45000 iterations +2022-05-05 17:04:27,460 - mmseg - INFO - Exp name: upernet_beit_adapter_large_512_80k_cocostuff10k_ss.py +2022-05-05 17:04:27,463 - mmseg - INFO - Iter [45000/80000] lr: 6.282e-07, eta: 6:05:14, time: 1.065, data_time: 0.055, memory: 60248, decode.loss_ce: 0.1579, decode.acc_seg: 74.6304, aux.loss_ce: 0.0990, aux.acc_seg: 72.7384, loss: 0.2568 +2022-05-05 17:04:57,011 - mmseg - INFO - Iter [45050/80000] lr: 6.273e-07, eta: 6:04:41, time: 0.593, data_time: 0.006, memory: 60248, decode.loss_ce: 0.1557, decode.acc_seg: 74.9024, aux.loss_ce: 0.1042, aux.acc_seg: 72.6506, loss: 0.2600 +2022-05-05 17:05:26,533 - mmseg - INFO - Iter [45100/80000] lr: 6.264e-07, eta: 6:04:09, time: 0.590, data_time: 0.005, memory: 60248, decode.loss_ce: 0.1568, decode.acc_seg: 75.0819, aux.loss_ce: 0.0994, aux.acc_seg: 73.1419, loss: 0.2562 +2022-05-05 17:05:55,830 - mmseg - INFO - Iter [45150/80000] lr: 6.255e-07, eta: 6:03:36, time: 0.586, data_time: 0.004, memory: 60248, decode.loss_ce: 0.1587, decode.acc_seg: 75.3022, aux.loss_ce: 0.0999, aux.acc_seg: 73.2403, loss: 0.2587 +2022-05-05 17:06:25,453 - mmseg - INFO - Iter [45200/80000] lr: 6.246e-07, eta: 6:03:03, time: 0.592, data_time: 0.005, memory: 60248, decode.loss_ce: 0.1541, decode.acc_seg: 76.7194, aux.loss_ce: 0.0972, aux.acc_seg: 74.8973, loss: 0.2513 +2022-05-05 17:06:54,868 - mmseg - INFO - Iter [45250/80000] lr: 6.237e-07, eta: 6:02:31, time: 0.588, data_time: 0.005, memory: 60248, decode.loss_ce: 0.1478, decode.acc_seg: 75.7446, aux.loss_ce: 0.0981, aux.acc_seg: 73.6504, loss: 0.2458 +2022-05-05 17:07:24,253 - mmseg - INFO - Iter [45300/80000] lr: 6.228e-07, eta: 6:01:58, time: 0.588, data_time: 0.005, memory: 60248, decode.loss_ce: 0.1527, decode.acc_seg: 74.7379, aux.loss_ce: 0.0980, aux.acc_seg: 72.7318, loss: 0.2506 +2022-05-05 17:07:53,677 - mmseg - INFO - Iter [45350/80000] lr: 6.219e-07, eta: 6:01:25, time: 0.588, data_time: 0.005, memory: 60248, decode.loss_ce: 0.1588, decode.acc_seg: 76.5253, aux.loss_ce: 0.1024, aux.acc_seg: 74.4909, loss: 0.2613 +2022-05-05 17:08:23,252 - mmseg - INFO - Iter [45400/80000] lr: 6.210e-07, eta: 6:00:52, time: 0.592, data_time: 0.005, memory: 60248, decode.loss_ce: 0.1530, decode.acc_seg: 76.4175, aux.loss_ce: 0.1032, aux.acc_seg: 74.0080, loss: 0.2562 +2022-05-05 17:08:52,885 - mmseg - INFO - Iter [45450/80000] lr: 6.201e-07, eta: 6:00:20, time: 0.593, data_time: 0.005, memory: 60248, decode.loss_ce: 0.1561, decode.acc_seg: 75.4431, aux.loss_ce: 0.1031, aux.acc_seg: 73.0994, loss: 0.2592 +2022-05-05 17:09:22,401 - mmseg - INFO - Iter [45500/80000] lr: 6.192e-07, eta: 5:59:47, time: 0.590, data_time: 0.004, memory: 60248, decode.loss_ce: 0.1466, decode.acc_seg: 75.3209, aux.loss_ce: 0.0970, aux.acc_seg: 73.2308, loss: 0.2436 +2022-05-05 17:09:54,479 - mmseg - INFO - Iter [45550/80000] lr: 6.183e-07, eta: 5:59:17, time: 0.641, data_time: 0.055, memory: 60248, decode.loss_ce: 0.1560, decode.acc_seg: 74.6549, aux.loss_ce: 0.0992, aux.acc_seg: 72.6944, loss: 0.2552 +2022-05-05 17:10:23,795 - mmseg - INFO - Iter [45600/80000] lr: 6.174e-07, eta: 5:58:44, time: 0.586, data_time: 0.004, memory: 60248, decode.loss_ce: 0.1579, decode.acc_seg: 75.9551, aux.loss_ce: 0.1011, aux.acc_seg: 73.9157, loss: 0.2590 +2022-05-05 17:10:53,219 - mmseg - INFO - Iter [45650/80000] lr: 6.165e-07, eta: 5:58:11, time: 0.588, data_time: 0.005, memory: 60248, decode.loss_ce: 0.1661, decode.acc_seg: 75.3973, aux.loss_ce: 0.1042, aux.acc_seg: 73.4504, loss: 0.2703 +2022-05-05 17:11:22,927 - mmseg - INFO - Iter [45700/80000] lr: 6.156e-07, eta: 5:57:39, time: 0.594, data_time: 0.005, memory: 60248, decode.loss_ce: 0.1454, decode.acc_seg: 76.1970, aux.loss_ce: 0.0979, aux.acc_seg: 73.9001, loss: 0.2433 +2022-05-05 17:11:52,555 - mmseg - INFO - Iter [45750/80000] lr: 6.147e-07, eta: 5:57:06, time: 0.593, data_time: 0.004, memory: 60248, decode.loss_ce: 0.1637, decode.acc_seg: 74.9622, aux.loss_ce: 0.1047, aux.acc_seg: 72.8605, loss: 0.2685 +2022-05-05 17:12:21,881 - mmseg - INFO - Iter [45800/80000] lr: 6.138e-07, eta: 5:56:33, time: 0.586, data_time: 0.004, memory: 60248, decode.loss_ce: 0.1662, decode.acc_seg: 75.3032, aux.loss_ce: 0.1041, aux.acc_seg: 73.3269, loss: 0.2703 +2022-05-05 17:12:51,710 - mmseg - INFO - Iter [45850/80000] lr: 6.129e-07, eta: 5:56:01, time: 0.597, data_time: 0.005, memory: 60248, decode.loss_ce: 0.1568, decode.acc_seg: 75.3551, aux.loss_ce: 0.1008, aux.acc_seg: 73.3382, loss: 0.2576 +2022-05-05 17:13:21,268 - mmseg - INFO - Iter [45900/80000] lr: 6.120e-07, eta: 5:55:28, time: 0.591, data_time: 0.006, memory: 60248, decode.loss_ce: 0.1494, decode.acc_seg: 74.8345, aux.loss_ce: 0.0982, aux.acc_seg: 72.7869, loss: 0.2476 +2022-05-05 17:13:50,751 - mmseg - INFO - Iter [45950/80000] lr: 6.111e-07, eta: 5:54:56, time: 0.590, data_time: 0.004, memory: 60248, decode.loss_ce: 0.1588, decode.acc_seg: 75.4798, aux.loss_ce: 0.1012, aux.acc_seg: 73.5400, loss: 0.2600 +2022-05-05 17:14:20,283 - mmseg - INFO - Saving checkpoint at 46000 iterations +2022-05-05 17:14:40,998 - mmseg - INFO - Exp name: upernet_beit_adapter_large_512_80k_cocostuff10k_ss.py +2022-05-05 17:14:41,000 - mmseg - INFO - Iter [46000/80000] lr: 6.102e-07, eta: 5:54:39, time: 1.002, data_time: 0.005, memory: 60248, decode.loss_ce: 0.1556, decode.acc_seg: 76.4492, aux.loss_ce: 0.1005, aux.acc_seg: 74.3355, loss: 0.2561 +2022-05-05 17:15:10,679 - mmseg - INFO - Iter [46050/80000] lr: 6.093e-07, eta: 5:54:06, time: 0.597, data_time: 0.009, memory: 60248, decode.loss_ce: 0.1610, decode.acc_seg: 75.0761, aux.loss_ce: 0.1038, aux.acc_seg: 72.9116, loss: 0.2649 +2022-05-05 17:15:43,102 - mmseg - INFO - Iter [46100/80000] lr: 6.084e-07, eta: 5:53:36, time: 0.648, data_time: 0.054, memory: 60248, decode.loss_ce: 0.1419, decode.acc_seg: 75.9640, aux.loss_ce: 0.0925, aux.acc_seg: 74.1318, loss: 0.2344 +2022-05-05 17:16:12,737 - mmseg - INFO - Iter [46150/80000] lr: 6.075e-07, eta: 5:53:03, time: 0.593, data_time: 0.005, memory: 60248, decode.loss_ce: 0.1475, decode.acc_seg: 75.9779, aux.loss_ce: 0.0963, aux.acc_seg: 74.1044, loss: 0.2438 +2022-05-05 17:16:42,011 - mmseg - INFO - Iter [46200/80000] lr: 6.066e-07, eta: 5:52:30, time: 0.585, data_time: 0.004, memory: 60248, decode.loss_ce: 0.1422, decode.acc_seg: 76.8138, aux.loss_ce: 0.0952, aux.acc_seg: 74.7556, loss: 0.2374 +2022-05-05 17:17:11,655 - mmseg - INFO - Iter [46250/80000] lr: 6.057e-07, eta: 5:51:58, time: 0.593, data_time: 0.004, memory: 60248, decode.loss_ce: 0.1620, decode.acc_seg: 75.5190, aux.loss_ce: 0.0995, aux.acc_seg: 73.6278, loss: 0.2615 +2022-05-05 17:17:41,142 - mmseg - INFO - Iter [46300/80000] lr: 6.048e-07, eta: 5:51:25, time: 0.590, data_time: 0.005, memory: 60248, decode.loss_ce: 0.1624, decode.acc_seg: 76.0264, aux.loss_ce: 0.1010, aux.acc_seg: 74.1245, loss: 0.2634 +2022-05-05 17:18:10,654 - mmseg - INFO - Iter [46350/80000] lr: 6.039e-07, eta: 5:50:53, time: 0.590, data_time: 0.005, memory: 60248, decode.loss_ce: 0.1602, decode.acc_seg: 76.4312, aux.loss_ce: 0.1033, aux.acc_seg: 74.4580, loss: 0.2635 +2022-05-05 17:18:40,164 - mmseg - INFO - Iter [46400/80000] lr: 6.031e-07, eta: 5:50:20, time: 0.590, data_time: 0.005, memory: 60248, decode.loss_ce: 0.1476, decode.acc_seg: 74.3697, aux.loss_ce: 0.0950, aux.acc_seg: 72.5510, loss: 0.2426 +2022-05-05 17:19:09,440 - mmseg - INFO - Iter [46450/80000] lr: 6.022e-07, eta: 5:49:47, time: 0.586, data_time: 0.004, memory: 60248, decode.loss_ce: 0.1551, decode.acc_seg: 76.3990, aux.loss_ce: 0.1002, aux.acc_seg: 74.3848, loss: 0.2552 +2022-05-05 17:19:39,124 - mmseg - INFO - Iter [46500/80000] lr: 6.013e-07, eta: 5:49:15, time: 0.594, data_time: 0.004, memory: 60248, decode.loss_ce: 0.1578, decode.acc_seg: 75.5212, aux.loss_ce: 0.0999, aux.acc_seg: 73.5428, loss: 0.2577 +2022-05-05 17:20:08,637 - mmseg - INFO - Iter [46550/80000] lr: 6.004e-07, eta: 5:48:42, time: 0.590, data_time: 0.004, memory: 60248, decode.loss_ce: 0.1510, decode.acc_seg: 74.7776, aux.loss_ce: 0.0988, aux.acc_seg: 72.8854, loss: 0.2499 +2022-05-05 17:20:38,486 - mmseg - INFO - Iter [46600/80000] lr: 5.995e-07, eta: 5:48:10, time: 0.597, data_time: 0.006, memory: 60248, decode.loss_ce: 0.1618, decode.acc_seg: 75.0926, aux.loss_ce: 0.1031, aux.acc_seg: 72.9946, loss: 0.2649 +2022-05-05 17:21:10,315 - mmseg - INFO - Iter [46650/80000] lr: 5.986e-07, eta: 5:47:39, time: 0.636, data_time: 0.052, memory: 60248, decode.loss_ce: 0.1573, decode.acc_seg: 77.0334, aux.loss_ce: 0.1004, aux.acc_seg: 75.0021, loss: 0.2578 +2022-05-05 17:21:39,652 - mmseg - INFO - Iter [46700/80000] lr: 5.977e-07, eta: 5:47:07, time: 0.587, data_time: 0.005, memory: 60248, decode.loss_ce: 0.1635, decode.acc_seg: 72.9321, aux.loss_ce: 0.1006, aux.acc_seg: 71.0034, loss: 0.2640 +2022-05-05 17:22:09,326 - mmseg - INFO - Iter [46750/80000] lr: 5.968e-07, eta: 5:46:34, time: 0.594, data_time: 0.004, memory: 60248, decode.loss_ce: 0.1499, decode.acc_seg: 75.5568, aux.loss_ce: 0.0985, aux.acc_seg: 73.4110, loss: 0.2484 +2022-05-05 17:22:38,699 - mmseg - INFO - Iter [46800/80000] lr: 5.959e-07, eta: 5:46:02, time: 0.587, data_time: 0.004, memory: 60248, decode.loss_ce: 0.1474, decode.acc_seg: 76.1313, aux.loss_ce: 0.0934, aux.acc_seg: 74.2056, loss: 0.2408 +2022-05-05 17:23:08,137 - mmseg - INFO - Iter [46850/80000] lr: 5.950e-07, eta: 5:45:29, time: 0.589, data_time: 0.004, memory: 60248, decode.loss_ce: 0.1509, decode.acc_seg: 75.1893, aux.loss_ce: 0.0942, aux.acc_seg: 73.5011, loss: 0.2451 +2022-05-05 17:23:37,647 - mmseg - INFO - Iter [46900/80000] lr: 5.941e-07, eta: 5:44:57, time: 0.590, data_time: 0.004, memory: 60248, decode.loss_ce: 0.1586, decode.acc_seg: 75.6985, aux.loss_ce: 0.1039, aux.acc_seg: 73.5676, loss: 0.2625 +2022-05-05 17:24:07,176 - mmseg - INFO - Iter [46950/80000] lr: 5.932e-07, eta: 5:44:24, time: 0.591, data_time: 0.004, memory: 60248, decode.loss_ce: 0.1606, decode.acc_seg: 75.6820, aux.loss_ce: 0.1032, aux.acc_seg: 73.6320, loss: 0.2638 +2022-05-05 17:24:36,594 - mmseg - INFO - Saving checkpoint at 47000 iterations +2022-05-05 17:24:57,778 - mmseg - INFO - Exp name: upernet_beit_adapter_large_512_80k_cocostuff10k_ss.py +2022-05-05 17:24:57,781 - mmseg - INFO - Iter [47000/80000] lr: 5.923e-07, eta: 5:44:06, time: 1.010, data_time: 0.005, memory: 60248, decode.loss_ce: 0.1608, decode.acc_seg: 74.2286, aux.loss_ce: 0.1009, aux.acc_seg: 72.3912, loss: 0.2617 +2022-05-05 17:25:28,058 - mmseg - INFO - Iter [47050/80000] lr: 5.914e-07, eta: 5:43:34, time: 0.606, data_time: 0.007, memory: 60248, decode.loss_ce: 0.1617, decode.acc_seg: 74.9666, aux.loss_ce: 0.1023, aux.acc_seg: 72.9076, loss: 0.2640 +2022-05-05 17:25:57,855 - mmseg - INFO - Iter [47100/80000] lr: 5.905e-07, eta: 5:43:02, time: 0.598, data_time: 0.008, memory: 60248, decode.loss_ce: 0.1458, decode.acc_seg: 75.7551, aux.loss_ce: 0.0953, aux.acc_seg: 73.8156, loss: 0.2411 +2022-05-05 17:26:27,578 - mmseg - INFO - Iter [47150/80000] lr: 5.896e-07, eta: 5:42:30, time: 0.594, data_time: 0.005, memory: 60248, decode.loss_ce: 0.1553, decode.acc_seg: 75.9442, aux.loss_ce: 0.0991, aux.acc_seg: 73.9415, loss: 0.2544 +2022-05-05 17:26:57,183 - mmseg - INFO - Iter [47200/80000] lr: 5.887e-07, eta: 5:41:57, time: 0.592, data_time: 0.005, memory: 60248, decode.loss_ce: 0.1542, decode.acc_seg: 76.6324, aux.loss_ce: 0.0991, aux.acc_seg: 74.6372, loss: 0.2533 +2022-05-05 17:27:29,034 - mmseg - INFO - Iter [47250/80000] lr: 5.878e-07, eta: 5:41:26, time: 0.637, data_time: 0.055, memory: 60248, decode.loss_ce: 0.1543, decode.acc_seg: 76.5781, aux.loss_ce: 0.0983, aux.acc_seg: 74.5312, loss: 0.2526 +2022-05-05 17:27:58,793 - mmseg - INFO - Iter [47300/80000] lr: 5.869e-07, eta: 5:40:54, time: 0.595, data_time: 0.004, memory: 60248, decode.loss_ce: 0.1505, decode.acc_seg: 76.3858, aux.loss_ce: 0.1010, aux.acc_seg: 74.1158, loss: 0.2516 +2022-05-05 17:28:28,594 - mmseg - INFO - Iter [47350/80000] lr: 5.860e-07, eta: 5:40:22, time: 0.596, data_time: 0.005, memory: 60248, decode.loss_ce: 0.1529, decode.acc_seg: 75.7094, aux.loss_ce: 0.0982, aux.acc_seg: 73.8463, loss: 0.2511 +2022-05-05 17:28:58,195 - mmseg - INFO - Iter [47400/80000] lr: 5.851e-07, eta: 5:39:49, time: 0.592, data_time: 0.005, memory: 60248, decode.loss_ce: 0.1545, decode.acc_seg: 75.4104, aux.loss_ce: 0.1006, aux.acc_seg: 73.3802, loss: 0.2551 +2022-05-05 17:29:27,883 - mmseg - INFO - Iter [47450/80000] lr: 5.842e-07, eta: 5:39:17, time: 0.594, data_time: 0.004, memory: 60248, decode.loss_ce: 0.1514, decode.acc_seg: 76.0867, aux.loss_ce: 0.0981, aux.acc_seg: 74.1900, loss: 0.2495 +2022-05-05 17:29:57,834 - mmseg - INFO - Iter [47500/80000] lr: 5.833e-07, eta: 5:38:45, time: 0.599, data_time: 0.004, memory: 60248, decode.loss_ce: 0.1637, decode.acc_seg: 73.9663, aux.loss_ce: 0.1085, aux.acc_seg: 71.5597, loss: 0.2722 +2022-05-05 17:30:27,740 - mmseg - INFO - Iter [47550/80000] lr: 5.824e-07, eta: 5:38:13, time: 0.598, data_time: 0.004, memory: 60248, decode.loss_ce: 0.1477, decode.acc_seg: 74.4404, aux.loss_ce: 0.0949, aux.acc_seg: 72.5721, loss: 0.2427 +2022-05-05 17:30:57,206 - mmseg - INFO - Iter [47600/80000] lr: 5.815e-07, eta: 5:37:40, time: 0.589, data_time: 0.005, memory: 60248, decode.loss_ce: 0.1413, decode.acc_seg: 76.0485, aux.loss_ce: 0.0921, aux.acc_seg: 74.1776, loss: 0.2334 +2022-05-05 17:31:26,780 - mmseg - INFO - Iter [47650/80000] lr: 5.806e-07, eta: 5:37:08, time: 0.592, data_time: 0.005, memory: 60248, decode.loss_ce: 0.1600, decode.acc_seg: 75.1904, aux.loss_ce: 0.1036, aux.acc_seg: 73.0300, loss: 0.2636 +2022-05-05 17:31:56,365 - mmseg - INFO - Iter [47700/80000] lr: 5.797e-07, eta: 5:36:35, time: 0.592, data_time: 0.004, memory: 60248, decode.loss_ce: 0.1553, decode.acc_seg: 76.1263, aux.loss_ce: 0.1007, aux.acc_seg: 73.8974, loss: 0.2560 +2022-05-05 17:32:25,979 - mmseg - INFO - Iter [47750/80000] lr: 5.788e-07, eta: 5:36:03, time: 0.590, data_time: 0.005, memory: 60248, decode.loss_ce: 0.1492, decode.acc_seg: 75.9256, aux.loss_ce: 0.0958, aux.acc_seg: 74.0383, loss: 0.2450 +2022-05-05 17:32:58,176 - mmseg - INFO - Iter [47800/80000] lr: 5.779e-07, eta: 5:35:32, time: 0.646, data_time: 0.056, memory: 60248, decode.loss_ce: 0.1410, decode.acc_seg: 75.8546, aux.loss_ce: 0.0907, aux.acc_seg: 74.0859, loss: 0.2317 +2022-05-05 17:33:27,807 - mmseg - INFO - Iter [47850/80000] lr: 5.770e-07, eta: 5:35:00, time: 0.591, data_time: 0.004, memory: 60248, decode.loss_ce: 0.1521, decode.acc_seg: 75.8266, aux.loss_ce: 0.0957, aux.acc_seg: 74.1079, loss: 0.2478 +2022-05-05 17:33:57,590 - mmseg - INFO - Iter [47900/80000] lr: 5.761e-07, eta: 5:34:28, time: 0.597, data_time: 0.007, memory: 60248, decode.loss_ce: 0.1573, decode.acc_seg: 76.4588, aux.loss_ce: 0.1007, aux.acc_seg: 74.3937, loss: 0.2580 +2022-05-05 17:34:27,027 - mmseg - INFO - Iter [47950/80000] lr: 5.752e-07, eta: 5:33:55, time: 0.589, data_time: 0.004, memory: 60248, decode.loss_ce: 0.1463, decode.acc_seg: 73.3916, aux.loss_ce: 0.0954, aux.acc_seg: 71.2552, loss: 0.2417 +2022-05-05 17:34:56,945 - mmseg - INFO - Saving checkpoint at 48000 iterations +2022-05-05 17:35:17,344 - mmseg - INFO - Exp name: upernet_beit_adapter_large_512_80k_cocostuff10k_ss.py +2022-05-05 17:35:17,347 - mmseg - INFO - Iter [48000/80000] lr: 5.743e-07, eta: 5:33:37, time: 1.004, data_time: 0.005, memory: 60248, decode.loss_ce: 0.1587, decode.acc_seg: 74.6760, aux.loss_ce: 0.1016, aux.acc_seg: 72.6711, loss: 0.2602 +2022-05-05 17:35:47,542 - mmseg - INFO - per class results: +2022-05-05 17:35:47,552 - mmseg - INFO - ++------------------+-------+-------+ +| Class | IoU | Acc | ++------------------+-------+-------+ +| person | 87.91 | 94.9 | +| bicycle | 73.27 | 92.64 | +| car | 64.87 | 72.95 | +| motorcycle | 87.97 | 95.59 | +| airplane | 88.54 | 96.15 | +| bus | 79.3 | 85.81 | +| train | 73.83 | 97.91 | +| truck | 76.95 | 88.87 | +| boat | 71.8 | 89.13 | +| traffic light | 73.83 | 91.73 | +| fire hydrant | 83.1 | 98.36 | +| stop sign | 90.61 | 98.06 | +| parking meter | 75.36 | 78.82 | +| bench | 48.92 | 72.94 | +| bird | 76.05 | 84.62 | +| cat | 92.79 | 97.4 | +| dog | 90.88 | 97.02 | +| horse | 89.05 | 96.36 | +| sheep | 88.4 | 92.93 | +| cow | 94.11 | 98.71 | +| elephant | 92.06 | 96.3 | +| bear | 87.16 | 95.91 | +| zebra | 90.74 | 96.61 | +| giraffe | 86.4 | 94.29 | +| backpack | 22.02 | 54.76 | +| umbrella | 77.39 | 86.16 | +| handbag | 16.73 | 22.43 | +| tie | 53.4 | 53.4 | +| suitcase | 76.89 | 96.28 | +| frisbee | 93.83 | 96.93 | +| skis | 41.98 | 67.62 | +| snowboard | 64.96 | 74.55 | +| sports ball | 83.52 | 91.77 | +| kite | 67.15 | 91.77 | +| baseball bat | 49.81 | 66.39 | +| baseball glove | 8.69 | 8.85 | +| skateboard | 66.65 | 89.23 | +| surfboard | 89.52 | 95.96 | +| tennis racket | 59.54 | 61.64 | +| bottle | 73.7 | 83.92 | +| wine glass | 83.97 | 92.39 | +| cup | 69.98 | 90.47 | +| fork | 51.65 | 63.19 | +| knife | 77.05 | 85.84 | +| spoon | 46.98 | 65.4 | +| bowl | 56.34 | 68.97 | +| banana | 78.89 | 90.26 | +| apple | 71.14 | 88.84 | +| sandwich | 85.86 | 97.42 | +| orange | 69.36 | 92.41 | +| broccoli | 91.73 | 96.03 | +| carrot | 40.98 | 74.74 | +| hot dog | 52.94 | 96.99 | +| pizza | 94.73 | 97.06 | +| donut | 67.01 | 90.45 | +| cake | 64.06 | 75.14 | +| chair | 57.8 | 76.55 | +| couch | 74.95 | 93.75 | +| potted plant | 37.57 | 48.06 | +| bed | 73.33 | 83.64 | +| dining table | 60.31 | 79.39 | +| toilet | 86.98 | 97.37 | +| tv | 68.79 | 91.47 | +| laptop | 87.24 | 98.57 | +| mouse | 70.19 | 76.34 | +| remote | 68.5 | 93.64 | +| keyboard | 84.48 | 98.02 | +| cell phone | 81.46 | 96.89 | +| microwave | 42.81 | 74.62 | +| oven | 62.32 | 85.79 | +| toaster | 29.56 | 29.56 | +| sink | 70.84 | 78.72 | +| refrigerator | 80.77 | 88.43 | +| book | 78.89 | 87.72 | +| clock | 76.1 | 87.25 | +| vase | 64.51 | 94.31 | +| scissors | 77.08 | 94.32 | +| teddy bear | 83.97 | 94.91 | +| hair drier | 0.0 | 0.0 | +| toothbrush | 14.34 | 26.45 | +| banner | 21.75 | 36.66 | +| blanket | 13.48 | 14.52 | +| branch | 4.74 | 4.74 | +| bridge | 2.58 | 3.39 | +| building-other | 54.31 | 75.94 | +| bush | 26.46 | 34.33 | +| cabinet | 16.74 | 30.66 | +| cage | 3.52 | 10.39 | +| cardboard | 23.26 | 29.88 | +| carpet | 56.93 | 73.6 | +| ceiling-other | 69.86 | 83.75 | +| ceiling-tile | 12.08 | 13.65 | +| cloth | 5.16 | 6.97 | +| clothes | 20.09 | 31.45 | +| clouds | 51.85 | 67.2 | +| counter | 34.33 | 41.35 | +| cupboard | 54.59 | 75.75 | +| curtain | 64.0 | 78.14 | +| desk-stuff | 35.85 | 43.44 | +| dirt | 33.4 | 54.46 | +| door-stuff | 45.55 | 56.85 | +| fence | 41.34 | 71.27 | +| floor-marble | 0.0 | 0.0 | +| floor-other | 44.04 | 61.91 | +| floor-stone | 28.61 | 42.91 | +| floor-tile | 59.24 | 75.58 | +| floor-wood | 69.88 | 86.46 | +| flower | 14.95 | 35.59 | +| fog | 0.0 | 0.0 | +| food-other | 38.79 | 52.25 | +| fruit | 41.11 | 48.07 | +| furniture-other | 14.43 | 20.76 | +| grass | 72.22 | 83.68 | +| gravel | 26.28 | 29.9 | +| ground-other | 7.74 | 15.48 | +| hill | 20.79 | 29.03 | +| house | 27.79 | 40.36 | +| leaves | 17.11 | 18.69 | +| light | 40.91 | 55.35 | +| mat | 23.78 | 33.18 | +| metal | 13.62 | 16.42 | +| mirror-stuff | 44.74 | 60.17 | +| moss | 0.0 | 0.0 | +| mountain | 30.83 | 53.91 | +| mud | 7.59 | 14.5 | +| napkin | 42.01 | 47.07 | +| net | 24.25 | 27.96 | +| paper | 45.14 | 55.02 | +| pavement | 56.49 | 76.47 | +| pillow | 0.0 | 0.0 | +| plant-other | 29.07 | 42.32 | +| plastic | 19.43 | 23.28 | +| platform | 41.56 | 57.74 | +| playingfield | 69.82 | 82.85 | +| railing | 19.61 | 32.43 | +| railroad | 63.62 | 87.89 | +| river | 4.11 | 4.66 | +| road | 70.09 | 78.65 | +| rock | 51.36 | 71.34 | +| roof | 5.33 | 10.34 | +| rug | 53.8 | 77.93 | +| salad | 8.67 | 9.12 | +| sand | 75.76 | 86.42 | +| sea | 75.4 | 91.38 | +| shelf | 24.84 | 35.45 | +| sky-other | 60.75 | 75.74 | +| skyscraper | 6.77 | 9.8 | +| snow | 91.78 | 94.75 | +| solid-other | 0.0 | nan | +| stairs | 33.85 | 49.8 | +| stone | 6.32 | 10.67 | +| straw | 20.18 | 32.37 | +| structural-other | 17.37 | 23.35 | +| table | 18.51 | 25.09 | +| tent | 71.33 | 79.39 | +| textile-other | 19.45 | 22.72 | +| towel | 40.15 | 49.96 | +| tree | 77.88 | 89.2 | +| vegetable | 39.77 | 61.51 | +| wall-brick | 42.68 | 51.98 | +| wall-concrete | 18.32 | 23.04 | +| wall-other | 59.9 | 79.97 | +| wall-panel | 5.93 | 6.67 | +| wall-stone | 29.16 | 35.86 | +| wall-tile | 56.38 | 85.98 | +| wall-wood | 42.52 | 61.01 | +| water-other | 31.49 | 46.35 | +| waterdrops | nan | nan | +| window-blind | 20.78 | 36.79 | +| window-other | 47.0 | 63.62 | +| wood | 14.58 | 29.57 | ++------------------+-------+-------+ +2022-05-05 17:35:47,552 - mmseg - INFO - Summary: +2022-05-05 17:35:47,553 - mmseg - INFO - ++-------+------+-------+ +| aAcc | mIoU | mAcc | ++-------+------+-------+ +| 75.26 | 50.2 | 62.39 | ++-------+------+-------+ +2022-05-05 17:35:47,555 - mmseg - INFO - The previous best checkpoint /mnt/lustre/chenzhe.vendor/workspace/ViT-Adapter/segmentation/work_dirs/upernet_beit_adapter_large_512_80k_cocostuff10k_ss/best_mIoU_iter_32000.pth was removed +2022-05-05 17:36:07,475 - mmseg - INFO - Now best checkpoint is saved as best_mIoU_iter_48000.pth. +2022-05-05 17:36:07,486 - mmseg - INFO - Best mIoU is 0.5020 at 48000 iter. +2022-05-05 17:36:07,496 - mmseg - INFO - Exp name: upernet_beit_adapter_large_512_80k_cocostuff10k_ss.py +2022-05-05 17:36:07,497 - mmseg - INFO - Iter(val) [125] aAcc: 0.7526, mIoU: 0.5020, mAcc: 0.6239, IoU.person: 0.8791, IoU.bicycle: 0.7327, IoU.car: 0.6487, IoU.motorcycle: 0.8797, IoU.airplane: 0.8854, IoU.bus: 0.7930, IoU.train: 0.7383, IoU.truck: 0.7695, IoU.boat: 0.7180, IoU.traffic light: 0.7383, IoU.fire hydrant: 0.8310, IoU.stop sign: 0.9061, IoU.parking meter: 0.7536, IoU.bench: 0.4892, IoU.bird: 0.7605, IoU.cat: 0.9279, IoU.dog: 0.9088, IoU.horse: 0.8905, IoU.sheep: 0.8840, IoU.cow: 0.9411, IoU.elephant: 0.9206, IoU.bear: 0.8716, IoU.zebra: 0.9074, IoU.giraffe: 0.8640, IoU.backpack: 0.2202, IoU.umbrella: 0.7739, IoU.handbag: 0.1673, IoU.tie: 0.5340, IoU.suitcase: 0.7689, IoU.frisbee: 0.9383, IoU.skis: 0.4198, IoU.snowboard: 0.6496, IoU.sports ball: 0.8352, IoU.kite: 0.6715, IoU.baseball bat: 0.4981, IoU.baseball glove: 0.0869, IoU.skateboard: 0.6665, IoU.surfboard: 0.8952, IoU.tennis racket: 0.5954, IoU.bottle: 0.7370, IoU.wine glass: 0.8397, IoU.cup: 0.6998, IoU.fork: 0.5165, IoU.knife: 0.7705, IoU.spoon: 0.4698, IoU.bowl: 0.5634, IoU.banana: 0.7889, IoU.apple: 0.7114, IoU.sandwich: 0.8586, IoU.orange: 0.6936, IoU.broccoli: 0.9173, IoU.carrot: 0.4098, IoU.hot dog: 0.5294, IoU.pizza: 0.9473, IoU.donut: 0.6701, IoU.cake: 0.6406, IoU.chair: 0.5780, IoU.couch: 0.7495, IoU.potted plant: 0.3757, IoU.bed: 0.7333, IoU.dining table: 0.6031, IoU.toilet: 0.8698, IoU.tv: 0.6879, IoU.laptop: 0.8724, IoU.mouse: 0.7019, IoU.remote: 0.6850, IoU.keyboard: 0.8448, IoU.cell phone: 0.8146, IoU.microwave: 0.4281, IoU.oven: 0.6232, IoU.toaster: 0.2956, IoU.sink: 0.7084, IoU.refrigerator: 0.8077, IoU.book: 0.7889, IoU.clock: 0.7610, IoU.vase: 0.6451, IoU.scissors: 0.7708, IoU.teddy bear: 0.8397, IoU.hair drier: 0.0000, IoU.toothbrush: 0.1434, IoU.banner: 0.2175, IoU.blanket: 0.1348, IoU.branch: 0.0474, IoU.bridge: 0.0258, IoU.building-other: 0.5431, IoU.bush: 0.2646, IoU.cabinet: 0.1674, IoU.cage: 0.0352, IoU.cardboard: 0.2326, IoU.carpet: 0.5693, IoU.ceiling-other: 0.6986, IoU.ceiling-tile: 0.1208, IoU.cloth: 0.0516, IoU.clothes: 0.2009, IoU.clouds: 0.5185, IoU.counter: 0.3433, IoU.cupboard: 0.5459, IoU.curtain: 0.6400, IoU.desk-stuff: 0.3585, IoU.dirt: 0.3340, IoU.door-stuff: 0.4555, IoU.fence: 0.4134, IoU.floor-marble: 0.0000, IoU.floor-other: 0.4404, IoU.floor-stone: 0.2861, IoU.floor-tile: 0.5924, IoU.floor-wood: 0.6988, IoU.flower: 0.1495, IoU.fog: 0.0000, IoU.food-other: 0.3879, IoU.fruit: 0.4111, IoU.furniture-other: 0.1443, IoU.grass: 0.7222, IoU.gravel: 0.2628, IoU.ground-other: 0.0774, IoU.hill: 0.2079, IoU.house: 0.2779, IoU.leaves: 0.1711, IoU.light: 0.4091, IoU.mat: 0.2378, IoU.metal: 0.1362, IoU.mirror-stuff: 0.4474, IoU.moss: 0.0000, IoU.mountain: 0.3083, IoU.mud: 0.0759, IoU.napkin: 0.4201, IoU.net: 0.2425, IoU.paper: 0.4514, IoU.pavement: 0.5649, IoU.pillow: 0.0000, IoU.plant-other: 0.2907, IoU.plastic: 0.1943, IoU.platform: 0.4156, IoU.playingfield: 0.6982, IoU.railing: 0.1961, IoU.railroad: 0.6362, IoU.river: 0.0411, IoU.road: 0.7009, IoU.rock: 0.5136, IoU.roof: 0.0533, IoU.rug: 0.5380, IoU.salad: 0.0867, IoU.sand: 0.7576, IoU.sea: 0.7540, IoU.shelf: 0.2484, IoU.sky-other: 0.6075, IoU.skyscraper: 0.0677, IoU.snow: 0.9178, IoU.solid-other: 0.0000, IoU.stairs: 0.3385, IoU.stone: 0.0632, IoU.straw: 0.2018, IoU.structural-other: 0.1737, IoU.table: 0.1851, IoU.tent: 0.7133, IoU.textile-other: 0.1945, IoU.towel: 0.4015, IoU.tree: 0.7788, IoU.vegetable: 0.3977, IoU.wall-brick: 0.4268, IoU.wall-concrete: 0.1832, IoU.wall-other: 0.5990, IoU.wall-panel: 0.0593, IoU.wall-stone: 0.2916, IoU.wall-tile: 0.5638, IoU.wall-wood: 0.4252, IoU.water-other: 0.3149, IoU.waterdrops: nan, IoU.window-blind: 0.2078, IoU.window-other: 0.4700, IoU.wood: 0.1458, Acc.person: 0.9490, Acc.bicycle: 0.9264, Acc.car: 0.7295, Acc.motorcycle: 0.9559, Acc.airplane: 0.9615, Acc.bus: 0.8581, Acc.train: 0.9791, Acc.truck: 0.8887, Acc.boat: 0.8913, Acc.traffic light: 0.9173, Acc.fire hydrant: 0.9836, Acc.stop sign: 0.9806, Acc.parking meter: 0.7882, Acc.bench: 0.7294, Acc.bird: 0.8462, Acc.cat: 0.9740, Acc.dog: 0.9702, Acc.horse: 0.9636, Acc.sheep: 0.9293, Acc.cow: 0.9871, Acc.elephant: 0.9630, Acc.bear: 0.9591, Acc.zebra: 0.9661, Acc.giraffe: 0.9429, Acc.backpack: 0.5476, Acc.umbrella: 0.8616, Acc.handbag: 0.2243, Acc.tie: 0.5340, Acc.suitcase: 0.9628, Acc.frisbee: 0.9693, Acc.skis: 0.6762, Acc.snowboard: 0.7455, Acc.sports ball: 0.9177, Acc.kite: 0.9177, Acc.baseball bat: 0.6639, Acc.baseball glove: 0.0885, Acc.skateboard: 0.8923, Acc.surfboard: 0.9596, Acc.tennis racket: 0.6164, Acc.bottle: 0.8392, Acc.wine glass: 0.9239, Acc.cup: 0.9047, Acc.fork: 0.6319, Acc.knife: 0.8584, Acc.spoon: 0.6540, Acc.bowl: 0.6897, Acc.banana: 0.9026, Acc.apple: 0.8884, Acc.sandwich: 0.9742, Acc.orange: 0.9241, Acc.broccoli: 0.9603, Acc.carrot: 0.7474, Acc.hot dog: 0.9699, Acc.pizza: 0.9706, Acc.donut: 0.9045, Acc.cake: 0.7514, Acc.chair: 0.7655, Acc.couch: 0.9375, Acc.potted plant: 0.4806, Acc.bed: 0.8364, Acc.dining table: 0.7939, Acc.toilet: 0.9737, Acc.tv: 0.9147, Acc.laptop: 0.9857, Acc.mouse: 0.7634, Acc.remote: 0.9364, Acc.keyboard: 0.9802, Acc.cell phone: 0.9689, Acc.microwave: 0.7462, Acc.oven: 0.8579, Acc.toaster: 0.2956, Acc.sink: 0.7872, Acc.refrigerator: 0.8843, Acc.book: 0.8772, Acc.clock: 0.8725, Acc.vase: 0.9431, Acc.scissors: 0.9432, Acc.teddy bear: 0.9491, Acc.hair drier: 0.0000, Acc.toothbrush: 0.2645, Acc.banner: 0.3666, Acc.blanket: 0.1452, Acc.branch: 0.0474, Acc.bridge: 0.0339, Acc.building-other: 0.7594, Acc.bush: 0.3433, Acc.cabinet: 0.3066, Acc.cage: 0.1039, Acc.cardboard: 0.2988, Acc.carpet: 0.7360, Acc.ceiling-other: 0.8375, Acc.ceiling-tile: 0.1365, Acc.cloth: 0.0697, Acc.clothes: 0.3145, Acc.clouds: 0.6720, Acc.counter: 0.4135, Acc.cupboard: 0.7575, Acc.curtain: 0.7814, Acc.desk-stuff: 0.4344, Acc.dirt: 0.5446, Acc.door-stuff: 0.5685, Acc.fence: 0.7127, Acc.floor-marble: 0.0000, Acc.floor-other: 0.6191, Acc.floor-stone: 0.4291, Acc.floor-tile: 0.7558, Acc.floor-wood: 0.8646, Acc.flower: 0.3559, Acc.fog: 0.0000, Acc.food-other: 0.5225, Acc.fruit: 0.4807, Acc.furniture-other: 0.2076, Acc.grass: 0.8368, Acc.gravel: 0.2990, Acc.ground-other: 0.1548, Acc.hill: 0.2903, Acc.house: 0.4036, Acc.leaves: 0.1869, Acc.light: 0.5535, Acc.mat: 0.3318, Acc.metal: 0.1642, Acc.mirror-stuff: 0.6017, Acc.moss: 0.0000, Acc.mountain: 0.5391, Acc.mud: 0.1450, Acc.napkin: 0.4707, Acc.net: 0.2796, Acc.paper: 0.5502, Acc.pavement: 0.7647, Acc.pillow: 0.0000, Acc.plant-other: 0.4232, Acc.plastic: 0.2328, Acc.platform: 0.5774, Acc.playingfield: 0.8285, Acc.railing: 0.3243, Acc.railroad: 0.8789, Acc.river: 0.0466, Acc.road: 0.7865, Acc.rock: 0.7134, Acc.roof: 0.1034, Acc.rug: 0.7793, Acc.salad: 0.0912, Acc.sand: 0.8642, Acc.sea: 0.9138, Acc.shelf: 0.3545, Acc.sky-other: 0.7574, Acc.skyscraper: 0.0980, Acc.snow: 0.9475, Acc.solid-other: nan, Acc.stairs: 0.4980, Acc.stone: 0.1067, Acc.straw: 0.3237, Acc.structural-other: 0.2335, Acc.table: 0.2509, Acc.tent: 0.7939, Acc.textile-other: 0.2272, Acc.towel: 0.4996, Acc.tree: 0.8920, Acc.vegetable: 0.6151, Acc.wall-brick: 0.5198, Acc.wall-concrete: 0.2304, Acc.wall-other: 0.7997, Acc.wall-panel: 0.0667, Acc.wall-stone: 0.3586, Acc.wall-tile: 0.8598, Acc.wall-wood: 0.6101, Acc.water-other: 0.4635, Acc.waterdrops: nan, Acc.window-blind: 0.3679, Acc.window-other: 0.6362, Acc.wood: 0.2957 +2022-05-05 17:36:37,801 - mmseg - INFO - Iter [48050/80000] lr: 5.734e-07, eta: 5:33:38, time: 1.612, data_time: 1.014, memory: 60248, decode.loss_ce: 0.1477, decode.acc_seg: 75.8157, aux.loss_ce: 0.0960, aux.acc_seg: 73.8526, loss: 0.2437 +2022-05-05 17:37:07,231 - mmseg - INFO - Iter [48100/80000] lr: 5.725e-07, eta: 5:33:06, time: 0.589, data_time: 0.005, memory: 60248, decode.loss_ce: 0.1439, decode.acc_seg: 76.1212, aux.loss_ce: 0.0926, aux.acc_seg: 74.2142, loss: 0.2366 +2022-05-05 17:37:36,745 - mmseg - INFO - Iter [48150/80000] lr: 5.716e-07, eta: 5:32:33, time: 0.590, data_time: 0.004, memory: 60248, decode.loss_ce: 0.1551, decode.acc_seg: 75.1745, aux.loss_ce: 0.0986, aux.acc_seg: 73.1560, loss: 0.2536 +2022-05-05 17:38:06,086 - mmseg - INFO - Iter [48200/80000] lr: 5.707e-07, eta: 5:32:00, time: 0.587, data_time: 0.005, memory: 60248, decode.loss_ce: 0.1412, decode.acc_seg: 76.1987, aux.loss_ce: 0.0911, aux.acc_seg: 74.3525, loss: 0.2324 +2022-05-05 17:38:35,563 - mmseg - INFO - Iter [48250/80000] lr: 5.698e-07, eta: 5:31:28, time: 0.589, data_time: 0.005, memory: 60248, decode.loss_ce: 0.1512, decode.acc_seg: 76.9518, aux.loss_ce: 0.0975, aux.acc_seg: 75.0028, loss: 0.2487 +2022-05-05 17:39:04,862 - mmseg - INFO - Iter [48300/80000] lr: 5.690e-07, eta: 5:30:55, time: 0.586, data_time: 0.004, memory: 60248, decode.loss_ce: 0.1626, decode.acc_seg: 75.9421, aux.loss_ce: 0.1032, aux.acc_seg: 73.8890, loss: 0.2658 +2022-05-05 17:39:37,054 - mmseg - INFO - Iter [48350/80000] lr: 5.681e-07, eta: 5:30:24, time: 0.643, data_time: 0.055, memory: 60248, decode.loss_ce: 0.1459, decode.acc_seg: 74.4168, aux.loss_ce: 0.0941, aux.acc_seg: 72.4615, loss: 0.2400 +2022-05-05 17:40:06,919 - mmseg - INFO - Iter [48400/80000] lr: 5.672e-07, eta: 5:29:52, time: 0.597, data_time: 0.005, memory: 60248, decode.loss_ce: 0.1530, decode.acc_seg: 74.7420, aux.loss_ce: 0.0969, aux.acc_seg: 72.7252, loss: 0.2499 +2022-05-05 17:40:36,378 - mmseg - INFO - Iter [48450/80000] lr: 5.663e-07, eta: 5:29:20, time: 0.589, data_time: 0.005, memory: 60248, decode.loss_ce: 0.1463, decode.acc_seg: 74.7398, aux.loss_ce: 0.0959, aux.acc_seg: 72.5879, loss: 0.2421 +2022-05-05 17:41:06,155 - mmseg - INFO - Iter [48500/80000] lr: 5.654e-07, eta: 5:28:47, time: 0.595, data_time: 0.005, memory: 60248, decode.loss_ce: 0.1531, decode.acc_seg: 75.9969, aux.loss_ce: 0.0977, aux.acc_seg: 74.0081, loss: 0.2508 +2022-05-05 17:41:35,655 - mmseg - INFO - Iter [48550/80000] lr: 5.645e-07, eta: 5:28:15, time: 0.590, data_time: 0.006, memory: 60248, decode.loss_ce: 0.1477, decode.acc_seg: 77.0659, aux.loss_ce: 0.0975, aux.acc_seg: 75.0509, loss: 0.2452 +2022-05-05 17:42:05,299 - mmseg - INFO - Iter [48600/80000] lr: 5.636e-07, eta: 5:27:42, time: 0.593, data_time: 0.004, memory: 60248, decode.loss_ce: 0.1456, decode.acc_seg: 75.8220, aux.loss_ce: 0.0911, aux.acc_seg: 74.1141, loss: 0.2367 +2022-05-05 17:42:34,904 - mmseg - INFO - Iter [48650/80000] lr: 5.627e-07, eta: 5:27:10, time: 0.592, data_time: 0.004, memory: 60248, decode.loss_ce: 0.1552, decode.acc_seg: 75.1363, aux.loss_ce: 0.0983, aux.acc_seg: 73.2284, loss: 0.2535 +2022-05-05 17:43:04,316 - mmseg - INFO - Iter [48700/80000] lr: 5.618e-07, eta: 5:26:37, time: 0.588, data_time: 0.005, memory: 60248, decode.loss_ce: 0.1479, decode.acc_seg: 76.1397, aux.loss_ce: 0.0978, aux.acc_seg: 73.9820, loss: 0.2456 +2022-05-05 17:43:34,049 - mmseg - INFO - Iter [48750/80000] lr: 5.609e-07, eta: 5:26:05, time: 0.594, data_time: 0.004, memory: 60248, decode.loss_ce: 0.1486, decode.acc_seg: 74.9931, aux.loss_ce: 0.0962, aux.acc_seg: 72.8983, loss: 0.2447 +2022-05-05 17:44:03,478 - mmseg - INFO - Iter [48800/80000] lr: 5.600e-07, eta: 5:25:33, time: 0.588, data_time: 0.005, memory: 60248, decode.loss_ce: 0.1503, decode.acc_seg: 75.5822, aux.loss_ce: 0.0966, aux.acc_seg: 73.6173, loss: 0.2469 +2022-05-05 17:44:33,222 - mmseg - INFO - Iter [48850/80000] lr: 5.591e-07, eta: 5:25:00, time: 0.595, data_time: 0.005, memory: 60248, decode.loss_ce: 0.1469, decode.acc_seg: 76.0347, aux.loss_ce: 0.0964, aux.acc_seg: 73.9450, loss: 0.2433 +2022-05-05 17:45:05,445 - mmseg - INFO - Iter [48900/80000] lr: 5.582e-07, eta: 5:24:30, time: 0.645, data_time: 0.056, memory: 60248, decode.loss_ce: 0.1524, decode.acc_seg: 75.4777, aux.loss_ce: 0.0980, aux.acc_seg: 73.5299, loss: 0.2504 +2022-05-05 17:45:34,846 - mmseg - INFO - Iter [48950/80000] lr: 5.573e-07, eta: 5:23:57, time: 0.588, data_time: 0.004, memory: 60248, decode.loss_ce: 0.1506, decode.acc_seg: 76.1383, aux.loss_ce: 0.0996, aux.acc_seg: 74.1126, loss: 0.2502 +2022-05-05 17:46:04,714 - mmseg - INFO - Saving checkpoint at 49000 iterations +2022-05-05 17:46:25,524 - mmseg - INFO - Exp name: upernet_beit_adapter_large_512_80k_cocostuff10k_ss.py +2022-05-05 17:46:25,526 - mmseg - INFO - Iter [49000/80000] lr: 5.564e-07, eta: 5:23:38, time: 1.011, data_time: 0.005, memory: 60248, decode.loss_ce: 0.1449, decode.acc_seg: 75.1328, aux.loss_ce: 0.0930, aux.acc_seg: 73.2896, loss: 0.2379 +2022-05-05 17:46:55,442 - mmseg - INFO - Iter [49050/80000] lr: 5.555e-07, eta: 5:23:06, time: 0.599, data_time: 0.007, memory: 60248, decode.loss_ce: 0.1525, decode.acc_seg: 76.4256, aux.loss_ce: 0.0991, aux.acc_seg: 74.4919, loss: 0.2515 +2022-05-05 17:47:24,938 - mmseg - INFO - Iter [49100/80000] lr: 5.546e-07, eta: 5:22:33, time: 0.592, data_time: 0.006, memory: 60248, decode.loss_ce: 0.1459, decode.acc_seg: 75.7282, aux.loss_ce: 0.0925, aux.acc_seg: 73.9700, loss: 0.2383 +2022-05-05 17:47:54,658 - mmseg - INFO - Iter [49150/80000] lr: 5.537e-07, eta: 5:22:01, time: 0.594, data_time: 0.005, memory: 60248, decode.loss_ce: 0.1544, decode.acc_seg: 75.7098, aux.loss_ce: 0.1004, aux.acc_seg: 73.7321, loss: 0.2548 +2022-05-05 17:48:24,392 - mmseg - INFO - Iter [49200/80000] lr: 5.528e-07, eta: 5:21:29, time: 0.595, data_time: 0.004, memory: 60248, decode.loss_ce: 0.1538, decode.acc_seg: 74.7925, aux.loss_ce: 0.0981, aux.acc_seg: 72.8367, loss: 0.2520 +2022-05-05 17:48:54,308 - mmseg - INFO - Iter [49250/80000] lr: 5.519e-07, eta: 5:20:57, time: 0.598, data_time: 0.004, memory: 60248, decode.loss_ce: 0.1434, decode.acc_seg: 76.7486, aux.loss_ce: 0.0937, aux.acc_seg: 74.6685, loss: 0.2371 +2022-05-05 17:49:24,314 - mmseg - INFO - Iter [49300/80000] lr: 5.510e-07, eta: 5:20:24, time: 0.600, data_time: 0.007, memory: 60248, decode.loss_ce: 0.1368, decode.acc_seg: 75.4303, aux.loss_ce: 0.0889, aux.acc_seg: 73.6599, loss: 0.2257 +2022-05-05 17:49:54,088 - mmseg - INFO - Iter [49350/80000] lr: 5.501e-07, eta: 5:19:52, time: 0.596, data_time: 0.005, memory: 60248, decode.loss_ce: 0.1485, decode.acc_seg: 76.8284, aux.loss_ce: 0.0915, aux.acc_seg: 75.0939, loss: 0.2400 +2022-05-05 17:50:23,712 - mmseg - INFO - Iter [49400/80000] lr: 5.492e-07, eta: 5:19:20, time: 0.593, data_time: 0.006, memory: 60248, decode.loss_ce: 0.1533, decode.acc_seg: 75.4886, aux.loss_ce: 0.0972, aux.acc_seg: 73.5361, loss: 0.2505 +2022-05-05 17:50:53,280 - mmseg - INFO - Iter [49450/80000] lr: 5.483e-07, eta: 5:18:47, time: 0.591, data_time: 0.005, memory: 60248, decode.loss_ce: 0.1424, decode.acc_seg: 75.2790, aux.loss_ce: 0.0962, aux.acc_seg: 73.0825, loss: 0.2386 +2022-05-05 17:51:25,406 - mmseg - INFO - Iter [49500/80000] lr: 5.474e-07, eta: 5:18:17, time: 0.642, data_time: 0.056, memory: 60248, decode.loss_ce: 0.1464, decode.acc_seg: 75.4063, aux.loss_ce: 0.0922, aux.acc_seg: 73.6582, loss: 0.2386 +2022-05-05 17:51:55,177 - mmseg - INFO - Iter [49550/80000] lr: 5.465e-07, eta: 5:17:44, time: 0.596, data_time: 0.005, memory: 60248, decode.loss_ce: 0.1478, decode.acc_seg: 76.5160, aux.loss_ce: 0.0959, aux.acc_seg: 74.4395, loss: 0.2437 +2022-05-05 17:52:24,962 - mmseg - INFO - Iter [49600/80000] lr: 5.456e-07, eta: 5:17:12, time: 0.596, data_time: 0.004, memory: 60248, decode.loss_ce: 0.1565, decode.acc_seg: 74.0135, aux.loss_ce: 0.0959, aux.acc_seg: 72.1530, loss: 0.2524 +2022-05-05 17:52:54,647 - mmseg - INFO - Iter [49650/80000] lr: 5.447e-07, eta: 5:16:40, time: 0.594, data_time: 0.005, memory: 60248, decode.loss_ce: 0.1492, decode.acc_seg: 74.6126, aux.loss_ce: 0.0967, aux.acc_seg: 72.5813, loss: 0.2459 +2022-05-05 17:53:24,029 - mmseg - INFO - Iter [49700/80000] lr: 5.438e-07, eta: 5:16:07, time: 0.588, data_time: 0.004, memory: 60248, decode.loss_ce: 0.1432, decode.acc_seg: 74.9874, aux.loss_ce: 0.0936, aux.acc_seg: 72.9779, loss: 0.2368 +2022-05-05 17:53:53,766 - mmseg - INFO - Iter [49750/80000] lr: 5.429e-07, eta: 5:15:35, time: 0.595, data_time: 0.004, memory: 60248, decode.loss_ce: 0.1502, decode.acc_seg: 76.5394, aux.loss_ce: 0.0959, aux.acc_seg: 74.5259, loss: 0.2461 +2022-05-05 17:54:23,400 - mmseg - INFO - Iter [49800/80000] lr: 5.420e-07, eta: 5:15:03, time: 0.593, data_time: 0.004, memory: 60248, decode.loss_ce: 0.1418, decode.acc_seg: 74.8489, aux.loss_ce: 0.0914, aux.acc_seg: 72.9740, loss: 0.2332 +2022-05-05 17:54:52,929 - mmseg - INFO - Iter [49850/80000] lr: 5.411e-07, eta: 5:14:31, time: 0.591, data_time: 0.005, memory: 60248, decode.loss_ce: 0.1521, decode.acc_seg: 75.9672, aux.loss_ce: 0.0984, aux.acc_seg: 73.9117, loss: 0.2505 +2022-05-05 17:55:22,468 - mmseg - INFO - Iter [49900/80000] lr: 5.402e-07, eta: 5:13:58, time: 0.591, data_time: 0.004, memory: 60248, decode.loss_ce: 0.1519, decode.acc_seg: 76.2611, aux.loss_ce: 0.0980, aux.acc_seg: 74.3103, loss: 0.2500 +2022-05-05 17:55:51,886 - mmseg - INFO - Iter [49950/80000] lr: 5.393e-07, eta: 5:13:26, time: 0.588, data_time: 0.004, memory: 60248, decode.loss_ce: 0.1492, decode.acc_seg: 75.7298, aux.loss_ce: 0.0961, aux.acc_seg: 73.8018, loss: 0.2453 +2022-05-05 17:56:21,307 - mmseg - INFO - Saving checkpoint at 50000 iterations +2022-05-05 17:56:41,684 - mmseg - INFO - Exp name: upernet_beit_adapter_large_512_80k_cocostuff10k_ss.py +2022-05-05 17:56:41,686 - mmseg - INFO - Iter [50000/80000] lr: 5.384e-07, eta: 5:13:05, time: 0.995, data_time: 0.004, memory: 60248, decode.loss_ce: 0.1440, decode.acc_seg: 76.7121, aux.loss_ce: 0.0913, aux.acc_seg: 75.0291, loss: 0.2354 +2022-05-05 17:57:14,109 - mmseg - INFO - Iter [50050/80000] lr: 5.375e-07, eta: 5:12:35, time: 0.648, data_time: 0.054, memory: 60248, decode.loss_ce: 0.1467, decode.acc_seg: 75.3314, aux.loss_ce: 0.0961, aux.acc_seg: 73.2659, loss: 0.2427 +2022-05-05 17:57:43,906 - mmseg - INFO - Iter [50100/80000] lr: 5.366e-07, eta: 5:12:03, time: 0.598, data_time: 0.006, memory: 60248, decode.loss_ce: 0.1379, decode.acc_seg: 75.6575, aux.loss_ce: 0.0896, aux.acc_seg: 73.7410, loss: 0.2275 +2022-05-05 17:58:13,362 - mmseg - INFO - Iter [50150/80000] lr: 5.357e-07, eta: 5:11:30, time: 0.589, data_time: 0.004, memory: 60248, decode.loss_ce: 0.1476, decode.acc_seg: 75.0351, aux.loss_ce: 0.0939, aux.acc_seg: 73.2325, loss: 0.2415 +2022-05-05 17:58:43,059 - mmseg - INFO - Iter [50200/80000] lr: 5.349e-07, eta: 5:10:58, time: 0.594, data_time: 0.004, memory: 60248, decode.loss_ce: 0.1406, decode.acc_seg: 75.6495, aux.loss_ce: 0.0915, aux.acc_seg: 73.7760, loss: 0.2321 +2022-05-05 17:59:12,757 - mmseg - INFO - Iter [50250/80000] lr: 5.340e-07, eta: 5:10:26, time: 0.594, data_time: 0.005, memory: 60248, decode.loss_ce: 0.1469, decode.acc_seg: 75.8879, aux.loss_ce: 0.0966, aux.acc_seg: 73.6921, loss: 0.2435 +2022-05-05 17:59:42,328 - mmseg - INFO - Iter [50300/80000] lr: 5.331e-07, eta: 5:09:53, time: 0.591, data_time: 0.005, memory: 60248, decode.loss_ce: 0.1401, decode.acc_seg: 76.1635, aux.loss_ce: 0.0915, aux.acc_seg: 74.1666, loss: 0.2316 +2022-05-05 18:00:13,433 - mmseg - INFO - Iter [50350/80000] lr: 5.322e-07, eta: 5:09:22, time: 0.620, data_time: 0.005, memory: 60248, decode.loss_ce: 0.1406, decode.acc_seg: 77.0438, aux.loss_ce: 0.0905, aux.acc_seg: 75.1853, loss: 0.2311 +2022-05-05 18:00:42,889 - mmseg - INFO - Iter [50400/80000] lr: 5.313e-07, eta: 5:08:50, time: 0.591, data_time: 0.007, memory: 60248, decode.loss_ce: 0.1462, decode.acc_seg: 74.7675, aux.loss_ce: 0.0954, aux.acc_seg: 72.7512, loss: 0.2416 +2022-05-05 18:01:12,254 - mmseg - INFO - Iter [50450/80000] lr: 5.304e-07, eta: 5:08:17, time: 0.587, data_time: 0.005, memory: 60248, decode.loss_ce: 0.1452, decode.acc_seg: 76.9249, aux.loss_ce: 0.0954, aux.acc_seg: 74.8001, loss: 0.2406 +2022-05-05 18:01:41,986 - mmseg - INFO - Iter [50500/80000] lr: 5.295e-07, eta: 5:07:45, time: 0.595, data_time: 0.005, memory: 60248, decode.loss_ce: 0.1534, decode.acc_seg: 75.8748, aux.loss_ce: 0.0966, aux.acc_seg: 73.9810, loss: 0.2501 +2022-05-05 18:02:11,815 - mmseg - INFO - Iter [50550/80000] lr: 5.286e-07, eta: 5:07:13, time: 0.596, data_time: 0.005, memory: 60248, decode.loss_ce: 0.1454, decode.acc_seg: 76.4866, aux.loss_ce: 0.0936, aux.acc_seg: 74.5358, loss: 0.2389 +2022-05-05 18:02:43,864 - mmseg - INFO - Iter [50600/80000] lr: 5.277e-07, eta: 5:06:42, time: 0.641, data_time: 0.054, memory: 60248, decode.loss_ce: 0.1429, decode.acc_seg: 74.6717, aux.loss_ce: 0.0896, aux.acc_seg: 73.0660, loss: 0.2325 +2022-05-05 18:03:13,366 - mmseg - INFO - Iter [50650/80000] lr: 5.268e-07, eta: 5:06:10, time: 0.590, data_time: 0.005, memory: 60248, decode.loss_ce: 0.1575, decode.acc_seg: 75.5520, aux.loss_ce: 0.1019, aux.acc_seg: 73.4551, loss: 0.2593 +2022-05-05 18:03:42,629 - mmseg - INFO - Iter [50700/80000] lr: 5.259e-07, eta: 5:05:37, time: 0.585, data_time: 0.004, memory: 60248, decode.loss_ce: 0.1393, decode.acc_seg: 75.8510, aux.loss_ce: 0.0929, aux.acc_seg: 73.7722, loss: 0.2322 +2022-05-05 18:04:12,223 - mmseg - INFO - Iter [50750/80000] lr: 5.250e-07, eta: 5:05:05, time: 0.592, data_time: 0.004, memory: 60248, decode.loss_ce: 0.1382, decode.acc_seg: 76.2081, aux.loss_ce: 0.0885, aux.acc_seg: 74.3426, loss: 0.2267 +2022-05-05 18:04:41,959 - mmseg - INFO - Iter [50800/80000] lr: 5.241e-07, eta: 5:04:33, time: 0.594, data_time: 0.004, memory: 60248, decode.loss_ce: 0.1580, decode.acc_seg: 76.8087, aux.loss_ce: 0.1009, aux.acc_seg: 74.7902, loss: 0.2589 +2022-05-05 18:05:11,438 - mmseg - INFO - Iter [50850/80000] lr: 5.232e-07, eta: 5:04:00, time: 0.590, data_time: 0.005, memory: 60248, decode.loss_ce: 0.1515, decode.acc_seg: 75.3804, aux.loss_ce: 0.0975, aux.acc_seg: 73.2866, loss: 0.2490 +2022-05-05 18:05:41,139 - mmseg - INFO - Iter [50900/80000] lr: 5.223e-07, eta: 5:03:28, time: 0.594, data_time: 0.005, memory: 60248, decode.loss_ce: 0.1406, decode.acc_seg: 75.6378, aux.loss_ce: 0.0887, aux.acc_seg: 74.0245, loss: 0.2293 +2022-05-05 18:06:10,633 - mmseg - INFO - Iter [50950/80000] lr: 5.214e-07, eta: 5:02:56, time: 0.590, data_time: 0.004, memory: 60248, decode.loss_ce: 0.1610, decode.acc_seg: 75.6859, aux.loss_ce: 0.1035, aux.acc_seg: 73.5769, loss: 0.2645 +2022-05-05 18:06:40,179 - mmseg - INFO - Saving checkpoint at 51000 iterations +2022-05-05 18:07:01,757 - mmseg - INFO - Exp name: upernet_beit_adapter_large_512_80k_cocostuff10k_ss.py +2022-05-05 18:07:01,759 - mmseg - INFO - Iter [51000/80000] lr: 5.205e-07, eta: 5:02:36, time: 1.020, data_time: 0.004, memory: 60248, decode.loss_ce: 0.1456, decode.acc_seg: 75.6380, aux.loss_ce: 0.0937, aux.acc_seg: 73.6484, loss: 0.2394 +2022-05-05 18:07:31,636 - mmseg - INFO - Iter [51050/80000] lr: 5.196e-07, eta: 5:02:04, time: 0.598, data_time: 0.007, memory: 60248, decode.loss_ce: 0.1532, decode.acc_seg: 75.7102, aux.loss_ce: 0.0993, aux.acc_seg: 73.5908, loss: 0.2525 +2022-05-05 18:08:01,581 - mmseg - INFO - Iter [51100/80000] lr: 5.187e-07, eta: 5:01:32, time: 0.601, data_time: 0.006, memory: 60248, decode.loss_ce: 0.1463, decode.acc_seg: 76.1508, aux.loss_ce: 0.0949, aux.acc_seg: 74.2482, loss: 0.2412 +2022-05-05 18:08:33,933 - mmseg - INFO - Iter [51150/80000] lr: 5.178e-07, eta: 5:01:01, time: 0.647, data_time: 0.056, memory: 60248, decode.loss_ce: 0.1578, decode.acc_seg: 75.1648, aux.loss_ce: 0.0997, aux.acc_seg: 73.1635, loss: 0.2575 +2022-05-05 18:09:03,679 - mmseg - INFO - Iter [51200/80000] lr: 5.169e-07, eta: 5:00:29, time: 0.595, data_time: 0.004, memory: 60248, decode.loss_ce: 0.1463, decode.acc_seg: 75.5110, aux.loss_ce: 0.0927, aux.acc_seg: 73.6929, loss: 0.2390 +2022-05-05 18:09:33,822 - mmseg - INFO - Iter [51250/80000] lr: 5.160e-07, eta: 4:59:57, time: 0.603, data_time: 0.005, memory: 60248, decode.loss_ce: 0.1482, decode.acc_seg: 75.7453, aux.loss_ce: 0.0943, aux.acc_seg: 73.7403, loss: 0.2424 +2022-05-05 18:10:03,273 - mmseg - INFO - Iter [51300/80000] lr: 5.151e-07, eta: 4:59:24, time: 0.589, data_time: 0.005, memory: 60248, decode.loss_ce: 0.1495, decode.acc_seg: 76.2029, aux.loss_ce: 0.0950, aux.acc_seg: 74.3175, loss: 0.2444 +2022-05-05 18:10:32,815 - mmseg - INFO - Iter [51350/80000] lr: 5.142e-07, eta: 4:58:52, time: 0.591, data_time: 0.005, memory: 60248, decode.loss_ce: 0.1508, decode.acc_seg: 76.2736, aux.loss_ce: 0.0942, aux.acc_seg: 74.5187, loss: 0.2450 +2022-05-05 18:11:02,315 - mmseg - INFO - Iter [51400/80000] lr: 5.133e-07, eta: 4:58:20, time: 0.589, data_time: 0.005, memory: 60248, decode.loss_ce: 0.1573, decode.acc_seg: 75.6365, aux.loss_ce: 0.0984, aux.acc_seg: 73.8181, loss: 0.2557 +2022-05-05 18:11:32,142 - mmseg - INFO - Iter [51450/80000] lr: 5.124e-07, eta: 4:57:48, time: 0.597, data_time: 0.007, memory: 60248, decode.loss_ce: 0.1527, decode.acc_seg: 75.7940, aux.loss_ce: 0.0971, aux.acc_seg: 73.8577, loss: 0.2498 +2022-05-05 18:12:01,707 - mmseg - INFO - Iter [51500/80000] lr: 5.115e-07, eta: 4:57:16, time: 0.591, data_time: 0.004, memory: 60248, decode.loss_ce: 0.1434, decode.acc_seg: 76.8602, aux.loss_ce: 0.0923, aux.acc_seg: 75.0376, loss: 0.2358 +2022-05-05 18:12:31,123 - mmseg - INFO - Iter [51550/80000] lr: 5.106e-07, eta: 4:56:43, time: 0.588, data_time: 0.005, memory: 60248, decode.loss_ce: 0.1413, decode.acc_seg: 75.6484, aux.loss_ce: 0.0885, aux.acc_seg: 74.0005, loss: 0.2297 +2022-05-05 18:13:00,574 - mmseg - INFO - Iter [51600/80000] lr: 5.097e-07, eta: 4:56:11, time: 0.589, data_time: 0.004, memory: 60248, decode.loss_ce: 0.1334, decode.acc_seg: 75.1284, aux.loss_ce: 0.0877, aux.acc_seg: 73.2017, loss: 0.2211 +2022-05-05 18:13:30,147 - mmseg - INFO - Iter [51650/80000] lr: 5.088e-07, eta: 4:55:39, time: 0.592, data_time: 0.005, memory: 60248, decode.loss_ce: 0.1470, decode.acc_seg: 75.1582, aux.loss_ce: 0.0959, aux.acc_seg: 72.9627, loss: 0.2430 +2022-05-05 18:13:59,537 - mmseg - INFO - Iter [51700/80000] lr: 5.079e-07, eta: 4:55:06, time: 0.587, data_time: 0.004, memory: 60248, decode.loss_ce: 0.1375, decode.acc_seg: 75.7312, aux.loss_ce: 0.0884, aux.acc_seg: 73.9660, loss: 0.2259 +2022-05-05 18:14:31,855 - mmseg - INFO - Iter [51750/80000] lr: 5.070e-07, eta: 4:54:36, time: 0.647, data_time: 0.054, memory: 60248, decode.loss_ce: 0.1414, decode.acc_seg: 76.5303, aux.loss_ce: 0.0926, aux.acc_seg: 74.4541, loss: 0.2341 +2022-05-05 18:15:01,640 - mmseg - INFO - Iter [51800/80000] lr: 5.061e-07, eta: 4:54:04, time: 0.596, data_time: 0.004, memory: 60248, decode.loss_ce: 0.1532, decode.acc_seg: 74.9382, aux.loss_ce: 0.0950, aux.acc_seg: 73.1923, loss: 0.2482 +2022-05-05 18:15:31,258 - mmseg - INFO - Iter [51850/80000] lr: 5.052e-07, eta: 4:53:31, time: 0.593, data_time: 0.005, memory: 60248, decode.loss_ce: 0.1492, decode.acc_seg: 74.0276, aux.loss_ce: 0.0963, aux.acc_seg: 71.9698, loss: 0.2455 +2022-05-05 18:16:00,820 - mmseg - INFO - Iter [51900/80000] lr: 5.043e-07, eta: 4:52:59, time: 0.591, data_time: 0.006, memory: 60248, decode.loss_ce: 0.1457, decode.acc_seg: 75.7148, aux.loss_ce: 0.0949, aux.acc_seg: 73.7477, loss: 0.2406 +2022-05-05 18:16:30,413 - mmseg - INFO - Iter [51950/80000] lr: 5.034e-07, eta: 4:52:27, time: 0.592, data_time: 0.005, memory: 60248, decode.loss_ce: 0.1514, decode.acc_seg: 75.8992, aux.loss_ce: 0.0941, aux.acc_seg: 74.2146, loss: 0.2456 +2022-05-05 18:17:00,087 - mmseg - INFO - Saving checkpoint at 52000 iterations +2022-05-05 18:17:21,245 - mmseg - INFO - Exp name: upernet_beit_adapter_large_512_80k_cocostuff10k_ss.py +2022-05-05 18:17:21,248 - mmseg - INFO - Iter [52000/80000] lr: 5.025e-07, eta: 4:52:06, time: 1.014, data_time: 0.005, memory: 60248, decode.loss_ce: 0.1459, decode.acc_seg: 74.7415, aux.loss_ce: 0.0946, aux.acc_seg: 72.8220, loss: 0.2404 +2022-05-05 18:17:51,037 - mmseg - INFO - Iter [52050/80000] lr: 5.016e-07, eta: 4:51:34, time: 0.597, data_time: 0.007, memory: 60248, decode.loss_ce: 0.1597, decode.acc_seg: 76.9029, aux.loss_ce: 0.1025, aux.acc_seg: 74.9137, loss: 0.2623 +2022-05-05 18:18:20,510 - mmseg - INFO - Iter [52100/80000] lr: 5.008e-07, eta: 4:51:02, time: 0.590, data_time: 0.007, memory: 60248, decode.loss_ce: 0.1552, decode.acc_seg: 76.6205, aux.loss_ce: 0.0986, aux.acc_seg: 74.6754, loss: 0.2537 +2022-05-05 18:18:49,936 - mmseg - INFO - Iter [52150/80000] lr: 4.999e-07, eta: 4:50:30, time: 0.588, data_time: 0.005, memory: 60248, decode.loss_ce: 0.1462, decode.acc_seg: 76.8036, aux.loss_ce: 0.0926, aux.acc_seg: 74.8707, loss: 0.2389 +2022-05-05 18:19:19,799 - mmseg - INFO - Iter [52200/80000] lr: 4.990e-07, eta: 4:49:57, time: 0.597, data_time: 0.006, memory: 60248, decode.loss_ce: 0.1364, decode.acc_seg: 75.9965, aux.loss_ce: 0.0888, aux.acc_seg: 74.1714, loss: 0.2252 +2022-05-05 18:19:49,599 - mmseg - INFO - Iter [52250/80000] lr: 4.981e-07, eta: 4:49:25, time: 0.594, data_time: 0.005, memory: 60248, decode.loss_ce: 0.1395, decode.acc_seg: 76.7142, aux.loss_ce: 0.0899, aux.acc_seg: 74.8450, loss: 0.2294 +2022-05-05 18:20:22,457 - mmseg - INFO - Iter [52300/80000] lr: 4.972e-07, eta: 4:48:55, time: 0.659, data_time: 0.059, memory: 60248, decode.loss_ce: 0.1376, decode.acc_seg: 74.9206, aux.loss_ce: 0.0882, aux.acc_seg: 73.1631, loss: 0.2259 +2022-05-05 18:20:52,056 - mmseg - INFO - Iter [52350/80000] lr: 4.963e-07, eta: 4:48:23, time: 0.592, data_time: 0.005, memory: 60248, decode.loss_ce: 0.1371, decode.acc_seg: 75.1435, aux.loss_ce: 0.0883, aux.acc_seg: 73.3691, loss: 0.2254 +2022-05-05 18:21:21,998 - mmseg - INFO - Iter [52400/80000] lr: 4.954e-07, eta: 4:47:51, time: 0.599, data_time: 0.005, memory: 60248, decode.loss_ce: 0.1437, decode.acc_seg: 74.4618, aux.loss_ce: 0.0899, aux.acc_seg: 72.8010, loss: 0.2337 +2022-05-05 18:21:51,304 - mmseg - INFO - Iter [52450/80000] lr: 4.945e-07, eta: 4:47:18, time: 0.586, data_time: 0.004, memory: 60248, decode.loss_ce: 0.1491, decode.acc_seg: 76.8776, aux.loss_ce: 0.0983, aux.acc_seg: 74.6387, loss: 0.2474 +2022-05-05 18:22:21,168 - mmseg - INFO - Iter [52500/80000] lr: 4.936e-07, eta: 4:46:46, time: 0.597, data_time: 0.005, memory: 60248, decode.loss_ce: 0.1401, decode.acc_seg: 76.2075, aux.loss_ce: 0.0912, aux.acc_seg: 74.1553, loss: 0.2313 +2022-05-05 18:22:50,898 - mmseg - INFO - Iter [52550/80000] lr: 4.927e-07, eta: 4:46:14, time: 0.595, data_time: 0.004, memory: 60248, decode.loss_ce: 0.1492, decode.acc_seg: 75.1504, aux.loss_ce: 0.0985, aux.acc_seg: 73.0478, loss: 0.2477 +2022-05-05 18:23:20,591 - mmseg - INFO - Iter [52600/80000] lr: 4.918e-07, eta: 4:45:42, time: 0.594, data_time: 0.004, memory: 60248, decode.loss_ce: 0.1430, decode.acc_seg: 76.8492, aux.loss_ce: 0.0927, aux.acc_seg: 74.8165, loss: 0.2357 +2022-05-05 18:23:50,017 - mmseg - INFO - Iter [52650/80000] lr: 4.909e-07, eta: 4:45:10, time: 0.589, data_time: 0.004, memory: 60248, decode.loss_ce: 0.1371, decode.acc_seg: 75.5341, aux.loss_ce: 0.0893, aux.acc_seg: 73.6328, loss: 0.2264 +2022-05-05 18:24:20,034 - mmseg - INFO - Iter [52700/80000] lr: 4.900e-07, eta: 4:44:38, time: 0.600, data_time: 0.004, memory: 60248, decode.loss_ce: 0.1439, decode.acc_seg: 76.6505, aux.loss_ce: 0.0929, aux.acc_seg: 74.7114, loss: 0.2368 +2022-05-05 18:24:50,010 - mmseg - INFO - Iter [52750/80000] lr: 4.891e-07, eta: 4:44:06, time: 0.599, data_time: 0.006, memory: 60248, decode.loss_ce: 0.1516, decode.acc_seg: 76.7450, aux.loss_ce: 0.0956, aux.acc_seg: 74.9162, loss: 0.2472 +2022-05-05 18:25:19,745 - mmseg - INFO - Iter [52800/80000] lr: 4.882e-07, eta: 4:43:34, time: 0.594, data_time: 0.004, memory: 60248, decode.loss_ce: 0.1425, decode.acc_seg: 74.1636, aux.loss_ce: 0.0919, aux.acc_seg: 72.3520, loss: 0.2344 +2022-05-05 18:25:51,701 - mmseg - INFO - Iter [52850/80000] lr: 4.873e-07, eta: 4:43:03, time: 0.640, data_time: 0.054, memory: 60248, decode.loss_ce: 0.1447, decode.acc_seg: 74.7440, aux.loss_ce: 0.0954, aux.acc_seg: 72.7528, loss: 0.2401 +2022-05-05 18:26:21,426 - mmseg - INFO - Iter [52900/80000] lr: 4.864e-07, eta: 4:42:31, time: 0.594, data_time: 0.004, memory: 60248, decode.loss_ce: 0.1449, decode.acc_seg: 74.8448, aux.loss_ce: 0.0899, aux.acc_seg: 73.2352, loss: 0.2348 +2022-05-05 18:26:50,943 - mmseg - INFO - Iter [52950/80000] lr: 4.855e-07, eta: 4:41:59, time: 0.590, data_time: 0.005, memory: 60248, decode.loss_ce: 0.1541, decode.acc_seg: 75.7939, aux.loss_ce: 0.0983, aux.acc_seg: 73.8002, loss: 0.2524 +2022-05-05 18:27:20,246 - mmseg - INFO - Saving checkpoint at 53000 iterations +2022-05-05 18:27:41,108 - mmseg - INFO - Exp name: upernet_beit_adapter_large_512_80k_cocostuff10k_ss.py +2022-05-05 18:27:41,111 - mmseg - INFO - Iter [53000/80000] lr: 4.846e-07, eta: 4:41:37, time: 1.001, data_time: 0.004, memory: 60248, decode.loss_ce: 0.1477, decode.acc_seg: 77.0796, aux.loss_ce: 0.0937, aux.acc_seg: 75.1978, loss: 0.2414 +2022-05-05 18:28:10,960 - mmseg - INFO - Iter [53050/80000] lr: 4.837e-07, eta: 4:41:05, time: 0.599, data_time: 0.007, memory: 60248, decode.loss_ce: 0.1345, decode.acc_seg: 75.6128, aux.loss_ce: 0.0891, aux.acc_seg: 73.7373, loss: 0.2236 +2022-05-05 18:28:40,559 - mmseg - INFO - Iter [53100/80000] lr: 4.828e-07, eta: 4:40:33, time: 0.592, data_time: 0.005, memory: 60248, decode.loss_ce: 0.1395, decode.acc_seg: 74.6504, aux.loss_ce: 0.0882, aux.acc_seg: 72.9778, loss: 0.2277 +2022-05-05 18:29:10,335 - mmseg - INFO - Iter [53150/80000] lr: 4.819e-07, eta: 4:40:01, time: 0.595, data_time: 0.004, memory: 60248, decode.loss_ce: 0.1467, decode.acc_seg: 75.6024, aux.loss_ce: 0.0943, aux.acc_seg: 73.5702, loss: 0.2410 +2022-05-05 18:29:39,907 - mmseg - INFO - Iter [53200/80000] lr: 4.810e-07, eta: 4:39:29, time: 0.591, data_time: 0.005, memory: 60248, decode.loss_ce: 0.1439, decode.acc_seg: 76.5514, aux.loss_ce: 0.0945, aux.acc_seg: 74.4953, loss: 0.2383 +2022-05-05 18:30:09,327 - mmseg - INFO - Iter [53250/80000] lr: 4.801e-07, eta: 4:38:57, time: 0.589, data_time: 0.005, memory: 60248, decode.loss_ce: 0.1383, decode.acc_seg: 76.0389, aux.loss_ce: 0.0908, aux.acc_seg: 74.0736, loss: 0.2291 +2022-05-05 18:30:38,843 - mmseg - INFO - Iter [53300/80000] lr: 4.792e-07, eta: 4:38:24, time: 0.590, data_time: 0.005, memory: 60248, decode.loss_ce: 0.1474, decode.acc_seg: 74.0893, aux.loss_ce: 0.0944, aux.acc_seg: 72.1258, loss: 0.2418 +2022-05-05 18:31:08,715 - mmseg - INFO - Iter [53350/80000] lr: 4.783e-07, eta: 4:37:52, time: 0.597, data_time: 0.005, memory: 60248, decode.loss_ce: 0.1391, decode.acc_seg: 76.4304, aux.loss_ce: 0.0915, aux.acc_seg: 74.4561, loss: 0.2306 +2022-05-05 18:31:41,123 - mmseg - INFO - Iter [53400/80000] lr: 4.774e-07, eta: 4:37:22, time: 0.648, data_time: 0.052, memory: 60248, decode.loss_ce: 0.1416, decode.acc_seg: 76.6347, aux.loss_ce: 0.0897, aux.acc_seg: 74.9869, loss: 0.2312 +2022-05-05 18:32:10,618 - mmseg - INFO - Iter [53450/80000] lr: 4.765e-07, eta: 4:36:49, time: 0.590, data_time: 0.005, memory: 60248, decode.loss_ce: 0.1443, decode.acc_seg: 76.1457, aux.loss_ce: 0.0928, aux.acc_seg: 74.1179, loss: 0.2371 +2022-05-05 18:32:40,092 - mmseg - INFO - Iter [53500/80000] lr: 4.756e-07, eta: 4:36:17, time: 0.590, data_time: 0.004, memory: 60248, decode.loss_ce: 0.1387, decode.acc_seg: 75.5453, aux.loss_ce: 0.0900, aux.acc_seg: 73.5797, loss: 0.2286 +2022-05-05 18:33:09,599 - mmseg - INFO - Iter [53550/80000] lr: 4.747e-07, eta: 4:35:45, time: 0.590, data_time: 0.004, memory: 60248, decode.loss_ce: 0.1426, decode.acc_seg: 76.6623, aux.loss_ce: 0.0916, aux.acc_seg: 74.8396, loss: 0.2343 +2022-05-05 18:33:38,929 - mmseg - INFO - Iter [53600/80000] lr: 4.738e-07, eta: 4:35:13, time: 0.587, data_time: 0.004, memory: 60248, decode.loss_ce: 0.1394, decode.acc_seg: 75.5434, aux.loss_ce: 0.0911, aux.acc_seg: 73.7056, loss: 0.2304 +2022-05-05 18:34:08,658 - mmseg - INFO - Iter [53650/80000] lr: 4.729e-07, eta: 4:34:41, time: 0.595, data_time: 0.005, memory: 60248, decode.loss_ce: 0.1449, decode.acc_seg: 76.3686, aux.loss_ce: 0.0933, aux.acc_seg: 74.4391, loss: 0.2382 +2022-05-05 18:34:38,207 - mmseg - INFO - Iter [53700/80000] lr: 4.720e-07, eta: 4:34:09, time: 0.591, data_time: 0.004, memory: 60248, decode.loss_ce: 0.1467, decode.acc_seg: 76.9629, aux.loss_ce: 0.0943, aux.acc_seg: 74.9804, loss: 0.2409 +2022-05-05 18:35:07,846 - mmseg - INFO - Iter [53750/80000] lr: 4.711e-07, eta: 4:33:37, time: 0.593, data_time: 0.004, memory: 60248, decode.loss_ce: 0.1352, decode.acc_seg: 75.7970, aux.loss_ce: 0.0891, aux.acc_seg: 73.9584, loss: 0.2243 +2022-05-05 18:35:37,467 - mmseg - INFO - Iter [53800/80000] lr: 4.702e-07, eta: 4:33:05, time: 0.592, data_time: 0.004, memory: 60248, decode.loss_ce: 0.1408, decode.acc_seg: 75.4168, aux.loss_ce: 0.0898, aux.acc_seg: 73.6572, loss: 0.2306 +2022-05-05 18:36:07,125 - mmseg - INFO - Iter [53850/80000] lr: 4.693e-07, eta: 4:32:33, time: 0.593, data_time: 0.004, memory: 60248, decode.loss_ce: 0.1433, decode.acc_seg: 74.7860, aux.loss_ce: 0.0892, aux.acc_seg: 73.0076, loss: 0.2325 +2022-05-05 18:36:36,873 - mmseg - INFO - Iter [53900/80000] lr: 4.684e-07, eta: 4:32:01, time: 0.595, data_time: 0.004, memory: 60248, decode.loss_ce: 0.1491, decode.acc_seg: 75.4903, aux.loss_ce: 0.0978, aux.acc_seg: 73.3438, loss: 0.2469 +2022-05-05 18:37:06,331 - mmseg - INFO - Iter [53950/80000] lr: 4.675e-07, eta: 4:31:28, time: 0.589, data_time: 0.004, memory: 60248, decode.loss_ce: 0.1385, decode.acc_seg: 75.9263, aux.loss_ce: 0.0886, aux.acc_seg: 74.1263, loss: 0.2271 +2022-05-05 18:37:38,264 - mmseg - INFO - Saving checkpoint at 54000 iterations +2022-05-05 18:37:58,398 - mmseg - INFO - Exp name: upernet_beit_adapter_large_512_80k_cocostuff10k_ss.py +2022-05-05 18:37:58,400 - mmseg - INFO - Iter [54000/80000] lr: 4.667e-07, eta: 4:31:07, time: 1.039, data_time: 0.053, memory: 60248, decode.loss_ce: 0.1517, decode.acc_seg: 76.4063, aux.loss_ce: 0.0967, aux.acc_seg: 74.4948, loss: 0.2484 +2022-05-05 18:38:28,313 - mmseg - INFO - Iter [54050/80000] lr: 4.658e-07, eta: 4:30:35, time: 0.601, data_time: 0.006, memory: 60248, decode.loss_ce: 0.1336, decode.acc_seg: 74.6012, aux.loss_ce: 0.0853, aux.acc_seg: 72.8765, loss: 0.2189 +2022-05-05 18:38:57,968 - mmseg - INFO - Iter [54100/80000] lr: 4.649e-07, eta: 4:30:03, time: 0.593, data_time: 0.004, memory: 60248, decode.loss_ce: 0.1439, decode.acc_seg: 76.4302, aux.loss_ce: 0.0920, aux.acc_seg: 74.5693, loss: 0.2359 +2022-05-05 18:39:27,913 - mmseg - INFO - Iter [54150/80000] lr: 4.640e-07, eta: 4:29:31, time: 0.599, data_time: 0.006, memory: 60248, decode.loss_ce: 0.1441, decode.acc_seg: 77.7746, aux.loss_ce: 0.0902, aux.acc_seg: 76.0746, loss: 0.2343 +2022-05-05 18:39:57,384 - mmseg - INFO - Iter [54200/80000] lr: 4.631e-07, eta: 4:28:59, time: 0.590, data_time: 0.005, memory: 60248, decode.loss_ce: 0.1418, decode.acc_seg: 76.1974, aux.loss_ce: 0.0911, aux.acc_seg: 74.3684, loss: 0.2329 +2022-05-05 18:40:26,883 - mmseg - INFO - Iter [54250/80000] lr: 4.622e-07, eta: 4:28:27, time: 0.590, data_time: 0.005, memory: 60248, decode.loss_ce: 0.1416, decode.acc_seg: 75.3344, aux.loss_ce: 0.0914, aux.acc_seg: 73.4582, loss: 0.2330 +2022-05-05 18:40:56,406 - mmseg - INFO - Iter [54300/80000] lr: 4.613e-07, eta: 4:27:55, time: 0.590, data_time: 0.005, memory: 60248, decode.loss_ce: 0.1434, decode.acc_seg: 74.6631, aux.loss_ce: 0.0944, aux.acc_seg: 72.7205, loss: 0.2379 +2022-05-05 18:41:26,388 - mmseg - INFO - Iter [54350/80000] lr: 4.604e-07, eta: 4:27:23, time: 0.600, data_time: 0.005, memory: 60248, decode.loss_ce: 0.1317, decode.acc_seg: 76.1956, aux.loss_ce: 0.0824, aux.acc_seg: 74.5400, loss: 0.2142 +2022-05-05 18:41:56,171 - mmseg - INFO - Iter [54400/80000] lr: 4.595e-07, eta: 4:26:51, time: 0.594, data_time: 0.004, memory: 60248, decode.loss_ce: 0.1398, decode.acc_seg: 76.2952, aux.loss_ce: 0.0890, aux.acc_seg: 74.5727, loss: 0.2289 +2022-05-05 18:42:25,759 - mmseg - INFO - Iter [54450/80000] lr: 4.586e-07, eta: 4:26:19, time: 0.594, data_time: 0.006, memory: 60248, decode.loss_ce: 0.1437, decode.acc_seg: 76.0947, aux.loss_ce: 0.0920, aux.acc_seg: 74.2807, loss: 0.2357 +2022-05-05 18:42:55,342 - mmseg - INFO - Iter [54500/80000] lr: 4.577e-07, eta: 4:25:47, time: 0.592, data_time: 0.004, memory: 60248, decode.loss_ce: 0.1429, decode.acc_seg: 75.2996, aux.loss_ce: 0.0910, aux.acc_seg: 73.5745, loss: 0.2339 +2022-05-05 18:43:27,191 - mmseg - INFO - Iter [54550/80000] lr: 4.568e-07, eta: 4:25:16, time: 0.637, data_time: 0.054, memory: 60248, decode.loss_ce: 0.1446, decode.acc_seg: 77.1367, aux.loss_ce: 0.0956, aux.acc_seg: 75.0341, loss: 0.2402 +2022-05-05 18:43:56,578 - mmseg - INFO - Iter [54600/80000] lr: 4.559e-07, eta: 4:24:44, time: 0.588, data_time: 0.004, memory: 60248, decode.loss_ce: 0.1341, decode.acc_seg: 75.8384, aux.loss_ce: 0.0853, aux.acc_seg: 74.1129, loss: 0.2194 +2022-05-05 18:44:26,005 - mmseg - INFO - Iter [54650/80000] lr: 4.550e-07, eta: 4:24:12, time: 0.588, data_time: 0.004, memory: 60248, decode.loss_ce: 0.1476, decode.acc_seg: 76.1273, aux.loss_ce: 0.0964, aux.acc_seg: 74.2336, loss: 0.2439 +2022-05-05 18:44:55,346 - mmseg - INFO - Iter [54700/80000] lr: 4.541e-07, eta: 4:23:39, time: 0.587, data_time: 0.004, memory: 60248, decode.loss_ce: 0.1378, decode.acc_seg: 76.2505, aux.loss_ce: 0.0903, aux.acc_seg: 74.2533, loss: 0.2281 +2022-05-05 18:45:24,937 - mmseg - INFO - Iter [54750/80000] lr: 4.532e-07, eta: 4:23:07, time: 0.592, data_time: 0.005, memory: 60248, decode.loss_ce: 0.1455, decode.acc_seg: 77.0263, aux.loss_ce: 0.0916, aux.acc_seg: 75.2654, loss: 0.2371 +2022-05-05 18:45:54,216 - mmseg - INFO - Iter [54800/80000] lr: 4.523e-07, eta: 4:22:35, time: 0.586, data_time: 0.005, memory: 60248, decode.loss_ce: 0.1372, decode.acc_seg: 77.2309, aux.loss_ce: 0.0886, aux.acc_seg: 75.4174, loss: 0.2259 +2022-05-05 18:46:23,939 - mmseg - INFO - Iter [54850/80000] lr: 4.514e-07, eta: 4:22:03, time: 0.594, data_time: 0.004, memory: 60248, decode.loss_ce: 0.1386, decode.acc_seg: 76.4336, aux.loss_ce: 0.0892, aux.acc_seg: 74.5548, loss: 0.2278 +2022-05-05 18:46:53,668 - mmseg - INFO - Iter [54900/80000] lr: 4.505e-07, eta: 4:21:31, time: 0.595, data_time: 0.004, memory: 60248, decode.loss_ce: 0.1445, decode.acc_seg: 75.0919, aux.loss_ce: 0.0935, aux.acc_seg: 73.1394, loss: 0.2379 +2022-05-05 18:47:23,245 - mmseg - INFO - Iter [54950/80000] lr: 4.496e-07, eta: 4:20:59, time: 0.591, data_time: 0.005, memory: 60248, decode.loss_ce: 0.1342, decode.acc_seg: 76.8600, aux.loss_ce: 0.0865, aux.acc_seg: 75.0671, loss: 0.2206 +2022-05-05 18:47:52,656 - mmseg - INFO - Saving checkpoint at 55000 iterations +2022-05-05 18:48:13,636 - mmseg - INFO - Exp name: upernet_beit_adapter_large_512_80k_cocostuff10k_ss.py +2022-05-05 18:48:13,639 - mmseg - INFO - Iter [55000/80000] lr: 4.487e-07, eta: 4:20:37, time: 1.005, data_time: 0.004, memory: 60248, decode.loss_ce: 0.1275, decode.acc_seg: 75.7047, aux.loss_ce: 0.0843, aux.acc_seg: 73.7732, loss: 0.2118 +2022-05-05 18:48:43,403 - mmseg - INFO - Iter [55050/80000] lr: 4.478e-07, eta: 4:20:05, time: 0.598, data_time: 0.007, memory: 60248, decode.loss_ce: 0.1403, decode.acc_seg: 75.4147, aux.loss_ce: 0.0907, aux.acc_seg: 73.5224, loss: 0.2309 +2022-05-05 18:49:15,336 - mmseg - INFO - Iter [55100/80000] lr: 4.469e-07, eta: 4:19:34, time: 0.639, data_time: 0.058, memory: 60248, decode.loss_ce: 0.1371, decode.acc_seg: 75.9883, aux.loss_ce: 0.0882, aux.acc_seg: 74.2681, loss: 0.2254 +2022-05-05 18:49:44,895 - mmseg - INFO - Iter [55150/80000] lr: 4.460e-07, eta: 4:19:02, time: 0.591, data_time: 0.004, memory: 60248, decode.loss_ce: 0.1451, decode.acc_seg: 76.0244, aux.loss_ce: 0.0945, aux.acc_seg: 73.9579, loss: 0.2396 +2022-05-05 18:50:14,133 - mmseg - INFO - Iter [55200/80000] lr: 4.451e-07, eta: 4:18:30, time: 0.585, data_time: 0.005, memory: 60248, decode.loss_ce: 0.1474, decode.acc_seg: 74.3744, aux.loss_ce: 0.0940, aux.acc_seg: 72.3953, loss: 0.2413 +2022-05-05 18:50:43,523 - mmseg - INFO - Iter [55250/80000] lr: 4.442e-07, eta: 4:17:57, time: 0.588, data_time: 0.005, memory: 60248, decode.loss_ce: 0.1315, decode.acc_seg: 76.2847, aux.loss_ce: 0.0850, aux.acc_seg: 74.5958, loss: 0.2165 +2022-05-05 18:51:13,249 - mmseg - INFO - Iter [55300/80000] lr: 4.433e-07, eta: 4:17:26, time: 0.594, data_time: 0.005, memory: 60248, decode.loss_ce: 0.1408, decode.acc_seg: 76.1159, aux.loss_ce: 0.0906, aux.acc_seg: 74.3610, loss: 0.2314 +2022-05-05 18:51:42,717 - mmseg - INFO - Iter [55350/80000] lr: 4.424e-07, eta: 4:16:53, time: 0.589, data_time: 0.004, memory: 60248, decode.loss_ce: 0.1369, decode.acc_seg: 75.4410, aux.loss_ce: 0.0885, aux.acc_seg: 73.4408, loss: 0.2254 +2022-05-05 18:52:12,058 - mmseg - INFO - Iter [55400/80000] lr: 4.415e-07, eta: 4:16:21, time: 0.587, data_time: 0.005, memory: 60248, decode.loss_ce: 0.1355, decode.acc_seg: 75.5480, aux.loss_ce: 0.0860, aux.acc_seg: 73.7546, loss: 0.2215 +2022-05-05 18:52:41,690 - mmseg - INFO - Iter [55450/80000] lr: 4.406e-07, eta: 4:15:49, time: 0.593, data_time: 0.005, memory: 60248, decode.loss_ce: 0.1401, decode.acc_seg: 77.0782, aux.loss_ce: 0.0875, aux.acc_seg: 75.5129, loss: 0.2276 +2022-05-05 18:53:11,101 - mmseg - INFO - Iter [55500/80000] lr: 4.397e-07, eta: 4:15:17, time: 0.588, data_time: 0.004, memory: 60248, decode.loss_ce: 0.1418, decode.acc_seg: 77.5428, aux.loss_ce: 0.0899, aux.acc_seg: 75.7296, loss: 0.2317 +2022-05-05 18:53:40,583 - mmseg - INFO - Iter [55550/80000] lr: 4.388e-07, eta: 4:14:45, time: 0.590, data_time: 0.004, memory: 60248, decode.loss_ce: 0.1436, decode.acc_seg: 75.4293, aux.loss_ce: 0.0960, aux.acc_seg: 73.3751, loss: 0.2395 +2022-05-05 18:54:10,250 - mmseg - INFO - Iter [55600/80000] lr: 4.379e-07, eta: 4:14:13, time: 0.593, data_time: 0.004, memory: 60248, decode.loss_ce: 0.1367, decode.acc_seg: 74.9364, aux.loss_ce: 0.0899, aux.acc_seg: 72.9694, loss: 0.2265 +2022-05-05 18:54:42,605 - mmseg - INFO - Iter [55650/80000] lr: 4.370e-07, eta: 4:13:42, time: 0.647, data_time: 0.053, memory: 60248, decode.loss_ce: 0.1374, decode.acc_seg: 74.3594, aux.loss_ce: 0.0878, aux.acc_seg: 72.5586, loss: 0.2252 +2022-05-05 18:55:12,351 - mmseg - INFO - Iter [55700/80000] lr: 4.361e-07, eta: 4:13:11, time: 0.595, data_time: 0.005, memory: 60248, decode.loss_ce: 0.1333, decode.acc_seg: 75.6116, aux.loss_ce: 0.0874, aux.acc_seg: 73.7513, loss: 0.2206 +2022-05-05 18:55:41,753 - mmseg - INFO - Iter [55750/80000] lr: 4.352e-07, eta: 4:12:38, time: 0.588, data_time: 0.004, memory: 60248, decode.loss_ce: 0.1336, decode.acc_seg: 76.0522, aux.loss_ce: 0.0858, aux.acc_seg: 74.2987, loss: 0.2194 +2022-05-05 18:56:11,507 - mmseg - INFO - Iter [55800/80000] lr: 4.343e-07, eta: 4:12:07, time: 0.595, data_time: 0.004, memory: 60248, decode.loss_ce: 0.1436, decode.acc_seg: 75.8100, aux.loss_ce: 0.0949, aux.acc_seg: 73.7135, loss: 0.2385 +2022-05-05 18:56:40,954 - mmseg - INFO - Iter [55850/80000] lr: 4.334e-07, eta: 4:11:35, time: 0.589, data_time: 0.004, memory: 60248, decode.loss_ce: 0.1367, decode.acc_seg: 75.2773, aux.loss_ce: 0.0877, aux.acc_seg: 73.6028, loss: 0.2244 +2022-05-05 18:57:10,460 - mmseg - INFO - Iter [55900/80000] lr: 4.326e-07, eta: 4:11:03, time: 0.590, data_time: 0.004, memory: 60248, decode.loss_ce: 0.1336, decode.acc_seg: 75.7221, aux.loss_ce: 0.0877, aux.acc_seg: 73.7960, loss: 0.2213 +2022-05-05 18:57:40,284 - mmseg - INFO - Iter [55950/80000] lr: 4.317e-07, eta: 4:10:31, time: 0.596, data_time: 0.005, memory: 60248, decode.loss_ce: 0.1423, decode.acc_seg: 76.6056, aux.loss_ce: 0.0928, aux.acc_seg: 74.6429, loss: 0.2352 +2022-05-05 18:58:10,149 - mmseg - INFO - Saving checkpoint at 56000 iterations +2022-05-05 18:58:30,512 - mmseg - INFO - Exp name: upernet_beit_adapter_large_512_80k_cocostuff10k_ss.py +2022-05-05 18:58:30,514 - mmseg - INFO - Iter [56000/80000] lr: 4.308e-07, eta: 4:10:08, time: 1.003, data_time: 0.005, memory: 60248, decode.loss_ce: 0.1439, decode.acc_seg: 74.9318, aux.loss_ce: 0.0929, aux.acc_seg: 73.0001, loss: 0.2368 +2022-05-05 18:59:00,610 - mmseg - INFO - per class results: +2022-05-05 18:59:00,623 - mmseg - INFO - ++------------------+-------+-------+ +| Class | IoU | Acc | ++------------------+-------+-------+ +| person | 87.97 | 95.02 | +| bicycle | 75.32 | 92.1 | +| car | 63.68 | 71.02 | +| motorcycle | 87.98 | 95.88 | +| airplane | 88.73 | 95.91 | +| bus | 82.12 | 88.74 | +| train | 69.92 | 98.21 | +| truck | 75.81 | 89.17 | +| boat | 73.31 | 88.5 | +| traffic light | 73.31 | 92.23 | +| fire hydrant | 84.62 | 98.2 | +| stop sign | 89.74 | 98.16 | +| parking meter | 77.12 | 80.68 | +| bench | 53.18 | 69.62 | +| bird | 74.01 | 81.96 | +| cat | 92.46 | 96.76 | +| dog | 91.49 | 96.9 | +| horse | 89.22 | 95.99 | +| sheep | 88.1 | 92.49 | +| cow | 94.42 | 98.81 | +| elephant | 91.8 | 97.69 | +| bear | 85.69 | 96.02 | +| zebra | 90.76 | 96.65 | +| giraffe | 86.46 | 96.02 | +| backpack | 21.5 | 55.56 | +| umbrella | 77.51 | 88.13 | +| handbag | 16.2 | 22.9 | +| tie | 53.5 | 53.5 | +| suitcase | 76.52 | 96.46 | +| frisbee | 94.01 | 96.61 | +| skis | 40.32 | 59.34 | +| snowboard | 65.03 | 78.25 | +| sports ball | 84.63 | 92.87 | +| kite | 66.7 | 89.0 | +| baseball bat | 49.36 | 66.2 | +| baseball glove | 11.74 | 11.96 | +| skateboard | 66.97 | 88.9 | +| surfboard | 88.69 | 95.04 | +| tennis racket | 64.42 | 66.97 | +| bottle | 74.12 | 83.44 | +| wine glass | 83.38 | 94.37 | +| cup | 65.29 | 92.29 | +| fork | 51.63 | 70.75 | +| knife | 76.24 | 87.18 | +| spoon | 46.76 | 64.45 | +| bowl | 53.7 | 64.69 | +| banana | 78.38 | 87.6 | +| apple | 68.85 | 90.3 | +| sandwich | 86.27 | 97.8 | +| orange | 68.69 | 90.82 | +| broccoli | 93.67 | 96.71 | +| carrot | 40.08 | 70.85 | +| hot dog | 49.91 | 96.03 | +| pizza | 93.71 | 96.07 | +| donut | 67.73 | 90.89 | +| cake | 50.31 | 59.13 | +| chair | 59.19 | 77.27 | +| couch | 76.43 | 94.48 | +| potted plant | 36.15 | 46.72 | +| bed | 72.67 | 84.67 | +| dining table | 63.25 | 78.75 | +| toilet | 87.87 | 96.99 | +| tv | 69.07 | 91.55 | +| laptop | 88.35 | 98.22 | +| mouse | 69.19 | 76.72 | +| remote | 69.78 | 91.81 | +| keyboard | 86.34 | 98.12 | +| cell phone | 78.03 | 96.23 | +| microwave | 47.68 | 73.89 | +| oven | 62.59 | 86.39 | +| toaster | 48.95 | 50.84 | +| sink | 69.1 | 78.75 | +| refrigerator | 82.13 | 88.1 | +| book | 79.69 | 90.44 | +| clock | 75.65 | 86.86 | +| vase | 63.01 | 91.76 | +| scissors | 78.42 | 94.29 | +| teddy bear | 85.68 | 96.02 | +| hair drier | 0.0 | 0.0 | +| toothbrush | 16.44 | 31.23 | +| banner | 24.51 | 42.1 | +| blanket | 2.71 | 2.72 | +| branch | 0.5 | 0.51 | +| bridge | 2.71 | 3.61 | +| building-other | 55.09 | 73.75 | +| bush | 26.22 | 36.58 | +| cabinet | 16.23 | 31.85 | +| cage | 7.08 | 26.14 | +| cardboard | 22.38 | 29.39 | +| carpet | 54.9 | 81.2 | +| ceiling-other | 72.22 | 87.79 | +| ceiling-tile | 13.07 | 13.87 | +| cloth | 7.02 | 10.59 | +| clothes | 20.17 | 30.67 | +| clouds | 47.58 | 59.89 | +| counter | 34.28 | 45.55 | +| cupboard | 52.64 | 69.06 | +| curtain | 64.15 | 80.59 | +| desk-stuff | 32.27 | 36.43 | +| dirt | 33.17 | 54.08 | +| door-stuff | 44.55 | 55.77 | +| fence | 43.9 | 73.5 | +| floor-marble | 0.0 | 0.0 | +| floor-other | 42.98 | 60.89 | +| floor-stone | 22.12 | 30.77 | +| floor-tile | 60.19 | 74.23 | +| floor-wood | 72.1 | 85.64 | +| flower | 18.23 | 43.75 | +| fog | 0.0 | 0.0 | +| food-other | 38.11 | 54.7 | +| fruit | 58.58 | 68.93 | +| furniture-other | 13.51 | 18.06 | +| grass | 73.28 | 85.26 | +| gravel | 28.45 | 33.75 | +| ground-other | 7.68 | 15.26 | +| hill | 23.32 | 32.39 | +| house | 28.29 | 41.18 | +| leaves | 8.3 | 18.66 | +| light | 40.53 | 52.42 | +| mat | 24.12 | 33.25 | +| metal | 15.44 | 18.25 | +| mirror-stuff | 39.4 | 52.37 | +| moss | 0.0 | 0.0 | +| mountain | 33.14 | 56.62 | +| mud | 11.4 | 18.01 | +| napkin | 31.95 | 34.59 | +| net | 28.95 | 32.82 | +| paper | 57.51 | 70.05 | +| pavement | 57.0 | 77.13 | +| pillow | 0.0 | 0.0 | +| plant-other | 31.55 | 41.13 | +| plastic | 20.28 | 24.17 | +| platform | 42.32 | 59.57 | +| playingfield | 69.82 | 81.92 | +| railing | 16.62 | 26.37 | +| railroad | 62.76 | 87.25 | +| river | 3.5 | 4.13 | +| road | 69.74 | 77.79 | +| rock | 50.39 | 71.27 | +| roof | 5.39 | 9.63 | +| rug | 44.64 | 57.35 | +| salad | 26.25 | 27.21 | +| sand | 75.55 | 87.26 | +| sea | 76.52 | 90.0 | +| shelf | 25.79 | 40.52 | +| sky-other | 60.07 | 78.6 | +| skyscraper | 6.8 | 9.59 | +| snow | 91.56 | 95.1 | +| solid-other | 0.0 | nan | +| stairs | 32.18 | 47.12 | +| stone | 6.66 | 11.35 | +| straw | 14.42 | 32.38 | +| structural-other | 18.76 | 26.47 | +| table | 19.24 | 27.97 | +| tent | 70.24 | 78.48 | +| textile-other | 16.1 | 20.44 | +| towel | 40.87 | 49.77 | +| tree | 77.82 | 88.53 | +| vegetable | 41.69 | 63.5 | +| wall-brick | 39.8 | 52.65 | +| wall-concrete | 18.59 | 23.77 | +| wall-other | 60.36 | 80.8 | +| wall-panel | 5.76 | 6.65 | +| wall-stone | 30.52 | 37.69 | +| wall-tile | 58.08 | 91.19 | +| wall-wood | 41.49 | 61.8 | +| water-other | 37.2 | 56.11 | +| waterdrops | nan | nan | +| window-blind | 22.87 | 40.62 | +| window-other | 48.3 | 62.79 | +| wood | 13.97 | 28.68 | ++------------------+-------+-------+ +2022-05-05 18:59:00,624 - mmseg - INFO - Summary: +2022-05-05 18:59:00,624 - mmseg - INFO - ++-------+-------+-------+ +| aAcc | mIoU | mAcc | ++-------+-------+-------+ +| 75.28 | 50.38 | 62.78 | ++-------+-------+-------+ +2022-05-05 18:59:00,626 - mmseg - INFO - The previous best checkpoint /mnt/lustre/chenzhe.vendor/workspace/ViT-Adapter/segmentation/work_dirs/upernet_beit_adapter_large_512_80k_cocostuff10k_ss/best_mIoU_iter_48000.pth was removed +2022-05-05 18:59:21,474 - mmseg - INFO - Now best checkpoint is saved as best_mIoU_iter_56000.pth. +2022-05-05 18:59:21,484 - mmseg - INFO - Best mIoU is 0.5038 at 56000 iter. +2022-05-05 18:59:21,496 - mmseg - INFO - Exp name: upernet_beit_adapter_large_512_80k_cocostuff10k_ss.py +2022-05-05 18:59:21,496 - mmseg - INFO - Iter(val) [125] aAcc: 0.7528, mIoU: 0.5038, mAcc: 0.6278, IoU.person: 0.8797, IoU.bicycle: 0.7532, IoU.car: 0.6368, IoU.motorcycle: 0.8798, IoU.airplane: 0.8873, IoU.bus: 0.8212, IoU.train: 0.6992, IoU.truck: 0.7581, IoU.boat: 0.7331, IoU.traffic light: 0.7331, IoU.fire hydrant: 0.8462, IoU.stop sign: 0.8974, IoU.parking meter: 0.7712, IoU.bench: 0.5318, IoU.bird: 0.7401, IoU.cat: 0.9246, IoU.dog: 0.9149, IoU.horse: 0.8922, IoU.sheep: 0.8810, IoU.cow: 0.9442, IoU.elephant: 0.9180, IoU.bear: 0.8569, IoU.zebra: 0.9076, IoU.giraffe: 0.8646, IoU.backpack: 0.2150, IoU.umbrella: 0.7751, IoU.handbag: 0.1620, IoU.tie: 0.5350, IoU.suitcase: 0.7652, IoU.frisbee: 0.9401, IoU.skis: 0.4032, IoU.snowboard: 0.6503, IoU.sports ball: 0.8463, IoU.kite: 0.6670, IoU.baseball bat: 0.4936, IoU.baseball glove: 0.1174, IoU.skateboard: 0.6697, IoU.surfboard: 0.8869, IoU.tennis racket: 0.6442, IoU.bottle: 0.7412, IoU.wine glass: 0.8338, IoU.cup: 0.6529, IoU.fork: 0.5163, IoU.knife: 0.7624, IoU.spoon: 0.4676, IoU.bowl: 0.5370, IoU.banana: 0.7838, IoU.apple: 0.6885, IoU.sandwich: 0.8627, IoU.orange: 0.6869, IoU.broccoli: 0.9367, IoU.carrot: 0.4008, IoU.hot dog: 0.4991, IoU.pizza: 0.9371, IoU.donut: 0.6773, IoU.cake: 0.5031, IoU.chair: 0.5919, IoU.couch: 0.7643, IoU.potted plant: 0.3615, IoU.bed: 0.7267, IoU.dining table: 0.6325, IoU.toilet: 0.8787, IoU.tv: 0.6907, IoU.laptop: 0.8835, IoU.mouse: 0.6919, IoU.remote: 0.6978, IoU.keyboard: 0.8634, IoU.cell phone: 0.7803, IoU.microwave: 0.4768, IoU.oven: 0.6259, IoU.toaster: 0.4895, IoU.sink: 0.6910, IoU.refrigerator: 0.8213, IoU.book: 0.7969, IoU.clock: 0.7565, IoU.vase: 0.6301, IoU.scissors: 0.7842, IoU.teddy bear: 0.8568, IoU.hair drier: 0.0000, IoU.toothbrush: 0.1644, IoU.banner: 0.2451, IoU.blanket: 0.0271, IoU.branch: 0.0050, IoU.bridge: 0.0271, IoU.building-other: 0.5509, IoU.bush: 0.2622, IoU.cabinet: 0.1623, IoU.cage: 0.0708, IoU.cardboard: 0.2238, IoU.carpet: 0.5490, IoU.ceiling-other: 0.7222, IoU.ceiling-tile: 0.1307, IoU.cloth: 0.0702, IoU.clothes: 0.2017, IoU.clouds: 0.4758, IoU.counter: 0.3428, IoU.cupboard: 0.5264, IoU.curtain: 0.6415, IoU.desk-stuff: 0.3227, IoU.dirt: 0.3317, IoU.door-stuff: 0.4455, IoU.fence: 0.4390, IoU.floor-marble: 0.0000, IoU.floor-other: 0.4298, IoU.floor-stone: 0.2212, IoU.floor-tile: 0.6019, IoU.floor-wood: 0.7210, IoU.flower: 0.1823, IoU.fog: 0.0000, IoU.food-other: 0.3811, IoU.fruit: 0.5858, IoU.furniture-other: 0.1351, IoU.grass: 0.7328, IoU.gravel: 0.2845, IoU.ground-other: 0.0768, IoU.hill: 0.2332, IoU.house: 0.2829, IoU.leaves: 0.0830, IoU.light: 0.4053, IoU.mat: 0.2412, IoU.metal: 0.1544, IoU.mirror-stuff: 0.3940, IoU.moss: 0.0000, IoU.mountain: 0.3314, IoU.mud: 0.1140, IoU.napkin: 0.3195, IoU.net: 0.2895, IoU.paper: 0.5751, IoU.pavement: 0.5700, IoU.pillow: 0.0000, IoU.plant-other: 0.3155, IoU.plastic: 0.2028, IoU.platform: 0.4232, IoU.playingfield: 0.6982, IoU.railing: 0.1662, IoU.railroad: 0.6276, IoU.river: 0.0350, IoU.road: 0.6974, IoU.rock: 0.5039, IoU.roof: 0.0539, IoU.rug: 0.4464, IoU.salad: 0.2625, IoU.sand: 0.7555, IoU.sea: 0.7652, IoU.shelf: 0.2579, IoU.sky-other: 0.6007, IoU.skyscraper: 0.0680, IoU.snow: 0.9156, IoU.solid-other: 0.0000, IoU.stairs: 0.3218, IoU.stone: 0.0666, IoU.straw: 0.1442, IoU.structural-other: 0.1876, IoU.table: 0.1924, IoU.tent: 0.7024, IoU.textile-other: 0.1610, IoU.towel: 0.4087, IoU.tree: 0.7782, IoU.vegetable: 0.4169, IoU.wall-brick: 0.3980, IoU.wall-concrete: 0.1859, IoU.wall-other: 0.6036, IoU.wall-panel: 0.0576, IoU.wall-stone: 0.3052, IoU.wall-tile: 0.5808, IoU.wall-wood: 0.4149, IoU.water-other: 0.3720, IoU.waterdrops: nan, IoU.window-blind: 0.2287, IoU.window-other: 0.4830, IoU.wood: 0.1397, Acc.person: 0.9502, Acc.bicycle: 0.9210, Acc.car: 0.7102, Acc.motorcycle: 0.9588, Acc.airplane: 0.9591, Acc.bus: 0.8874, Acc.train: 0.9821, Acc.truck: 0.8917, Acc.boat: 0.8850, Acc.traffic light: 0.9223, Acc.fire hydrant: 0.9820, Acc.stop sign: 0.9816, Acc.parking meter: 0.8068, Acc.bench: 0.6962, Acc.bird: 0.8196, Acc.cat: 0.9676, Acc.dog: 0.9690, Acc.horse: 0.9599, Acc.sheep: 0.9249, Acc.cow: 0.9881, Acc.elephant: 0.9769, Acc.bear: 0.9602, Acc.zebra: 0.9665, Acc.giraffe: 0.9602, Acc.backpack: 0.5556, Acc.umbrella: 0.8813, Acc.handbag: 0.2290, Acc.tie: 0.5350, Acc.suitcase: 0.9646, Acc.frisbee: 0.9661, Acc.skis: 0.5934, Acc.snowboard: 0.7825, Acc.sports ball: 0.9287, Acc.kite: 0.8900, Acc.baseball bat: 0.6620, Acc.baseball glove: 0.1196, Acc.skateboard: 0.8890, Acc.surfboard: 0.9504, Acc.tennis racket: 0.6697, Acc.bottle: 0.8344, Acc.wine glass: 0.9437, Acc.cup: 0.9229, Acc.fork: 0.7075, Acc.knife: 0.8718, Acc.spoon: 0.6445, Acc.bowl: 0.6469, Acc.banana: 0.8760, Acc.apple: 0.9030, Acc.sandwich: 0.9780, Acc.orange: 0.9082, Acc.broccoli: 0.9671, Acc.carrot: 0.7085, Acc.hot dog: 0.9603, Acc.pizza: 0.9607, Acc.donut: 0.9089, Acc.cake: 0.5913, Acc.chair: 0.7727, Acc.couch: 0.9448, Acc.potted plant: 0.4672, Acc.bed: 0.8467, Acc.dining table: 0.7875, Acc.toilet: 0.9699, Acc.tv: 0.9155, Acc.laptop: 0.9822, Acc.mouse: 0.7672, Acc.remote: 0.9181, Acc.keyboard: 0.9812, Acc.cell phone: 0.9623, Acc.microwave: 0.7389, Acc.oven: 0.8639, Acc.toaster: 0.5084, Acc.sink: 0.7875, Acc.refrigerator: 0.8810, Acc.book: 0.9044, Acc.clock: 0.8686, Acc.vase: 0.9176, Acc.scissors: 0.9429, Acc.teddy bear: 0.9602, Acc.hair drier: 0.0000, Acc.toothbrush: 0.3123, Acc.banner: 0.4210, Acc.blanket: 0.0272, Acc.branch: 0.0051, Acc.bridge: 0.0361, Acc.building-other: 0.7375, Acc.bush: 0.3658, Acc.cabinet: 0.3185, Acc.cage: 0.2614, Acc.cardboard: 0.2939, Acc.carpet: 0.8120, Acc.ceiling-other: 0.8779, Acc.ceiling-tile: 0.1387, Acc.cloth: 0.1059, Acc.clothes: 0.3067, Acc.clouds: 0.5989, Acc.counter: 0.4555, Acc.cupboard: 0.6906, Acc.curtain: 0.8059, Acc.desk-stuff: 0.3643, Acc.dirt: 0.5408, Acc.door-stuff: 0.5577, Acc.fence: 0.7350, Acc.floor-marble: 0.0000, Acc.floor-other: 0.6089, Acc.floor-stone: 0.3077, Acc.floor-tile: 0.7423, Acc.floor-wood: 0.8564, Acc.flower: 0.4375, Acc.fog: 0.0000, Acc.food-other: 0.5470, Acc.fruit: 0.6893, Acc.furniture-other: 0.1806, Acc.grass: 0.8526, Acc.gravel: 0.3375, Acc.ground-other: 0.1526, Acc.hill: 0.3239, Acc.house: 0.4118, Acc.leaves: 0.1866, Acc.light: 0.5242, Acc.mat: 0.3325, Acc.metal: 0.1825, Acc.mirror-stuff: 0.5237, Acc.moss: 0.0000, Acc.mountain: 0.5662, Acc.mud: 0.1801, Acc.napkin: 0.3459, Acc.net: 0.3282, Acc.paper: 0.7005, Acc.pavement: 0.7713, Acc.pillow: 0.0000, Acc.plant-other: 0.4113, Acc.plastic: 0.2417, Acc.platform: 0.5957, Acc.playingfield: 0.8192, Acc.railing: 0.2637, Acc.railroad: 0.8725, Acc.river: 0.0413, Acc.road: 0.7779, Acc.rock: 0.7127, Acc.roof: 0.0963, Acc.rug: 0.5735, Acc.salad: 0.2721, Acc.sand: 0.8726, Acc.sea: 0.9000, Acc.shelf: 0.4052, Acc.sky-other: 0.7860, Acc.skyscraper: 0.0959, Acc.snow: 0.9510, Acc.solid-other: nan, Acc.stairs: 0.4712, Acc.stone: 0.1135, Acc.straw: 0.3238, Acc.structural-other: 0.2647, Acc.table: 0.2797, Acc.tent: 0.7848, Acc.textile-other: 0.2044, Acc.towel: 0.4977, Acc.tree: 0.8853, Acc.vegetable: 0.6350, Acc.wall-brick: 0.5265, Acc.wall-concrete: 0.2377, Acc.wall-other: 0.8080, Acc.wall-panel: 0.0665, Acc.wall-stone: 0.3769, Acc.wall-tile: 0.9119, Acc.wall-wood: 0.6180, Acc.water-other: 0.5611, Acc.waterdrops: nan, Acc.window-blind: 0.4062, Acc.window-other: 0.6279, Acc.wood: 0.2868 +2022-05-05 18:59:51,454 - mmseg - INFO - Iter [56050/80000] lr: 4.299e-07, eta: 4:09:58, time: 1.620, data_time: 1.027, memory: 60248, decode.loss_ce: 0.1460, decode.acc_seg: 76.6380, aux.loss_ce: 0.0935, aux.acc_seg: 74.7048, loss: 0.2396 +2022-05-05 19:00:20,882 - mmseg - INFO - Iter [56100/80000] lr: 4.290e-07, eta: 4:09:25, time: 0.589, data_time: 0.005, memory: 60248, decode.loss_ce: 0.1437, decode.acc_seg: 74.8914, aux.loss_ce: 0.0911, aux.acc_seg: 73.0845, loss: 0.2348 +2022-05-05 19:00:50,414 - mmseg - INFO - Iter [56150/80000] lr: 4.281e-07, eta: 4:08:53, time: 0.591, data_time: 0.005, memory: 60248, decode.loss_ce: 0.1342, decode.acc_seg: 77.1474, aux.loss_ce: 0.0893, aux.acc_seg: 75.2152, loss: 0.2235 +2022-05-05 19:01:19,964 - mmseg - INFO - Iter [56200/80000] lr: 4.272e-07, eta: 4:08:21, time: 0.591, data_time: 0.004, memory: 60248, decode.loss_ce: 0.1462, decode.acc_seg: 76.5876, aux.loss_ce: 0.0948, aux.acc_seg: 74.6333, loss: 0.2410 +2022-05-05 19:01:52,488 - mmseg - INFO - Iter [56250/80000] lr: 4.263e-07, eta: 4:07:50, time: 0.650, data_time: 0.055, memory: 60248, decode.loss_ce: 0.1455, decode.acc_seg: 76.2892, aux.loss_ce: 0.0935, aux.acc_seg: 74.3714, loss: 0.2390 +2022-05-05 19:02:21,858 - mmseg - INFO - Iter [56300/80000] lr: 4.254e-07, eta: 4:07:18, time: 0.588, data_time: 0.005, memory: 60248, decode.loss_ce: 0.1407, decode.acc_seg: 75.4389, aux.loss_ce: 0.0933, aux.acc_seg: 73.4664, loss: 0.2340 +2022-05-05 19:02:51,562 - mmseg - INFO - Iter [56350/80000] lr: 4.245e-07, eta: 4:06:46, time: 0.594, data_time: 0.005, memory: 60248, decode.loss_ce: 0.1361, decode.acc_seg: 76.5968, aux.loss_ce: 0.0855, aux.acc_seg: 74.9012, loss: 0.2216 +2022-05-05 19:03:21,395 - mmseg - INFO - Iter [56400/80000] lr: 4.236e-07, eta: 4:06:14, time: 0.597, data_time: 0.005, memory: 60248, decode.loss_ce: 0.1418, decode.acc_seg: 75.7958, aux.loss_ce: 0.0901, aux.acc_seg: 73.9532, loss: 0.2319 +2022-05-05 19:03:51,090 - mmseg - INFO - Iter [56450/80000] lr: 4.227e-07, eta: 4:05:43, time: 0.594, data_time: 0.004, memory: 60248, decode.loss_ce: 0.1357, decode.acc_seg: 76.8429, aux.loss_ce: 0.0879, aux.acc_seg: 74.9943, loss: 0.2235 +2022-05-05 19:04:20,931 - mmseg - INFO - Iter [56500/80000] lr: 4.218e-07, eta: 4:05:11, time: 0.597, data_time: 0.005, memory: 60248, decode.loss_ce: 0.1357, decode.acc_seg: 74.8392, aux.loss_ce: 0.0886, aux.acc_seg: 73.0243, loss: 0.2243 +2022-05-05 19:04:50,648 - mmseg - INFO - Iter [56550/80000] lr: 4.209e-07, eta: 4:04:39, time: 0.594, data_time: 0.004, memory: 60248, decode.loss_ce: 0.1403, decode.acc_seg: 77.2752, aux.loss_ce: 0.0905, aux.acc_seg: 75.3908, loss: 0.2308 +2022-05-05 19:05:20,236 - mmseg - INFO - Iter [56600/80000] lr: 4.200e-07, eta: 4:04:07, time: 0.592, data_time: 0.004, memory: 60248, decode.loss_ce: 0.1343, decode.acc_seg: 75.4516, aux.loss_ce: 0.0859, aux.acc_seg: 73.7923, loss: 0.2202 +2022-05-05 19:05:49,834 - mmseg - INFO - Iter [56650/80000] lr: 4.191e-07, eta: 4:03:35, time: 0.592, data_time: 0.004, memory: 60248, decode.loss_ce: 0.1346, decode.acc_seg: 75.7305, aux.loss_ce: 0.0876, aux.acc_seg: 73.7964, loss: 0.2222 +2022-05-05 19:06:19,239 - mmseg - INFO - Iter [56700/80000] lr: 4.182e-07, eta: 4:03:03, time: 0.588, data_time: 0.004, memory: 60248, decode.loss_ce: 0.1368, decode.acc_seg: 75.6963, aux.loss_ce: 0.0899, aux.acc_seg: 73.7533, loss: 0.2266 +2022-05-05 19:06:48,722 - mmseg - INFO - Iter [56750/80000] lr: 4.173e-07, eta: 4:02:31, time: 0.590, data_time: 0.004, memory: 60248, decode.loss_ce: 0.1388, decode.acc_seg: 76.0256, aux.loss_ce: 0.0895, aux.acc_seg: 74.2585, loss: 0.2283 +2022-05-05 19:07:21,093 - mmseg - INFO - Iter [56800/80000] lr: 4.164e-07, eta: 4:02:00, time: 0.647, data_time: 0.052, memory: 60248, decode.loss_ce: 0.1422, decode.acc_seg: 75.2260, aux.loss_ce: 0.0899, aux.acc_seg: 73.4865, loss: 0.2321 +2022-05-05 19:07:50,607 - mmseg - INFO - Iter [56850/80000] lr: 4.155e-07, eta: 4:01:28, time: 0.590, data_time: 0.004, memory: 60248, decode.loss_ce: 0.1309, decode.acc_seg: 76.1802, aux.loss_ce: 0.0850, aux.acc_seg: 74.5010, loss: 0.2159 +2022-05-05 19:08:20,109 - mmseg - INFO - Iter [56900/80000] lr: 4.146e-07, eta: 4:00:56, time: 0.590, data_time: 0.005, memory: 60248, decode.loss_ce: 0.1381, decode.acc_seg: 77.8315, aux.loss_ce: 0.0871, aux.acc_seg: 76.0048, loss: 0.2252 +2022-05-05 19:08:49,575 - mmseg - INFO - Iter [56950/80000] lr: 4.137e-07, eta: 4:00:24, time: 0.589, data_time: 0.004, memory: 60248, decode.loss_ce: 0.1341, decode.acc_seg: 76.0908, aux.loss_ce: 0.0869, aux.acc_seg: 74.2740, loss: 0.2210 +2022-05-05 19:09:19,036 - mmseg - INFO - Saving checkpoint at 57000 iterations +2022-05-05 19:09:39,503 - mmseg - INFO - Exp name: upernet_beit_adapter_large_512_80k_cocostuff10k_ss.py +2022-05-05 19:09:39,506 - mmseg - INFO - Iter [57000/80000] lr: 4.128e-07, eta: 4:00:00, time: 0.997, data_time: 0.004, memory: 60248, decode.loss_ce: 0.1371, decode.acc_seg: 75.4025, aux.loss_ce: 0.0867, aux.acc_seg: 73.8010, loss: 0.2239 +2022-05-05 19:10:09,273 - mmseg - INFO - Iter [57050/80000] lr: 4.119e-07, eta: 3:59:28, time: 0.596, data_time: 0.006, memory: 60248, decode.loss_ce: 0.1400, decode.acc_seg: 76.8601, aux.loss_ce: 0.0903, aux.acc_seg: 75.0279, loss: 0.2304 +2022-05-05 19:10:39,086 - mmseg - INFO - Iter [57100/80000] lr: 4.110e-07, eta: 3:58:56, time: 0.597, data_time: 0.005, memory: 60248, decode.loss_ce: 0.1496, decode.acc_seg: 76.4479, aux.loss_ce: 0.0964, aux.acc_seg: 74.4786, loss: 0.2460 +2022-05-05 19:11:08,463 - mmseg - INFO - Iter [57150/80000] lr: 4.101e-07, eta: 3:58:24, time: 0.587, data_time: 0.004, memory: 60248, decode.loss_ce: 0.1455, decode.acc_seg: 74.9136, aux.loss_ce: 0.0932, aux.acc_seg: 72.9207, loss: 0.2386 +2022-05-05 19:11:37,879 - mmseg - INFO - Iter [57200/80000] lr: 4.092e-07, eta: 3:57:52, time: 0.588, data_time: 0.005, memory: 60248, decode.loss_ce: 0.1416, decode.acc_seg: 76.7522, aux.loss_ce: 0.0922, aux.acc_seg: 74.8318, loss: 0.2338 +2022-05-05 19:12:07,288 - mmseg - INFO - Iter [57250/80000] lr: 4.083e-07, eta: 3:57:20, time: 0.588, data_time: 0.005, memory: 60248, decode.loss_ce: 0.1350, decode.acc_seg: 74.7294, aux.loss_ce: 0.0877, aux.acc_seg: 72.8756, loss: 0.2228 +2022-05-05 19:12:36,850 - mmseg - INFO - Iter [57300/80000] lr: 4.074e-07, eta: 3:56:48, time: 0.591, data_time: 0.005, memory: 60248, decode.loss_ce: 0.1442, decode.acc_seg: 75.0931, aux.loss_ce: 0.0922, aux.acc_seg: 73.1665, loss: 0.2364 +2022-05-05 19:13:08,997 - mmseg - INFO - Iter [57350/80000] lr: 4.065e-07, eta: 3:56:17, time: 0.641, data_time: 0.053, memory: 60248, decode.loss_ce: 0.1452, decode.acc_seg: 75.4605, aux.loss_ce: 0.0928, aux.acc_seg: 73.5835, loss: 0.2380 +2022-05-05 19:13:38,596 - mmseg - INFO - Iter [57400/80000] lr: 4.056e-07, eta: 3:55:45, time: 0.594, data_time: 0.006, memory: 60248, decode.loss_ce: 0.1408, decode.acc_seg: 75.4692, aux.loss_ce: 0.0921, aux.acc_seg: 73.4578, loss: 0.2329 +2022-05-05 19:14:08,203 - mmseg - INFO - Iter [57450/80000] lr: 4.047e-07, eta: 3:55:13, time: 0.592, data_time: 0.005, memory: 60248, decode.loss_ce: 0.1468, decode.acc_seg: 77.1358, aux.loss_ce: 0.0955, aux.acc_seg: 75.1499, loss: 0.2423 +2022-05-05 19:14:37,513 - mmseg - INFO - Iter [57500/80000] lr: 4.038e-07, eta: 3:54:41, time: 0.586, data_time: 0.005, memory: 60248, decode.loss_ce: 0.1422, decode.acc_seg: 75.6483, aux.loss_ce: 0.0910, aux.acc_seg: 73.7588, loss: 0.2333 +2022-05-05 19:15:06,966 - mmseg - INFO - Iter [57550/80000] lr: 4.029e-07, eta: 3:54:09, time: 0.589, data_time: 0.005, memory: 60248, decode.loss_ce: 0.1434, decode.acc_seg: 75.7377, aux.loss_ce: 0.0908, aux.acc_seg: 73.9917, loss: 0.2342 +2022-05-05 19:15:36,495 - mmseg - INFO - Iter [57600/80000] lr: 4.020e-07, eta: 3:53:37, time: 0.591, data_time: 0.004, memory: 60248, decode.loss_ce: 0.1297, decode.acc_seg: 75.8712, aux.loss_ce: 0.0840, aux.acc_seg: 74.2203, loss: 0.2136 +2022-05-05 19:16:05,996 - mmseg - INFO - Iter [57650/80000] lr: 4.011e-07, eta: 3:53:05, time: 0.590, data_time: 0.004, memory: 60248, decode.loss_ce: 0.1515, decode.acc_seg: 74.8017, aux.loss_ce: 0.0958, aux.acc_seg: 72.8463, loss: 0.2474 +2022-05-05 19:16:35,379 - mmseg - INFO - Iter [57700/80000] lr: 4.002e-07, eta: 3:52:33, time: 0.588, data_time: 0.005, memory: 60248, decode.loss_ce: 0.1370, decode.acc_seg: 75.9024, aux.loss_ce: 0.0888, aux.acc_seg: 74.0804, loss: 0.2258 +2022-05-05 19:17:04,864 - mmseg - INFO - Iter [57750/80000] lr: 3.993e-07, eta: 3:52:01, time: 0.590, data_time: 0.004, memory: 60248, decode.loss_ce: 0.1375, decode.acc_seg: 76.5184, aux.loss_ce: 0.0903, aux.acc_seg: 74.5084, loss: 0.2277 +2022-05-05 19:17:34,468 - mmseg - INFO - Iter [57800/80000] lr: 3.985e-07, eta: 3:51:29, time: 0.592, data_time: 0.005, memory: 60248, decode.loss_ce: 0.1356, decode.acc_seg: 77.0739, aux.loss_ce: 0.0876, aux.acc_seg: 75.2562, loss: 0.2232 +2022-05-05 19:18:03,914 - mmseg - INFO - Iter [57850/80000] lr: 3.976e-07, eta: 3:50:57, time: 0.589, data_time: 0.005, memory: 60248, decode.loss_ce: 0.1376, decode.acc_seg: 76.4423, aux.loss_ce: 0.0893, aux.acc_seg: 74.5295, loss: 0.2270 +2022-05-05 19:18:36,231 - mmseg - INFO - Iter [57900/80000] lr: 3.967e-07, eta: 3:50:26, time: 0.646, data_time: 0.056, memory: 60248, decode.loss_ce: 0.1300, decode.acc_seg: 76.8702, aux.loss_ce: 0.0876, aux.acc_seg: 74.8819, loss: 0.2177 +2022-05-05 19:19:05,664 - mmseg - INFO - Iter [57950/80000] lr: 3.958e-07, eta: 3:49:54, time: 0.589, data_time: 0.005, memory: 60248, decode.loss_ce: 0.1355, decode.acc_seg: 75.1765, aux.loss_ce: 0.0910, aux.acc_seg: 73.2478, loss: 0.2265 +2022-05-05 19:19:35,264 - mmseg - INFO - Saving checkpoint at 58000 iterations +2022-05-05 19:19:55,652 - mmseg - INFO - Exp name: upernet_beit_adapter_large_512_80k_cocostuff10k_ss.py +2022-05-05 19:19:55,659 - mmseg - INFO - Iter [58000/80000] lr: 3.949e-07, eta: 3:49:30, time: 0.998, data_time: 0.004, memory: 60248, decode.loss_ce: 0.1361, decode.acc_seg: 75.1824, aux.loss_ce: 0.0888, aux.acc_seg: 73.3801, loss: 0.2249 +2022-05-05 19:20:25,368 - mmseg - INFO - Iter [58050/80000] lr: 3.940e-07, eta: 3:48:58, time: 0.596, data_time: 0.006, memory: 60248, decode.loss_ce: 0.1341, decode.acc_seg: 76.0451, aux.loss_ce: 0.0881, aux.acc_seg: 74.1866, loss: 0.2222 +2022-05-05 19:20:54,904 - mmseg - INFO - Iter [58100/80000] lr: 3.931e-07, eta: 3:48:26, time: 0.591, data_time: 0.005, memory: 60248, decode.loss_ce: 0.1416, decode.acc_seg: 75.4805, aux.loss_ce: 0.0918, aux.acc_seg: 73.5255, loss: 0.2334 +2022-05-05 19:21:24,494 - mmseg - INFO - Iter [58150/80000] lr: 3.922e-07, eta: 3:47:54, time: 0.592, data_time: 0.004, memory: 60248, decode.loss_ce: 0.1432, decode.acc_seg: 74.9851, aux.loss_ce: 0.0919, aux.acc_seg: 73.1043, loss: 0.2351 +2022-05-05 19:21:54,017 - mmseg - INFO - Iter [58200/80000] lr: 3.913e-07, eta: 3:47:22, time: 0.591, data_time: 0.004, memory: 60248, decode.loss_ce: 0.1260, decode.acc_seg: 75.7214, aux.loss_ce: 0.0801, aux.acc_seg: 74.2069, loss: 0.2061 +2022-05-05 19:22:23,684 - mmseg - INFO - Iter [58250/80000] lr: 3.904e-07, eta: 3:46:50, time: 0.593, data_time: 0.007, memory: 60248, decode.loss_ce: 0.1297, decode.acc_seg: 76.3579, aux.loss_ce: 0.0839, aux.acc_seg: 74.6498, loss: 0.2136 +2022-05-05 19:22:53,008 - mmseg - INFO - Iter [58300/80000] lr: 3.895e-07, eta: 3:46:18, time: 0.586, data_time: 0.005, memory: 60248, decode.loss_ce: 0.1374, decode.acc_seg: 76.6809, aux.loss_ce: 0.0895, aux.acc_seg: 74.7274, loss: 0.2269 +2022-05-05 19:23:22,598 - mmseg - INFO - Iter [58350/80000] lr: 3.886e-07, eta: 3:45:46, time: 0.592, data_time: 0.004, memory: 60248, decode.loss_ce: 0.1360, decode.acc_seg: 76.1304, aux.loss_ce: 0.0871, aux.acc_seg: 74.3520, loss: 0.2232 +2022-05-05 19:23:51,945 - mmseg - INFO - Iter [58400/80000] lr: 3.877e-07, eta: 3:45:14, time: 0.587, data_time: 0.005, memory: 60248, decode.loss_ce: 0.1374, decode.acc_seg: 75.7855, aux.loss_ce: 0.0868, aux.acc_seg: 74.0773, loss: 0.2242 +2022-05-05 19:24:23,932 - mmseg - INFO - Iter [58450/80000] lr: 3.868e-07, eta: 3:44:43, time: 0.640, data_time: 0.054, memory: 60248, decode.loss_ce: 0.1331, decode.acc_seg: 75.4776, aux.loss_ce: 0.0877, aux.acc_seg: 73.5561, loss: 0.2208 +2022-05-05 19:24:53,180 - mmseg - INFO - Iter [58500/80000] lr: 3.859e-07, eta: 3:44:11, time: 0.585, data_time: 0.004, memory: 60248, decode.loss_ce: 0.1400, decode.acc_seg: 75.1746, aux.loss_ce: 0.0915, aux.acc_seg: 73.3144, loss: 0.2315 +2022-05-05 19:25:22,599 - mmseg - INFO - Iter [58550/80000] lr: 3.850e-07, eta: 3:43:39, time: 0.588, data_time: 0.005, memory: 60248, decode.loss_ce: 0.1328, decode.acc_seg: 75.7301, aux.loss_ce: 0.0877, aux.acc_seg: 73.9393, loss: 0.2205 +2022-05-05 19:25:52,006 - mmseg - INFO - Iter [58600/80000] lr: 3.841e-07, eta: 3:43:07, time: 0.588, data_time: 0.004, memory: 60248, decode.loss_ce: 0.1319, decode.acc_seg: 75.6132, aux.loss_ce: 0.0854, aux.acc_seg: 73.7926, loss: 0.2173 +2022-05-05 19:26:21,683 - mmseg - INFO - Iter [58650/80000] lr: 3.832e-07, eta: 3:42:36, time: 0.593, data_time: 0.004, memory: 60248, decode.loss_ce: 0.1326, decode.acc_seg: 74.5789, aux.loss_ce: 0.0868, aux.acc_seg: 72.6945, loss: 0.2194 +2022-05-05 19:26:51,064 - mmseg - INFO - Iter [58700/80000] lr: 3.823e-07, eta: 3:42:04, time: 0.588, data_time: 0.004, memory: 60248, decode.loss_ce: 0.1336, decode.acc_seg: 76.3590, aux.loss_ce: 0.0883, aux.acc_seg: 74.3867, loss: 0.2219 +2022-05-05 19:27:20,395 - mmseg - INFO - Iter [58750/80000] lr: 3.814e-07, eta: 3:41:32, time: 0.587, data_time: 0.004, memory: 60248, decode.loss_ce: 0.1351, decode.acc_seg: 76.5179, aux.loss_ce: 0.0876, aux.acc_seg: 74.7024, loss: 0.2226 +2022-05-05 19:27:49,975 - mmseg - INFO - Iter [58800/80000] lr: 3.805e-07, eta: 3:41:00, time: 0.592, data_time: 0.004, memory: 60248, decode.loss_ce: 0.1445, decode.acc_seg: 75.2339, aux.loss_ce: 0.0905, aux.acc_seg: 73.3304, loss: 0.2349 +2022-05-05 19:28:19,508 - mmseg - INFO - Iter [58850/80000] lr: 3.796e-07, eta: 3:40:28, time: 0.591, data_time: 0.004, memory: 60248, decode.loss_ce: 0.1276, decode.acc_seg: 76.0272, aux.loss_ce: 0.0833, aux.acc_seg: 74.1558, loss: 0.2109 +2022-05-05 19:28:48,996 - mmseg - INFO - Iter [58900/80000] lr: 3.787e-07, eta: 3:39:56, time: 0.590, data_time: 0.005, memory: 60248, decode.loss_ce: 0.1345, decode.acc_seg: 76.0126, aux.loss_ce: 0.0873, aux.acc_seg: 74.2179, loss: 0.2218 +2022-05-05 19:29:18,622 - mmseg - INFO - Iter [58950/80000] lr: 3.778e-07, eta: 3:39:24, time: 0.593, data_time: 0.004, memory: 60248, decode.loss_ce: 0.1394, decode.acc_seg: 76.0117, aux.loss_ce: 0.0883, aux.acc_seg: 74.2314, loss: 0.2277 +2022-05-05 19:29:47,956 - mmseg - INFO - Saving checkpoint at 59000 iterations +2022-05-05 19:30:09,766 - mmseg - INFO - Exp name: upernet_beit_adapter_large_512_80k_cocostuff10k_ss.py +2022-05-05 19:30:09,768 - mmseg - INFO - Iter [59000/80000] lr: 3.769e-07, eta: 3:39:00, time: 1.020, data_time: 0.004, memory: 60248, decode.loss_ce: 0.1466, decode.acc_seg: 75.0840, aux.loss_ce: 0.0933, aux.acc_seg: 73.2066, loss: 0.2399 +2022-05-05 19:30:42,098 - mmseg - INFO - Iter [59050/80000] lr: 3.760e-07, eta: 3:38:29, time: 0.650, data_time: 0.055, memory: 60248, decode.loss_ce: 0.1385, decode.acc_seg: 76.5115, aux.loss_ce: 0.0889, aux.acc_seg: 74.6019, loss: 0.2274 +2022-05-05 19:31:11,551 - mmseg - INFO - Iter [59100/80000] lr: 3.751e-07, eta: 3:37:57, time: 0.589, data_time: 0.005, memory: 60248, decode.loss_ce: 0.1291, decode.acc_seg: 75.7284, aux.loss_ce: 0.0866, aux.acc_seg: 73.6659, loss: 0.2157 +2022-05-05 19:31:40,984 - mmseg - INFO - Iter [59150/80000] lr: 3.742e-07, eta: 3:37:25, time: 0.589, data_time: 0.004, memory: 60248, decode.loss_ce: 0.1336, decode.acc_seg: 76.1163, aux.loss_ce: 0.0865, aux.acc_seg: 74.3416, loss: 0.2201 +2022-05-05 19:32:11,047 - mmseg - INFO - Iter [59200/80000] lr: 3.733e-07, eta: 3:36:53, time: 0.601, data_time: 0.005, memory: 60248, decode.loss_ce: 0.1386, decode.acc_seg: 76.3547, aux.loss_ce: 0.0893, aux.acc_seg: 74.5438, loss: 0.2279 +2022-05-05 19:32:40,682 - mmseg - INFO - Iter [59250/80000] lr: 3.724e-07, eta: 3:36:21, time: 0.593, data_time: 0.005, memory: 60248, decode.loss_ce: 0.1308, decode.acc_seg: 75.9739, aux.loss_ce: 0.0843, aux.acc_seg: 74.2134, loss: 0.2151 +2022-05-05 19:33:10,269 - mmseg - INFO - Iter [59300/80000] lr: 3.715e-07, eta: 3:35:50, time: 0.592, data_time: 0.004, memory: 60248, decode.loss_ce: 0.1291, decode.acc_seg: 76.1398, aux.loss_ce: 0.0826, aux.acc_seg: 74.5439, loss: 0.2117 +2022-05-05 19:33:39,720 - mmseg - INFO - Iter [59350/80000] lr: 3.706e-07, eta: 3:35:18, time: 0.589, data_time: 0.004, memory: 60248, decode.loss_ce: 0.1368, decode.acc_seg: 76.1497, aux.loss_ce: 0.0880, aux.acc_seg: 74.2536, loss: 0.2248 +2022-05-05 19:34:09,093 - mmseg - INFO - Iter [59400/80000] lr: 3.697e-07, eta: 3:34:46, time: 0.587, data_time: 0.004, memory: 60248, decode.loss_ce: 0.1358, decode.acc_seg: 75.6283, aux.loss_ce: 0.0885, aux.acc_seg: 73.7840, loss: 0.2243 +2022-05-05 19:34:38,597 - mmseg - INFO - Iter [59450/80000] lr: 3.688e-07, eta: 3:34:14, time: 0.590, data_time: 0.004, memory: 60248, decode.loss_ce: 0.1311, decode.acc_seg: 76.4736, aux.loss_ce: 0.0836, aux.acc_seg: 74.7126, loss: 0.2147 +2022-05-05 19:35:08,181 - mmseg - INFO - Iter [59500/80000] lr: 3.679e-07, eta: 3:33:42, time: 0.592, data_time: 0.004, memory: 60248, decode.loss_ce: 0.1392, decode.acc_seg: 76.0577, aux.loss_ce: 0.0894, aux.acc_seg: 74.4276, loss: 0.2285 +2022-05-05 19:35:37,867 - mmseg - INFO - Iter [59550/80000] lr: 3.670e-07, eta: 3:33:10, time: 0.594, data_time: 0.004, memory: 60248, decode.loss_ce: 0.1386, decode.acc_seg: 76.0031, aux.loss_ce: 0.0884, aux.acc_seg: 74.3145, loss: 0.2270 +2022-05-05 19:36:09,831 - mmseg - INFO - Iter [59600/80000] lr: 3.661e-07, eta: 3:32:39, time: 0.639, data_time: 0.054, memory: 60248, decode.loss_ce: 0.1410, decode.acc_seg: 75.9261, aux.loss_ce: 0.0909, aux.acc_seg: 74.0192, loss: 0.2319 +2022-05-05 19:36:39,661 - mmseg - INFO - Iter [59650/80000] lr: 3.652e-07, eta: 3:32:07, time: 0.597, data_time: 0.004, memory: 60248, decode.loss_ce: 0.1338, decode.acc_seg: 77.3941, aux.loss_ce: 0.0847, aux.acc_seg: 75.8255, loss: 0.2185 +2022-05-05 19:37:09,221 - mmseg - INFO - Iter [59700/80000] lr: 3.644e-07, eta: 3:31:35, time: 0.591, data_time: 0.004, memory: 60248, decode.loss_ce: 0.1359, decode.acc_seg: 75.5006, aux.loss_ce: 0.0862, aux.acc_seg: 73.7132, loss: 0.2221 +2022-05-05 19:37:39,104 - mmseg - INFO - Iter [59750/80000] lr: 3.635e-07, eta: 3:31:04, time: 0.596, data_time: 0.004, memory: 60248, decode.loss_ce: 0.1406, decode.acc_seg: 76.8370, aux.loss_ce: 0.0900, aux.acc_seg: 74.9950, loss: 0.2305 +2022-05-05 19:38:09,023 - mmseg - INFO - Iter [59800/80000] lr: 3.626e-07, eta: 3:30:32, time: 0.600, data_time: 0.006, memory: 60248, decode.loss_ce: 0.1404, decode.acc_seg: 76.1284, aux.loss_ce: 0.0894, aux.acc_seg: 74.3448, loss: 0.2298 +2022-05-05 19:38:38,718 - mmseg - INFO - Iter [59850/80000] lr: 3.617e-07, eta: 3:30:00, time: 0.594, data_time: 0.004, memory: 60248, decode.loss_ce: 0.1326, decode.acc_seg: 74.4479, aux.loss_ce: 0.0872, aux.acc_seg: 72.7130, loss: 0.2199 +2022-05-05 19:39:08,386 - mmseg - INFO - Iter [59900/80000] lr: 3.608e-07, eta: 3:29:28, time: 0.593, data_time: 0.005, memory: 60248, decode.loss_ce: 0.1336, decode.acc_seg: 76.4029, aux.loss_ce: 0.0854, aux.acc_seg: 74.5748, loss: 0.2190 +2022-05-05 19:39:37,882 - mmseg - INFO - Iter [59950/80000] lr: 3.599e-07, eta: 3:28:57, time: 0.590, data_time: 0.004, memory: 60248, decode.loss_ce: 0.1304, decode.acc_seg: 76.6163, aux.loss_ce: 0.0858, aux.acc_seg: 74.6443, loss: 0.2162 +2022-05-05 19:40:07,440 - mmseg - INFO - Saving checkpoint at 60000 iterations +2022-05-05 19:40:27,649 - mmseg - INFO - Exp name: upernet_beit_adapter_large_512_80k_cocostuff10k_ss.py +2022-05-05 19:40:27,651 - mmseg - INFO - Iter [60000/80000] lr: 3.590e-07, eta: 3:28:31, time: 0.993, data_time: 0.004, memory: 60248, decode.loss_ce: 0.1304, decode.acc_seg: 76.2593, aux.loss_ce: 0.0864, aux.acc_seg: 74.3078, loss: 0.2167 +2022-05-05 19:40:57,377 - mmseg - INFO - Iter [60050/80000] lr: 3.581e-07, eta: 3:28:00, time: 0.597, data_time: 0.007, memory: 60248, decode.loss_ce: 0.1363, decode.acc_seg: 76.4959, aux.loss_ce: 0.0882, aux.acc_seg: 74.6639, loss: 0.2245 +2022-05-05 19:41:26,754 - mmseg - INFO - Iter [60100/80000] lr: 3.572e-07, eta: 3:27:28, time: 0.587, data_time: 0.004, memory: 60248, decode.loss_ce: 0.1314, decode.acc_seg: 74.6679, aux.loss_ce: 0.0863, aux.acc_seg: 72.9415, loss: 0.2178 +2022-05-05 19:41:58,691 - mmseg - INFO - Iter [60150/80000] lr: 3.563e-07, eta: 3:26:57, time: 0.639, data_time: 0.053, memory: 60248, decode.loss_ce: 0.1365, decode.acc_seg: 75.4391, aux.loss_ce: 0.0876, aux.acc_seg: 73.6397, loss: 0.2241 +2022-05-05 19:42:28,185 - mmseg - INFO - Iter [60200/80000] lr: 3.554e-07, eta: 3:26:25, time: 0.590, data_time: 0.005, memory: 60248, decode.loss_ce: 0.1352, decode.acc_seg: 76.3430, aux.loss_ce: 0.0869, aux.acc_seg: 74.5125, loss: 0.2221 +2022-05-05 19:42:57,538 - mmseg - INFO - Iter [60250/80000] lr: 3.545e-07, eta: 3:25:53, time: 0.587, data_time: 0.004, memory: 60248, decode.loss_ce: 0.1351, decode.acc_seg: 76.3991, aux.loss_ce: 0.0873, aux.acc_seg: 74.7112, loss: 0.2224 +2022-05-05 19:43:26,841 - mmseg - INFO - Iter [60300/80000] lr: 3.536e-07, eta: 3:25:21, time: 0.586, data_time: 0.005, memory: 60248, decode.loss_ce: 0.1269, decode.acc_seg: 76.2265, aux.loss_ce: 0.0830, aux.acc_seg: 74.4702, loss: 0.2099 +2022-05-05 19:43:56,324 - mmseg - INFO - Iter [60350/80000] lr: 3.527e-07, eta: 3:24:49, time: 0.589, data_time: 0.004, memory: 60248, decode.loss_ce: 0.1381, decode.acc_seg: 77.9713, aux.loss_ce: 0.0890, aux.acc_seg: 76.1398, loss: 0.2271 +2022-05-05 19:44:25,795 - mmseg - INFO - Iter [60400/80000] lr: 3.518e-07, eta: 3:24:17, time: 0.590, data_time: 0.005, memory: 60248, decode.loss_ce: 0.1318, decode.acc_seg: 75.4827, aux.loss_ce: 0.0873, aux.acc_seg: 73.5218, loss: 0.2191 +2022-05-05 19:44:55,387 - mmseg - INFO - Iter [60450/80000] lr: 3.509e-07, eta: 3:23:45, time: 0.592, data_time: 0.004, memory: 60248, decode.loss_ce: 0.1351, decode.acc_seg: 76.5473, aux.loss_ce: 0.0875, aux.acc_seg: 74.7123, loss: 0.2226 +2022-05-05 19:45:24,982 - mmseg - INFO - Iter [60500/80000] lr: 3.500e-07, eta: 3:23:14, time: 0.592, data_time: 0.004, memory: 60248, decode.loss_ce: 0.1335, decode.acc_seg: 76.8992, aux.loss_ce: 0.0865, aux.acc_seg: 75.1300, loss: 0.2201 +2022-05-05 19:45:54,747 - mmseg - INFO - Iter [60550/80000] lr: 3.491e-07, eta: 3:22:42, time: 0.596, data_time: 0.004, memory: 60248, decode.loss_ce: 0.1394, decode.acc_seg: 76.5659, aux.loss_ce: 0.0902, aux.acc_seg: 74.5776, loss: 0.2297 +2022-05-05 19:46:24,219 - mmseg - INFO - Iter [60600/80000] lr: 3.482e-07, eta: 3:22:10, time: 0.589, data_time: 0.005, memory: 60248, decode.loss_ce: 0.1367, decode.acc_seg: 77.3173, aux.loss_ce: 0.0875, aux.acc_seg: 75.5385, loss: 0.2242 +2022-05-05 19:46:53,645 - mmseg - INFO - Iter [60650/80000] lr: 3.473e-07, eta: 3:21:38, time: 0.589, data_time: 0.004, memory: 60248, decode.loss_ce: 0.1337, decode.acc_seg: 75.5830, aux.loss_ce: 0.0848, aux.acc_seg: 73.8953, loss: 0.2185 +2022-05-05 19:47:25,734 - mmseg - INFO - Iter [60700/80000] lr: 3.464e-07, eta: 3:21:07, time: 0.642, data_time: 0.055, memory: 60248, decode.loss_ce: 0.1274, decode.acc_seg: 76.2373, aux.loss_ce: 0.0812, aux.acc_seg: 74.6594, loss: 0.2086 +2022-05-05 19:47:55,291 - mmseg - INFO - Iter [60750/80000] lr: 3.455e-07, eta: 3:20:35, time: 0.591, data_time: 0.004, memory: 60248, decode.loss_ce: 0.1349, decode.acc_seg: 77.2484, aux.loss_ce: 0.0881, aux.acc_seg: 75.3255, loss: 0.2230 +2022-05-05 19:48:25,046 - mmseg - INFO - Iter [60800/80000] lr: 3.446e-07, eta: 3:20:04, time: 0.595, data_time: 0.005, memory: 60248, decode.loss_ce: 0.1322, decode.acc_seg: 76.2898, aux.loss_ce: 0.0867, aux.acc_seg: 74.4267, loss: 0.2189 +2022-05-05 19:48:54,430 - mmseg - INFO - Iter [60850/80000] lr: 3.437e-07, eta: 3:19:32, time: 0.588, data_time: 0.005, memory: 60248, decode.loss_ce: 0.1346, decode.acc_seg: 76.7209, aux.loss_ce: 0.0866, aux.acc_seg: 74.9166, loss: 0.2212 +2022-05-05 19:49:24,066 - mmseg - INFO - Iter [60900/80000] lr: 3.428e-07, eta: 3:19:00, time: 0.593, data_time: 0.006, memory: 60248, decode.loss_ce: 0.1265, decode.acc_seg: 75.9809, aux.loss_ce: 0.0817, aux.acc_seg: 74.3467, loss: 0.2082 +2022-05-05 19:49:53,834 - mmseg - INFO - Iter [60950/80000] lr: 3.419e-07, eta: 3:18:28, time: 0.595, data_time: 0.005, memory: 60248, decode.loss_ce: 0.1391, decode.acc_seg: 75.8466, aux.loss_ce: 0.0896, aux.acc_seg: 73.8959, loss: 0.2287 +2022-05-05 19:50:23,344 - mmseg - INFO - Saving checkpoint at 61000 iterations +2022-05-05 19:50:43,696 - mmseg - INFO - Exp name: upernet_beit_adapter_large_512_80k_cocostuff10k_ss.py +2022-05-05 19:50:43,699 - mmseg - INFO - Iter [61000/80000] lr: 3.410e-07, eta: 3:18:03, time: 0.996, data_time: 0.005, memory: 60248, decode.loss_ce: 0.1394, decode.acc_seg: 76.7508, aux.loss_ce: 0.0917, aux.acc_seg: 74.7063, loss: 0.2311 +2022-05-05 19:51:13,251 - mmseg - INFO - Iter [61050/80000] lr: 3.401e-07, eta: 3:17:31, time: 0.592, data_time: 0.005, memory: 60248, decode.loss_ce: 0.1225, decode.acc_seg: 76.7620, aux.loss_ce: 0.0797, aux.acc_seg: 75.0260, loss: 0.2023 +2022-05-05 19:51:42,860 - mmseg - INFO - Iter [61100/80000] lr: 3.392e-07, eta: 3:16:59, time: 0.592, data_time: 0.004, memory: 60248, decode.loss_ce: 0.1329, decode.acc_seg: 77.0101, aux.loss_ce: 0.0883, aux.acc_seg: 75.1195, loss: 0.2212 +2022-05-05 19:52:12,610 - mmseg - INFO - Iter [61150/80000] lr: 3.383e-07, eta: 3:16:28, time: 0.595, data_time: 0.004, memory: 60248, decode.loss_ce: 0.1384, decode.acc_seg: 76.1557, aux.loss_ce: 0.0907, aux.acc_seg: 74.2819, loss: 0.2290 +2022-05-05 19:52:42,530 - mmseg - INFO - Iter [61200/80000] lr: 3.374e-07, eta: 3:15:56, time: 0.598, data_time: 0.006, memory: 60248, decode.loss_ce: 0.1356, decode.acc_seg: 76.0864, aux.loss_ce: 0.0895, aux.acc_seg: 74.0567, loss: 0.2251 +2022-05-05 19:53:12,064 - mmseg - INFO - Iter [61250/80000] lr: 3.365e-07, eta: 3:15:24, time: 0.591, data_time: 0.004, memory: 60248, decode.loss_ce: 0.1408, decode.acc_seg: 75.4324, aux.loss_ce: 0.0886, aux.acc_seg: 73.5961, loss: 0.2294 +2022-05-05 19:53:44,440 - mmseg - INFO - Iter [61300/80000] lr: 3.356e-07, eta: 3:14:53, time: 0.648, data_time: 0.055, memory: 60248, decode.loss_ce: 0.1250, decode.acc_seg: 76.7070, aux.loss_ce: 0.0820, aux.acc_seg: 74.9682, loss: 0.2070 +2022-05-05 19:54:13,957 - mmseg - INFO - Iter [61350/80000] lr: 3.347e-07, eta: 3:14:21, time: 0.590, data_time: 0.005, memory: 60248, decode.loss_ce: 0.1277, decode.acc_seg: 77.1976, aux.loss_ce: 0.0848, aux.acc_seg: 75.4054, loss: 0.2125 +2022-05-05 19:54:43,639 - mmseg - INFO - Iter [61400/80000] lr: 3.338e-07, eta: 3:13:50, time: 0.594, data_time: 0.004, memory: 60248, decode.loss_ce: 0.1373, decode.acc_seg: 75.2730, aux.loss_ce: 0.0884, aux.acc_seg: 73.3547, loss: 0.2257 +2022-05-05 19:55:13,324 - mmseg - INFO - Iter [61450/80000] lr: 3.329e-07, eta: 3:13:18, time: 0.593, data_time: 0.004, memory: 60248, decode.loss_ce: 0.1350, decode.acc_seg: 76.0365, aux.loss_ce: 0.0861, aux.acc_seg: 74.3417, loss: 0.2211 +2022-05-05 19:55:42,832 - mmseg - INFO - Iter [61500/80000] lr: 3.320e-07, eta: 3:12:46, time: 0.590, data_time: 0.005, memory: 60248, decode.loss_ce: 0.1390, decode.acc_seg: 75.7166, aux.loss_ce: 0.0871, aux.acc_seg: 73.9714, loss: 0.2261 +2022-05-05 19:56:12,494 - mmseg - INFO - Iter [61550/80000] lr: 3.311e-07, eta: 3:12:14, time: 0.593, data_time: 0.004, memory: 60248, decode.loss_ce: 0.1337, decode.acc_seg: 75.7568, aux.loss_ce: 0.0865, aux.acc_seg: 73.9648, loss: 0.2202 +2022-05-05 19:56:41,883 - mmseg - INFO - Iter [61600/80000] lr: 3.303e-07, eta: 3:11:43, time: 0.588, data_time: 0.004, memory: 60248, decode.loss_ce: 0.1401, decode.acc_seg: 76.4783, aux.loss_ce: 0.0927, aux.acc_seg: 74.4617, loss: 0.2327 +2022-05-05 19:57:11,684 - mmseg - INFO - Iter [61650/80000] lr: 3.294e-07, eta: 3:11:11, time: 0.596, data_time: 0.006, memory: 60248, decode.loss_ce: 0.1340, decode.acc_seg: 76.6712, aux.loss_ce: 0.0854, aux.acc_seg: 75.0259, loss: 0.2194 +2022-05-05 19:57:41,414 - mmseg - INFO - Iter [61700/80000] lr: 3.285e-07, eta: 3:10:39, time: 0.595, data_time: 0.004, memory: 60248, decode.loss_ce: 0.1284, decode.acc_seg: 75.3958, aux.loss_ce: 0.0880, aux.acc_seg: 73.3918, loss: 0.2164 +2022-05-05 19:58:11,042 - mmseg - INFO - Iter [61750/80000] lr: 3.276e-07, eta: 3:10:07, time: 0.593, data_time: 0.004, memory: 60248, decode.loss_ce: 0.1279, decode.acc_seg: 77.2453, aux.loss_ce: 0.0836, aux.acc_seg: 75.5373, loss: 0.2115 +2022-05-05 19:58:40,840 - mmseg - INFO - Iter [61800/80000] lr: 3.267e-07, eta: 3:09:36, time: 0.596, data_time: 0.004, memory: 60248, decode.loss_ce: 0.1379, decode.acc_seg: 76.9787, aux.loss_ce: 0.0870, aux.acc_seg: 75.2255, loss: 0.2249 +2022-05-05 19:59:15,208 - mmseg - INFO - Iter [61850/80000] lr: 3.258e-07, eta: 3:09:05, time: 0.687, data_time: 0.052, memory: 60248, decode.loss_ce: 0.1257, decode.acc_seg: 76.7894, aux.loss_ce: 0.0818, aux.acc_seg: 75.0649, loss: 0.2075 +2022-05-05 19:59:44,780 - mmseg - INFO - Iter [61900/80000] lr: 3.249e-07, eta: 3:08:34, time: 0.591, data_time: 0.006, memory: 60248, decode.loss_ce: 0.1253, decode.acc_seg: 77.4245, aux.loss_ce: 0.0801, aux.acc_seg: 75.7601, loss: 0.2054 +2022-05-05 20:00:14,160 - mmseg - INFO - Iter [61950/80000] lr: 3.240e-07, eta: 3:08:02, time: 0.587, data_time: 0.004, memory: 60248, decode.loss_ce: 0.1367, decode.acc_seg: 77.1692, aux.loss_ce: 0.0894, aux.acc_seg: 75.3254, loss: 0.2261 +2022-05-05 20:00:43,573 - mmseg - INFO - Saving checkpoint at 62000 iterations +2022-05-05 20:01:04,744 - mmseg - INFO - Exp name: upernet_beit_adapter_large_512_80k_cocostuff10k_ss.py +2022-05-05 20:01:04,746 - mmseg - INFO - Iter [62000/80000] lr: 3.231e-07, eta: 3:07:36, time: 1.010, data_time: 0.004, memory: 60248, decode.loss_ce: 0.1336, decode.acc_seg: 75.6197, aux.loss_ce: 0.0886, aux.acc_seg: 73.7098, loss: 0.2222 +2022-05-05 20:01:34,616 - mmseg - INFO - Iter [62050/80000] lr: 3.222e-07, eta: 3:07:04, time: 0.597, data_time: 0.006, memory: 60248, decode.loss_ce: 0.1324, decode.acc_seg: 76.0249, aux.loss_ce: 0.0857, aux.acc_seg: 74.2897, loss: 0.2181 +2022-05-05 20:02:03,912 - mmseg - INFO - Iter [62100/80000] lr: 3.213e-07, eta: 3:06:33, time: 0.588, data_time: 0.007, memory: 60248, decode.loss_ce: 0.1317, decode.acc_seg: 76.3958, aux.loss_ce: 0.0852, aux.acc_seg: 74.6324, loss: 0.2169 +2022-05-05 20:02:33,423 - mmseg - INFO - Iter [62150/80000] lr: 3.204e-07, eta: 3:06:01, time: 0.590, data_time: 0.005, memory: 60248, decode.loss_ce: 0.1433, decode.acc_seg: 76.4857, aux.loss_ce: 0.0901, aux.acc_seg: 74.6979, loss: 0.2334 +2022-05-05 20:03:02,876 - mmseg - INFO - Iter [62200/80000] lr: 3.195e-07, eta: 3:05:29, time: 0.589, data_time: 0.005, memory: 60248, decode.loss_ce: 0.1286, decode.acc_seg: 75.0317, aux.loss_ce: 0.0850, aux.acc_seg: 73.1050, loss: 0.2136 +2022-05-05 20:03:32,451 - mmseg - INFO - Iter [62250/80000] lr: 3.186e-07, eta: 3:04:57, time: 0.591, data_time: 0.005, memory: 60248, decode.loss_ce: 0.1296, decode.acc_seg: 75.9665, aux.loss_ce: 0.0840, aux.acc_seg: 74.1390, loss: 0.2136 +2022-05-05 20:04:01,919 - mmseg - INFO - Iter [62300/80000] lr: 3.177e-07, eta: 3:04:26, time: 0.589, data_time: 0.004, memory: 60248, decode.loss_ce: 0.1509, decode.acc_seg: 75.6143, aux.loss_ce: 0.0924, aux.acc_seg: 73.6934, loss: 0.2433 +2022-05-05 20:04:31,337 - mmseg - INFO - Iter [62350/80000] lr: 3.168e-07, eta: 3:03:54, time: 0.588, data_time: 0.005, memory: 60248, decode.loss_ce: 0.1401, decode.acc_seg: 76.9958, aux.loss_ce: 0.0918, aux.acc_seg: 75.0278, loss: 0.2318 +2022-05-05 20:05:03,413 - mmseg - INFO - Iter [62400/80000] lr: 3.159e-07, eta: 3:03:23, time: 0.641, data_time: 0.055, memory: 60248, decode.loss_ce: 0.1404, decode.acc_seg: 76.0673, aux.loss_ce: 0.0910, aux.acc_seg: 74.2147, loss: 0.2315 +2022-05-05 20:05:32,723 - mmseg - INFO - Iter [62450/80000] lr: 3.150e-07, eta: 3:02:51, time: 0.586, data_time: 0.004, memory: 60248, decode.loss_ce: 0.1256, decode.acc_seg: 76.5801, aux.loss_ce: 0.0802, aux.acc_seg: 74.8704, loss: 0.2058 +2022-05-05 20:06:02,189 - mmseg - INFO - Iter [62500/80000] lr: 3.141e-07, eta: 3:02:19, time: 0.589, data_time: 0.005, memory: 60248, decode.loss_ce: 0.1336, decode.acc_seg: 76.8812, aux.loss_ce: 0.0864, aux.acc_seg: 75.0334, loss: 0.2199 +2022-05-05 20:06:31,660 - mmseg - INFO - Iter [62550/80000] lr: 3.132e-07, eta: 3:01:47, time: 0.589, data_time: 0.004, memory: 60248, decode.loss_ce: 0.1328, decode.acc_seg: 75.1697, aux.loss_ce: 0.0856, aux.acc_seg: 73.3621, loss: 0.2184 +2022-05-05 20:07:01,373 - mmseg - INFO - Iter [62600/80000] lr: 3.123e-07, eta: 3:01:16, time: 0.594, data_time: 0.004, memory: 60248, decode.loss_ce: 0.1357, decode.acc_seg: 76.5500, aux.loss_ce: 0.0886, aux.acc_seg: 74.6557, loss: 0.2243 +2022-05-05 20:07:30,975 - mmseg - INFO - Iter [62650/80000] lr: 3.114e-07, eta: 3:00:44, time: 0.592, data_time: 0.006, memory: 60248, decode.loss_ce: 0.1351, decode.acc_seg: 77.3113, aux.loss_ce: 0.0876, aux.acc_seg: 75.4327, loss: 0.2227 +2022-05-05 20:08:00,383 - mmseg - INFO - Iter [62700/80000] lr: 3.105e-07, eta: 3:00:12, time: 0.588, data_time: 0.004, memory: 60248, decode.loss_ce: 0.1308, decode.acc_seg: 76.4016, aux.loss_ce: 0.0867, aux.acc_seg: 74.5130, loss: 0.2175 +2022-05-05 20:08:29,929 - mmseg - INFO - Iter [62750/80000] lr: 3.096e-07, eta: 2:59:41, time: 0.591, data_time: 0.005, memory: 60248, decode.loss_ce: 0.1291, decode.acc_seg: 76.6972, aux.loss_ce: 0.0865, aux.acc_seg: 74.6765, loss: 0.2155 +2022-05-05 20:08:59,294 - mmseg - INFO - Iter [62800/80000] lr: 3.087e-07, eta: 2:59:09, time: 0.587, data_time: 0.004, memory: 60248, decode.loss_ce: 0.1344, decode.acc_seg: 75.2104, aux.loss_ce: 0.0897, aux.acc_seg: 73.2875, loss: 0.2241 +2022-05-05 20:09:28,762 - mmseg - INFO - Iter [62850/80000] lr: 3.078e-07, eta: 2:58:37, time: 0.589, data_time: 0.004, memory: 60248, decode.loss_ce: 0.1246, decode.acc_seg: 75.7441, aux.loss_ce: 0.0798, aux.acc_seg: 74.1818, loss: 0.2045 +2022-05-05 20:09:58,204 - mmseg - INFO - Iter [62900/80000] lr: 3.069e-07, eta: 2:58:05, time: 0.589, data_time: 0.005, memory: 60248, decode.loss_ce: 0.1329, decode.acc_seg: 76.2379, aux.loss_ce: 0.0870, aux.acc_seg: 74.3711, loss: 0.2199 +2022-05-05 20:10:30,195 - mmseg - INFO - Iter [62950/80000] lr: 3.060e-07, eta: 2:57:34, time: 0.640, data_time: 0.052, memory: 60248, decode.loss_ce: 0.1309, decode.acc_seg: 74.0768, aux.loss_ce: 0.0862, aux.acc_seg: 72.2827, loss: 0.2172 +2022-05-05 20:10:59,669 - mmseg - INFO - Saving checkpoint at 63000 iterations +2022-05-05 20:11:21,405 - mmseg - INFO - Exp name: upernet_beit_adapter_large_512_80k_cocostuff10k_ss.py +2022-05-05 20:11:21,407 - mmseg - INFO - Iter [63000/80000] lr: 3.051e-07, eta: 2:57:08, time: 1.022, data_time: 0.005, memory: 60248, decode.loss_ce: 0.1375, decode.acc_seg: 77.3355, aux.loss_ce: 0.0905, aux.acc_seg: 75.3813, loss: 0.2280 +2022-05-05 20:11:51,286 - mmseg - INFO - Iter [63050/80000] lr: 3.042e-07, eta: 2:56:37, time: 0.600, data_time: 0.007, memory: 60248, decode.loss_ce: 0.1302, decode.acc_seg: 77.5140, aux.loss_ce: 0.0867, aux.acc_seg: 75.6896, loss: 0.2169 +2022-05-05 20:12:20,908 - mmseg - INFO - Iter [63100/80000] lr: 3.033e-07, eta: 2:56:05, time: 0.593, data_time: 0.005, memory: 60248, decode.loss_ce: 0.1312, decode.acc_seg: 77.1915, aux.loss_ce: 0.0852, aux.acc_seg: 75.3040, loss: 0.2164 +2022-05-05 20:12:50,275 - mmseg - INFO - Iter [63150/80000] lr: 3.024e-07, eta: 2:55:33, time: 0.587, data_time: 0.004, memory: 60248, decode.loss_ce: 0.1356, decode.acc_seg: 75.5783, aux.loss_ce: 0.0883, aux.acc_seg: 73.7068, loss: 0.2239 +2022-05-05 20:13:19,799 - mmseg - INFO - Iter [63200/80000] lr: 3.015e-07, eta: 2:55:02, time: 0.590, data_time: 0.005, memory: 60248, decode.loss_ce: 0.1301, decode.acc_seg: 75.8750, aux.loss_ce: 0.0844, aux.acc_seg: 74.0465, loss: 0.2145 +2022-05-05 20:13:49,357 - mmseg - INFO - Iter [63250/80000] lr: 3.006e-07, eta: 2:54:30, time: 0.591, data_time: 0.004, memory: 60248, decode.loss_ce: 0.1248, decode.acc_seg: 75.9730, aux.loss_ce: 0.0830, aux.acc_seg: 74.1972, loss: 0.2078 +2022-05-05 20:14:18,913 - mmseg - INFO - Iter [63300/80000] lr: 2.997e-07, eta: 2:53:58, time: 0.591, data_time: 0.004, memory: 60248, decode.loss_ce: 0.1255, decode.acc_seg: 75.8114, aux.loss_ce: 0.0827, aux.acc_seg: 74.0113, loss: 0.2082 +2022-05-05 20:14:48,803 - mmseg - INFO - Iter [63350/80000] lr: 2.988e-07, eta: 2:53:27, time: 0.597, data_time: 0.006, memory: 60248, decode.loss_ce: 0.1370, decode.acc_seg: 75.5328, aux.loss_ce: 0.0880, aux.acc_seg: 73.7249, loss: 0.2250 +2022-05-05 20:15:18,337 - mmseg - INFO - Iter [63400/80000] lr: 2.979e-07, eta: 2:52:55, time: 0.591, data_time: 0.005, memory: 60248, decode.loss_ce: 0.1294, decode.acc_seg: 74.3892, aux.loss_ce: 0.0832, aux.acc_seg: 72.6719, loss: 0.2126 +2022-05-05 20:15:47,813 - mmseg - INFO - Iter [63450/80000] lr: 2.970e-07, eta: 2:52:23, time: 0.590, data_time: 0.005, memory: 60248, decode.loss_ce: 0.1373, decode.acc_seg: 77.6441, aux.loss_ce: 0.0887, aux.acc_seg: 75.6851, loss: 0.2260 +2022-05-05 20:16:17,171 - mmseg - INFO - Iter [63500/80000] lr: 2.962e-07, eta: 2:51:51, time: 0.587, data_time: 0.005, memory: 60248, decode.loss_ce: 0.1364, decode.acc_seg: 77.2160, aux.loss_ce: 0.0896, aux.acc_seg: 75.3763, loss: 0.2260 +2022-05-05 20:16:49,578 - mmseg - INFO - Iter [63550/80000] lr: 2.953e-07, eta: 2:51:20, time: 0.647, data_time: 0.052, memory: 60248, decode.loss_ce: 0.1270, decode.acc_seg: 76.1567, aux.loss_ce: 0.0839, aux.acc_seg: 74.2100, loss: 0.2109 +2022-05-05 20:17:19,091 - mmseg - INFO - Iter [63600/80000] lr: 2.944e-07, eta: 2:50:49, time: 0.591, data_time: 0.005, memory: 60248, decode.loss_ce: 0.1386, decode.acc_seg: 76.5614, aux.loss_ce: 0.0908, aux.acc_seg: 74.5656, loss: 0.2295 +2022-05-05 20:17:48,493 - mmseg - INFO - Iter [63650/80000] lr: 2.935e-07, eta: 2:50:17, time: 0.588, data_time: 0.005, memory: 60248, decode.loss_ce: 0.1280, decode.acc_seg: 77.0620, aux.loss_ce: 0.0841, aux.acc_seg: 75.2269, loss: 0.2121 +2022-05-05 20:18:18,187 - mmseg - INFO - Iter [63700/80000] lr: 2.926e-07, eta: 2:49:45, time: 0.594, data_time: 0.005, memory: 60248, decode.loss_ce: 0.1382, decode.acc_seg: 75.2242, aux.loss_ce: 0.0902, aux.acc_seg: 73.2109, loss: 0.2285 +2022-05-05 20:18:47,789 - mmseg - INFO - Iter [63750/80000] lr: 2.917e-07, eta: 2:49:14, time: 0.592, data_time: 0.004, memory: 60248, decode.loss_ce: 0.1223, decode.acc_seg: 76.2471, aux.loss_ce: 0.0820, aux.acc_seg: 74.4422, loss: 0.2043 +2022-05-05 20:19:17,462 - mmseg - INFO - Iter [63800/80000] lr: 2.908e-07, eta: 2:48:42, time: 0.593, data_time: 0.005, memory: 60248, decode.loss_ce: 0.1391, decode.acc_seg: 75.1812, aux.loss_ce: 0.0898, aux.acc_seg: 73.3174, loss: 0.2289 +2022-05-05 20:19:46,938 - mmseg - INFO - Iter [63850/80000] lr: 2.899e-07, eta: 2:48:10, time: 0.590, data_time: 0.005, memory: 60248, decode.loss_ce: 0.1218, decode.acc_seg: 75.5174, aux.loss_ce: 0.0795, aux.acc_seg: 73.9196, loss: 0.2012 +2022-05-05 20:20:16,387 - mmseg - INFO - Iter [63900/80000] lr: 2.890e-07, eta: 2:47:39, time: 0.589, data_time: 0.005, memory: 60248, decode.loss_ce: 0.1328, decode.acc_seg: 76.0543, aux.loss_ce: 0.0857, aux.acc_seg: 74.1279, loss: 0.2185 +2022-05-05 20:20:46,076 - mmseg - INFO - Iter [63950/80000] lr: 2.881e-07, eta: 2:47:07, time: 0.594, data_time: 0.004, memory: 60248, decode.loss_ce: 0.1319, decode.acc_seg: 76.4463, aux.loss_ce: 0.0840, aux.acc_seg: 74.8611, loss: 0.2159 +2022-05-05 20:21:15,632 - mmseg - INFO - Saving checkpoint at 64000 iterations +2022-05-05 20:21:35,850 - mmseg - INFO - Exp name: upernet_beit_adapter_large_512_80k_cocostuff10k_ss.py +2022-05-05 20:21:35,852 - mmseg - INFO - Iter [64000/80000] lr: 2.872e-07, eta: 2:46:40, time: 0.994, data_time: 0.004, memory: 60248, decode.loss_ce: 0.1313, decode.acc_seg: 76.0661, aux.loss_ce: 0.0870, aux.acc_seg: 74.1297, loss: 0.2183 +2022-05-05 20:22:06,148 - mmseg - INFO - per class results: +2022-05-05 20:22:06,160 - mmseg - INFO - ++------------------+-------+-------+ +| Class | IoU | Acc | ++------------------+-------+-------+ +| person | 87.56 | 95.49 | +| bicycle | 75.38 | 92.36 | +| car | 63.66 | 70.7 | +| motorcycle | 87.94 | 95.73 | +| airplane | 89.17 | 96.08 | +| bus | 81.17 | 86.8 | +| train | 70.5 | 97.81 | +| truck | 76.74 | 89.78 | +| boat | 73.9 | 88.26 | +| traffic light | 76.48 | 92.27 | +| fire hydrant | 85.32 | 97.97 | +| stop sign | 90.55 | 98.39 | +| parking meter | 76.62 | 80.56 | +| bench | 53.05 | 67.48 | +| bird | 74.32 | 83.2 | +| cat | 92.15 | 97.19 | +| dog | 91.18 | 97.24 | +| horse | 89.02 | 96.42 | +| sheep | 87.96 | 92.69 | +| cow | 94.8 | 98.89 | +| elephant | 91.36 | 97.6 | +| bear | 88.26 | 96.27 | +| zebra | 90.54 | 96.8 | +| giraffe | 85.69 | 95.86 | +| backpack | 22.16 | 54.25 | +| umbrella | 78.48 | 89.29 | +| handbag | 17.18 | 24.66 | +| tie | 59.55 | 59.55 | +| suitcase | 76.91 | 96.55 | +| frisbee | 93.83 | 96.67 | +| skis | 40.91 | 60.71 | +| snowboard | 64.9 | 79.07 | +| sports ball | 84.57 | 90.91 | +| kite | 68.96 | 89.82 | +| baseball bat | 48.92 | 61.93 | +| baseball glove | 2.28 | 2.31 | +| skateboard | 67.37 | 89.09 | +| surfboard | 89.07 | 95.21 | +| tennis racket | 64.47 | 66.6 | +| bottle | 71.95 | 85.04 | +| wine glass | 83.04 | 92.69 | +| cup | 63.37 | 86.75 | +| fork | 52.35 | 72.02 | +| knife | 75.84 | 87.56 | +| spoon | 47.1 | 66.41 | +| bowl | 54.97 | 68.28 | +| banana | 76.82 | 88.38 | +| apple | 70.3 | 92.15 | +| sandwich | 86.12 | 97.34 | +| orange | 69.2 | 92.62 | +| broccoli | 94.94 | 96.96 | +| carrot | 37.9 | 67.93 | +| hot dog | 50.93 | 97.12 | +| pizza | 93.85 | 96.09 | +| donut | 68.96 | 92.26 | +| cake | 57.05 | 69.0 | +| chair | 59.33 | 76.52 | +| couch | 74.54 | 94.67 | +| potted plant | 35.85 | 46.58 | +| bed | 72.56 | 83.94 | +| dining table | 61.05 | 77.41 | +| toilet | 87.72 | 96.45 | +| tv | 68.36 | 92.65 | +| laptop | 87.0 | 98.28 | +| mouse | 70.66 | 77.81 | +| remote | 69.34 | 90.8 | +| keyboard | 82.68 | 98.57 | +| cell phone | 79.76 | 97.53 | +| microwave | 50.32 | 71.61 | +| oven | 62.65 | 86.66 | +| toaster | 44.9 | 44.9 | +| sink | 69.02 | 78.79 | +| refrigerator | 83.15 | 90.31 | +| book | 79.29 | 89.87 | +| clock | 75.73 | 87.47 | +| vase | 62.65 | 92.25 | +| scissors | 78.65 | 92.38 | +| teddy bear | 83.94 | 93.74 | +| hair drier | 0.0 | 0.0 | +| toothbrush | 16.74 | 30.79 | +| banner | 33.04 | 54.42 | +| blanket | 3.47 | 3.5 | +| branch | 6.57 | 6.7 | +| bridge | 2.57 | 3.41 | +| building-other | 55.62 | 76.54 | +| bush | 27.2 | 34.25 | +| cabinet | 20.43 | 35.76 | +| cage | 1.69 | 6.47 | +| cardboard | 23.52 | 28.27 | +| carpet | 61.67 | 78.87 | +| ceiling-other | 69.85 | 84.82 | +| ceiling-tile | 12.01 | 14.32 | +| cloth | 4.8 | 6.66 | +| clothes | 20.82 | 30.58 | +| clouds | 52.15 | 66.16 | +| counter | 35.57 | 44.04 | +| cupboard | 57.47 | 75.38 | +| curtain | 64.56 | 80.87 | +| desk-stuff | 37.21 | 42.06 | +| dirt | 32.42 | 50.29 | +| door-stuff | 48.9 | 61.5 | +| fence | 43.85 | 74.33 | +| floor-marble | 0.0 | 0.0 | +| floor-other | 43.53 | 55.12 | +| floor-stone | 23.65 | 35.67 | +| floor-tile | 59.62 | 75.54 | +| floor-wood | 71.28 | 86.42 | +| flower | 16.65 | 43.12 | +| fog | 0.0 | 0.0 | +| food-other | 40.15 | 54.59 | +| fruit | 62.67 | 72.7 | +| furniture-other | 13.97 | 18.94 | +| grass | 71.67 | 85.47 | +| gravel | 25.03 | 28.05 | +| ground-other | 7.38 | 13.82 | +| hill | 26.57 | 36.37 | +| house | 27.34 | 40.09 | +| leaves | 9.13 | 18.67 | +| light | 40.87 | 53.86 | +| mat | 20.99 | 30.08 | +| metal | 16.63 | 20.14 | +| mirror-stuff | 43.68 | 59.81 | +| moss | 0.1 | 0.1 | +| mountain | 35.36 | 54.69 | +| mud | 15.42 | 29.0 | +| napkin | 26.41 | 36.59 | +| net | 27.42 | 31.04 | +| paper | 56.91 | 67.52 | +| pavement | 56.69 | 77.14 | +| pillow | 0.0 | 0.0 | +| plant-other | 31.58 | 41.64 | +| plastic | 19.48 | 24.2 | +| platform | 42.14 | 59.13 | +| playingfield | 69.48 | 81.82 | +| railing | 14.56 | 21.72 | +| railroad | 61.96 | 90.08 | +| river | 13.63 | 18.54 | +| road | 70.15 | 80.08 | +| rock | 50.26 | 69.81 | +| roof | 5.98 | 9.69 | +| rug | 55.99 | 75.3 | +| salad | 10.02 | 10.38 | +| sand | 74.41 | 87.38 | +| sea | 75.21 | 90.29 | +| shelf | 25.27 | 36.6 | +| sky-other | 61.56 | 78.03 | +| skyscraper | 7.32 | 10.64 | +| snow | 91.9 | 95.44 | +| solid-other | nan | nan | +| stairs | 32.62 | 52.7 | +| stone | 6.27 | 11.26 | +| straw | 18.87 | 32.86 | +| structural-other | 19.65 | 26.9 | +| table | 19.06 | 28.04 | +| tent | 65.27 | 70.05 | +| textile-other | 18.93 | 23.52 | +| towel | 41.15 | 50.61 | +| tree | 78.24 | 89.44 | +| vegetable | 44.4 | 67.53 | +| wall-brick | 43.55 | 54.22 | +| wall-concrete | 20.24 | 25.77 | +| wall-other | 61.52 | 80.06 | +| wall-panel | 5.67 | 6.59 | +| wall-stone | 30.68 | 36.77 | +| wall-tile | 57.98 | 88.04 | +| wall-wood | 40.17 | 59.99 | +| water-other | 33.5 | 45.84 | +| waterdrops | nan | nan | +| window-blind | 21.8 | 41.85 | +| window-other | 46.52 | 61.51 | +| wood | 13.34 | 26.02 | ++------------------+-------+-------+ +2022-05-05 20:22:06,162 - mmseg - INFO - Summary: +2022-05-05 20:22:06,162 - mmseg - INFO - ++-------+------+-------+ +| aAcc | mIoU | mAcc | ++-------+------+-------+ +| 75.75 | 51.0 | 62.96 | ++-------+------+-------+ +2022-05-05 20:22:06,165 - mmseg - INFO - The previous best checkpoint /mnt/lustre/chenzhe.vendor/workspace/ViT-Adapter/segmentation/work_dirs/upernet_beit_adapter_large_512_80k_cocostuff10k_ss/best_mIoU_iter_56000.pth was removed +2022-05-05 20:22:26,162 - mmseg - INFO - Now best checkpoint is saved as best_mIoU_iter_64000.pth. +2022-05-05 20:22:26,172 - mmseg - INFO - Best mIoU is 0.5100 at 64000 iter. +2022-05-05 20:22:26,182 - mmseg - INFO - Exp name: upernet_beit_adapter_large_512_80k_cocostuff10k_ss.py +2022-05-05 20:22:26,183 - mmseg - INFO - Iter(val) [125] aAcc: 0.7575, mIoU: 0.5100, mAcc: 0.6296, IoU.person: 0.8756, IoU.bicycle: 0.7538, IoU.car: 0.6366, IoU.motorcycle: 0.8794, IoU.airplane: 0.8917, IoU.bus: 0.8117, IoU.train: 0.7050, IoU.truck: 0.7674, IoU.boat: 0.7390, IoU.traffic light: 0.7648, IoU.fire hydrant: 0.8532, IoU.stop sign: 0.9055, IoU.parking meter: 0.7662, IoU.bench: 0.5305, IoU.bird: 0.7432, IoU.cat: 0.9215, IoU.dog: 0.9118, IoU.horse: 0.8902, IoU.sheep: 0.8796, IoU.cow: 0.9480, IoU.elephant: 0.9136, IoU.bear: 0.8826, IoU.zebra: 0.9054, IoU.giraffe: 0.8569, IoU.backpack: 0.2216, IoU.umbrella: 0.7848, IoU.handbag: 0.1718, IoU.tie: 0.5955, IoU.suitcase: 0.7691, IoU.frisbee: 0.9383, IoU.skis: 0.4091, IoU.snowboard: 0.6490, IoU.sports ball: 0.8457, IoU.kite: 0.6896, IoU.baseball bat: 0.4892, IoU.baseball glove: 0.0228, IoU.skateboard: 0.6737, IoU.surfboard: 0.8907, IoU.tennis racket: 0.6447, IoU.bottle: 0.7195, IoU.wine glass: 0.8304, IoU.cup: 0.6337, IoU.fork: 0.5235, IoU.knife: 0.7584, IoU.spoon: 0.4710, IoU.bowl: 0.5497, IoU.banana: 0.7682, IoU.apple: 0.7030, IoU.sandwich: 0.8612, IoU.orange: 0.6920, IoU.broccoli: 0.9494, IoU.carrot: 0.3790, IoU.hot dog: 0.5093, IoU.pizza: 0.9385, IoU.donut: 0.6896, IoU.cake: 0.5705, IoU.chair: 0.5933, IoU.couch: 0.7454, IoU.potted plant: 0.3585, IoU.bed: 0.7256, IoU.dining table: 0.6105, IoU.toilet: 0.8772, IoU.tv: 0.6836, IoU.laptop: 0.8700, IoU.mouse: 0.7066, IoU.remote: 0.6934, IoU.keyboard: 0.8268, IoU.cell phone: 0.7976, IoU.microwave: 0.5032, IoU.oven: 0.6265, IoU.toaster: 0.4490, IoU.sink: 0.6902, IoU.refrigerator: 0.8315, IoU.book: 0.7929, IoU.clock: 0.7573, IoU.vase: 0.6265, IoU.scissors: 0.7865, IoU.teddy bear: 0.8394, IoU.hair drier: 0.0000, IoU.toothbrush: 0.1674, IoU.banner: 0.3304, IoU.blanket: 0.0347, IoU.branch: 0.0657, IoU.bridge: 0.0257, IoU.building-other: 0.5562, IoU.bush: 0.2720, IoU.cabinet: 0.2043, IoU.cage: 0.0169, IoU.cardboard: 0.2352, IoU.carpet: 0.6167, IoU.ceiling-other: 0.6985, IoU.ceiling-tile: 0.1201, IoU.cloth: 0.0480, IoU.clothes: 0.2082, IoU.clouds: 0.5215, IoU.counter: 0.3557, IoU.cupboard: 0.5747, IoU.curtain: 0.6456, IoU.desk-stuff: 0.3721, IoU.dirt: 0.3242, IoU.door-stuff: 0.4890, IoU.fence: 0.4385, IoU.floor-marble: 0.0000, IoU.floor-other: 0.4353, IoU.floor-stone: 0.2365, IoU.floor-tile: 0.5962, IoU.floor-wood: 0.7128, IoU.flower: 0.1665, IoU.fog: 0.0000, IoU.food-other: 0.4015, IoU.fruit: 0.6267, IoU.furniture-other: 0.1397, IoU.grass: 0.7167, IoU.gravel: 0.2503, IoU.ground-other: 0.0738, IoU.hill: 0.2657, IoU.house: 0.2734, IoU.leaves: 0.0913, IoU.light: 0.4087, IoU.mat: 0.2099, IoU.metal: 0.1663, IoU.mirror-stuff: 0.4368, IoU.moss: 0.0010, IoU.mountain: 0.3536, IoU.mud: 0.1542, IoU.napkin: 0.2641, IoU.net: 0.2742, IoU.paper: 0.5691, IoU.pavement: 0.5669, IoU.pillow: 0.0000, IoU.plant-other: 0.3158, IoU.plastic: 0.1948, IoU.platform: 0.4214, IoU.playingfield: 0.6948, IoU.railing: 0.1456, IoU.railroad: 0.6196, IoU.river: 0.1363, IoU.road: 0.7015, IoU.rock: 0.5026, IoU.roof: 0.0598, IoU.rug: 0.5599, IoU.salad: 0.1002, IoU.sand: 0.7441, IoU.sea: 0.7521, IoU.shelf: 0.2527, IoU.sky-other: 0.6156, IoU.skyscraper: 0.0732, IoU.snow: 0.9190, IoU.solid-other: nan, IoU.stairs: 0.3262, IoU.stone: 0.0627, IoU.straw: 0.1887, IoU.structural-other: 0.1965, IoU.table: 0.1906, IoU.tent: 0.6527, IoU.textile-other: 0.1893, IoU.towel: 0.4115, IoU.tree: 0.7824, IoU.vegetable: 0.4440, IoU.wall-brick: 0.4355, IoU.wall-concrete: 0.2024, IoU.wall-other: 0.6152, IoU.wall-panel: 0.0567, IoU.wall-stone: 0.3068, IoU.wall-tile: 0.5798, IoU.wall-wood: 0.4017, IoU.water-other: 0.3350, IoU.waterdrops: nan, IoU.window-blind: 0.2180, IoU.window-other: 0.4652, IoU.wood: 0.1334, Acc.person: 0.9549, Acc.bicycle: 0.9236, Acc.car: 0.7070, Acc.motorcycle: 0.9573, Acc.airplane: 0.9608, Acc.bus: 0.8680, Acc.train: 0.9781, Acc.truck: 0.8978, Acc.boat: 0.8826, Acc.traffic light: 0.9227, Acc.fire hydrant: 0.9797, Acc.stop sign: 0.9839, Acc.parking meter: 0.8056, Acc.bench: 0.6748, Acc.bird: 0.8320, Acc.cat: 0.9719, Acc.dog: 0.9724, Acc.horse: 0.9642, Acc.sheep: 0.9269, Acc.cow: 0.9889, Acc.elephant: 0.9760, Acc.bear: 0.9627, Acc.zebra: 0.9680, Acc.giraffe: 0.9586, Acc.backpack: 0.5425, Acc.umbrella: 0.8929, Acc.handbag: 0.2466, Acc.tie: 0.5955, Acc.suitcase: 0.9655, Acc.frisbee: 0.9667, Acc.skis: 0.6071, Acc.snowboard: 0.7907, Acc.sports ball: 0.9091, Acc.kite: 0.8982, Acc.baseball bat: 0.6193, Acc.baseball glove: 0.0231, Acc.skateboard: 0.8909, Acc.surfboard: 0.9521, Acc.tennis racket: 0.6660, Acc.bottle: 0.8504, Acc.wine glass: 0.9269, Acc.cup: 0.8675, Acc.fork: 0.7202, Acc.knife: 0.8756, Acc.spoon: 0.6641, Acc.bowl: 0.6828, Acc.banana: 0.8838, Acc.apple: 0.9215, Acc.sandwich: 0.9734, Acc.orange: 0.9262, Acc.broccoli: 0.9696, Acc.carrot: 0.6793, Acc.hot dog: 0.9712, Acc.pizza: 0.9609, Acc.donut: 0.9226, Acc.cake: 0.6900, Acc.chair: 0.7652, Acc.couch: 0.9467, Acc.potted plant: 0.4658, Acc.bed: 0.8394, Acc.dining table: 0.7741, Acc.toilet: 0.9645, Acc.tv: 0.9265, Acc.laptop: 0.9828, Acc.mouse: 0.7781, Acc.remote: 0.9080, Acc.keyboard: 0.9857, Acc.cell phone: 0.9753, Acc.microwave: 0.7161, Acc.oven: 0.8666, Acc.toaster: 0.4490, Acc.sink: 0.7879, Acc.refrigerator: 0.9031, Acc.book: 0.8987, Acc.clock: 0.8747, Acc.vase: 0.9225, Acc.scissors: 0.9238, Acc.teddy bear: 0.9374, Acc.hair drier: 0.0000, Acc.toothbrush: 0.3079, Acc.banner: 0.5442, Acc.blanket: 0.0350, Acc.branch: 0.0670, Acc.bridge: 0.0341, Acc.building-other: 0.7654, Acc.bush: 0.3425, Acc.cabinet: 0.3576, Acc.cage: 0.0647, Acc.cardboard: 0.2827, Acc.carpet: 0.7887, Acc.ceiling-other: 0.8482, Acc.ceiling-tile: 0.1432, Acc.cloth: 0.0666, Acc.clothes: 0.3058, Acc.clouds: 0.6616, Acc.counter: 0.4404, Acc.cupboard: 0.7538, Acc.curtain: 0.8087, Acc.desk-stuff: 0.4206, Acc.dirt: 0.5029, Acc.door-stuff: 0.6150, Acc.fence: 0.7433, Acc.floor-marble: 0.0000, Acc.floor-other: 0.5512, Acc.floor-stone: 0.3567, Acc.floor-tile: 0.7554, Acc.floor-wood: 0.8642, Acc.flower: 0.4312, Acc.fog: 0.0000, Acc.food-other: 0.5459, Acc.fruit: 0.7270, Acc.furniture-other: 0.1894, Acc.grass: 0.8547, Acc.gravel: 0.2805, Acc.ground-other: 0.1382, Acc.hill: 0.3637, Acc.house: 0.4009, Acc.leaves: 0.1867, Acc.light: 0.5386, Acc.mat: 0.3008, Acc.metal: 0.2014, Acc.mirror-stuff: 0.5981, Acc.moss: 0.0010, Acc.mountain: 0.5469, Acc.mud: 0.2900, Acc.napkin: 0.3659, Acc.net: 0.3104, Acc.paper: 0.6752, Acc.pavement: 0.7714, Acc.pillow: 0.0000, Acc.plant-other: 0.4164, Acc.plastic: 0.2420, Acc.platform: 0.5913, Acc.playingfield: 0.8182, Acc.railing: 0.2172, Acc.railroad: 0.9008, Acc.river: 0.1854, Acc.road: 0.8008, Acc.rock: 0.6981, Acc.roof: 0.0969, Acc.rug: 0.7530, Acc.salad: 0.1038, Acc.sand: 0.8738, Acc.sea: 0.9029, Acc.shelf: 0.3660, Acc.sky-other: 0.7803, Acc.skyscraper: 0.1064, Acc.snow: 0.9544, Acc.solid-other: nan, Acc.stairs: 0.5270, Acc.stone: 0.1126, Acc.straw: 0.3286, Acc.structural-other: 0.2690, Acc.table: 0.2804, Acc.tent: 0.7005, Acc.textile-other: 0.2352, Acc.towel: 0.5061, Acc.tree: 0.8944, Acc.vegetable: 0.6753, Acc.wall-brick: 0.5422, Acc.wall-concrete: 0.2577, Acc.wall-other: 0.8006, Acc.wall-panel: 0.0659, Acc.wall-stone: 0.3677, Acc.wall-tile: 0.8804, Acc.wall-wood: 0.5999, Acc.water-other: 0.4584, Acc.waterdrops: nan, Acc.window-blind: 0.4185, Acc.window-other: 0.6151, Acc.wood: 0.2602 +2022-05-05 20:22:55,874 - mmseg - INFO - Iter [64050/80000] lr: 2.863e-07, eta: 2:46:21, time: 1.600, data_time: 1.013, memory: 60248, decode.loss_ce: 0.1297, decode.acc_seg: 76.6819, aux.loss_ce: 0.0852, aux.acc_seg: 74.9216, loss: 0.2149 +2022-05-05 20:23:28,144 - mmseg - INFO - Iter [64100/80000] lr: 2.854e-07, eta: 2:45:50, time: 0.647, data_time: 0.053, memory: 60248, decode.loss_ce: 0.1377, decode.acc_seg: 77.2963, aux.loss_ce: 0.0874, aux.acc_seg: 75.5950, loss: 0.2251 +2022-05-05 20:23:57,900 - mmseg - INFO - Iter [64150/80000] lr: 2.845e-07, eta: 2:45:19, time: 0.595, data_time: 0.004, memory: 60248, decode.loss_ce: 0.1374, decode.acc_seg: 75.5932, aux.loss_ce: 0.0909, aux.acc_seg: 73.6225, loss: 0.2283 +2022-05-05 20:24:27,522 - mmseg - INFO - Iter [64200/80000] lr: 2.836e-07, eta: 2:44:47, time: 0.593, data_time: 0.005, memory: 60248, decode.loss_ce: 0.1308, decode.acc_seg: 76.3126, aux.loss_ce: 0.0862, aux.acc_seg: 74.4107, loss: 0.2170 +2022-05-05 20:24:57,661 - mmseg - INFO - Iter [64250/80000] lr: 2.827e-07, eta: 2:44:15, time: 0.603, data_time: 0.004, memory: 60248, decode.loss_ce: 0.1340, decode.acc_seg: 76.6733, aux.loss_ce: 0.0865, aux.acc_seg: 74.9555, loss: 0.2205 +2022-05-05 20:25:27,525 - mmseg - INFO - Iter [64300/80000] lr: 2.818e-07, eta: 2:43:44, time: 0.597, data_time: 0.005, memory: 60248, decode.loss_ce: 0.1278, decode.acc_seg: 74.3307, aux.loss_ce: 0.0829, aux.acc_seg: 72.5220, loss: 0.2107 +2022-05-05 20:25:57,176 - mmseg - INFO - Iter [64350/80000] lr: 2.809e-07, eta: 2:43:12, time: 0.593, data_time: 0.004, memory: 60248, decode.loss_ce: 0.1337, decode.acc_seg: 76.0420, aux.loss_ce: 0.0887, aux.acc_seg: 74.0951, loss: 0.2224 +2022-05-05 20:26:26,705 - mmseg - INFO - Iter [64400/80000] lr: 2.800e-07, eta: 2:42:40, time: 0.591, data_time: 0.004, memory: 60248, decode.loss_ce: 0.1326, decode.acc_seg: 75.6873, aux.loss_ce: 0.0860, aux.acc_seg: 73.8283, loss: 0.2187 +2022-05-05 20:26:56,665 - mmseg - INFO - Iter [64450/80000] lr: 2.791e-07, eta: 2:42:09, time: 0.599, data_time: 0.004, memory: 60248, decode.loss_ce: 0.1225, decode.acc_seg: 75.6951, aux.loss_ce: 0.0797, aux.acc_seg: 73.9836, loss: 0.2022 +2022-05-05 20:27:26,317 - mmseg - INFO - Iter [64500/80000] lr: 2.782e-07, eta: 2:41:37, time: 0.593, data_time: 0.004, memory: 60248, decode.loss_ce: 0.1287, decode.acc_seg: 75.4033, aux.loss_ce: 0.0840, aux.acc_seg: 73.6713, loss: 0.2127 +2022-05-05 20:27:55,784 - mmseg - INFO - Iter [64550/80000] lr: 2.773e-07, eta: 2:41:05, time: 0.589, data_time: 0.004, memory: 60248, decode.loss_ce: 0.1284, decode.acc_seg: 74.8890, aux.loss_ce: 0.0845, aux.acc_seg: 73.0198, loss: 0.2129 +2022-05-05 20:28:25,225 - mmseg - INFO - Iter [64600/80000] lr: 2.764e-07, eta: 2:40:34, time: 0.589, data_time: 0.005, memory: 60248, decode.loss_ce: 0.1267, decode.acc_seg: 75.6672, aux.loss_ce: 0.0837, aux.acc_seg: 73.9707, loss: 0.2104 +2022-05-05 20:28:57,503 - mmseg - INFO - Iter [64650/80000] lr: 2.755e-07, eta: 2:40:03, time: 0.645, data_time: 0.057, memory: 60248, decode.loss_ce: 0.1237, decode.acc_seg: 74.5920, aux.loss_ce: 0.0792, aux.acc_seg: 72.9239, loss: 0.2029 +2022-05-05 20:29:27,303 - mmseg - INFO - Iter [64700/80000] lr: 2.746e-07, eta: 2:39:31, time: 0.596, data_time: 0.004, memory: 60248, decode.loss_ce: 0.1278, decode.acc_seg: 76.7872, aux.loss_ce: 0.0848, aux.acc_seg: 74.7733, loss: 0.2125 +2022-05-05 20:29:56,728 - mmseg - INFO - Iter [64750/80000] lr: 2.737e-07, eta: 2:38:59, time: 0.589, data_time: 0.004, memory: 60248, decode.loss_ce: 0.1259, decode.acc_seg: 76.0084, aux.loss_ce: 0.0826, aux.acc_seg: 74.2727, loss: 0.2084 +2022-05-05 20:30:26,812 - mmseg - INFO - Iter [64800/80000] lr: 2.728e-07, eta: 2:38:28, time: 0.602, data_time: 0.005, memory: 60248, decode.loss_ce: 0.1252, decode.acc_seg: 76.2654, aux.loss_ce: 0.0800, aux.acc_seg: 74.6298, loss: 0.2053 +2022-05-05 20:30:56,567 - mmseg - INFO - Iter [64850/80000] lr: 2.719e-07, eta: 2:37:56, time: 0.595, data_time: 0.005, memory: 60248, decode.loss_ce: 0.1332, decode.acc_seg: 76.4662, aux.loss_ce: 0.0850, aux.acc_seg: 74.7595, loss: 0.2182 +2022-05-05 20:31:26,346 - mmseg - INFO - Iter [64900/80000] lr: 2.710e-07, eta: 2:37:24, time: 0.596, data_time: 0.005, memory: 60248, decode.loss_ce: 0.1382, decode.acc_seg: 77.0297, aux.loss_ce: 0.0886, aux.acc_seg: 75.0991, loss: 0.2268 +2022-05-05 20:31:55,980 - mmseg - INFO - Iter [64950/80000] lr: 2.701e-07, eta: 2:36:53, time: 0.593, data_time: 0.005, memory: 60248, decode.loss_ce: 0.1271, decode.acc_seg: 76.0468, aux.loss_ce: 0.0836, aux.acc_seg: 74.3199, loss: 0.2107 +2022-05-05 20:32:25,489 - mmseg - INFO - Saving checkpoint at 65000 iterations +2022-05-05 20:32:46,740 - mmseg - INFO - Exp name: upernet_beit_adapter_large_512_80k_cocostuff10k_ss.py +2022-05-05 20:32:46,743 - mmseg - INFO - Iter [65000/80000] lr: 2.692e-07, eta: 2:36:26, time: 1.013, data_time: 0.005, memory: 60248, decode.loss_ce: 0.1282, decode.acc_seg: 76.5778, aux.loss_ce: 0.0846, aux.acc_seg: 74.7845, loss: 0.2127 +2022-05-05 20:33:16,441 - mmseg - INFO - Iter [65050/80000] lr: 2.683e-07, eta: 2:35:54, time: 0.596, data_time: 0.007, memory: 60248, decode.loss_ce: 0.1299, decode.acc_seg: 77.1837, aux.loss_ce: 0.0827, aux.acc_seg: 75.4480, loss: 0.2126 +2022-05-05 20:33:46,025 - mmseg - INFO - Iter [65100/80000] lr: 2.674e-07, eta: 2:35:23, time: 0.592, data_time: 0.004, memory: 60248, decode.loss_ce: 0.1338, decode.acc_seg: 76.2634, aux.loss_ce: 0.0868, aux.acc_seg: 74.4288, loss: 0.2206 +2022-05-05 20:34:15,502 - mmseg - INFO - Iter [65150/80000] lr: 2.665e-07, eta: 2:34:51, time: 0.590, data_time: 0.004, memory: 60248, decode.loss_ce: 0.1420, decode.acc_seg: 75.8036, aux.loss_ce: 0.0922, aux.acc_seg: 73.8724, loss: 0.2342 +2022-05-05 20:34:47,826 - mmseg - INFO - Iter [65200/80000] lr: 2.656e-07, eta: 2:34:20, time: 0.646, data_time: 0.057, memory: 60248, decode.loss_ce: 0.1349, decode.acc_seg: 76.1313, aux.loss_ce: 0.0878, aux.acc_seg: 74.3615, loss: 0.2227 +2022-05-05 20:35:17,300 - mmseg - INFO - Iter [65250/80000] lr: 2.647e-07, eta: 2:33:48, time: 0.589, data_time: 0.004, memory: 60248, decode.loss_ce: 0.1208, decode.acc_seg: 75.9809, aux.loss_ce: 0.0791, aux.acc_seg: 74.3719, loss: 0.1999 +2022-05-05 20:35:46,862 - mmseg - INFO - Iter [65300/80000] lr: 2.638e-07, eta: 2:33:17, time: 0.591, data_time: 0.005, memory: 60248, decode.loss_ce: 0.1293, decode.acc_seg: 76.4660, aux.loss_ce: 0.0824, aux.acc_seg: 74.7130, loss: 0.2117 +2022-05-05 20:36:16,126 - mmseg - INFO - Iter [65350/80000] lr: 2.629e-07, eta: 2:32:45, time: 0.585, data_time: 0.004, memory: 60248, decode.loss_ce: 0.1328, decode.acc_seg: 75.3239, aux.loss_ce: 0.0857, aux.acc_seg: 73.5016, loss: 0.2185 +2022-05-05 20:36:45,635 - mmseg - INFO - Iter [65400/80000] lr: 2.621e-07, eta: 2:32:13, time: 0.590, data_time: 0.005, memory: 60248, decode.loss_ce: 0.1211, decode.acc_seg: 74.6075, aux.loss_ce: 0.0819, aux.acc_seg: 72.7126, loss: 0.2030 +2022-05-05 20:37:15,404 - mmseg - INFO - Iter [65450/80000] lr: 2.612e-07, eta: 2:31:42, time: 0.595, data_time: 0.004, memory: 60248, decode.loss_ce: 0.1214, decode.acc_seg: 77.8183, aux.loss_ce: 0.0820, aux.acc_seg: 75.9637, loss: 0.2034 +2022-05-05 20:37:45,190 - mmseg - INFO - Iter [65500/80000] lr: 2.603e-07, eta: 2:31:10, time: 0.596, data_time: 0.006, memory: 60248, decode.loss_ce: 0.1343, decode.acc_seg: 76.2344, aux.loss_ce: 0.0856, aux.acc_seg: 74.5276, loss: 0.2199 +2022-05-05 20:38:14,464 - mmseg - INFO - Iter [65550/80000] lr: 2.594e-07, eta: 2:30:38, time: 0.586, data_time: 0.004, memory: 60248, decode.loss_ce: 0.1272, decode.acc_seg: 75.6185, aux.loss_ce: 0.0827, aux.acc_seg: 73.8107, loss: 0.2099 +2022-05-05 20:38:43,972 - mmseg - INFO - Iter [65600/80000] lr: 2.585e-07, eta: 2:30:07, time: 0.590, data_time: 0.006, memory: 60248, decode.loss_ce: 0.1284, decode.acc_seg: 76.2403, aux.loss_ce: 0.0841, aux.acc_seg: 74.4957, loss: 0.2126 +2022-05-05 20:39:13,344 - mmseg - INFO - Iter [65650/80000] lr: 2.576e-07, eta: 2:29:35, time: 0.587, data_time: 0.005, memory: 60248, decode.loss_ce: 0.1312, decode.acc_seg: 76.2009, aux.loss_ce: 0.0853, aux.acc_seg: 74.4168, loss: 0.2165 +2022-05-05 20:39:43,258 - mmseg - INFO - Iter [65700/80000] lr: 2.567e-07, eta: 2:29:03, time: 0.598, data_time: 0.004, memory: 60248, decode.loss_ce: 0.1274, decode.acc_seg: 76.1931, aux.loss_ce: 0.0833, aux.acc_seg: 74.4483, loss: 0.2107 +2022-05-05 20:40:12,980 - mmseg - INFO - Iter [65750/80000] lr: 2.558e-07, eta: 2:28:32, time: 0.595, data_time: 0.005, memory: 60248, decode.loss_ce: 0.1317, decode.acc_seg: 75.7729, aux.loss_ce: 0.0895, aux.acc_seg: 73.6760, loss: 0.2212 +2022-05-05 20:40:45,223 - mmseg - INFO - Iter [65800/80000] lr: 2.549e-07, eta: 2:28:01, time: 0.645, data_time: 0.053, memory: 60248, decode.loss_ce: 0.1245, decode.acc_seg: 76.2649, aux.loss_ce: 0.0821, aux.acc_seg: 74.4716, loss: 0.2065 +2022-05-05 20:41:14,793 - mmseg - INFO - Iter [65850/80000] lr: 2.540e-07, eta: 2:27:29, time: 0.591, data_time: 0.005, memory: 60248, decode.loss_ce: 0.1260, decode.acc_seg: 76.8412, aux.loss_ce: 0.0837, aux.acc_seg: 75.0052, loss: 0.2097 +2022-05-05 20:41:44,199 - mmseg - INFO - Iter [65900/80000] lr: 2.531e-07, eta: 2:26:57, time: 0.588, data_time: 0.005, memory: 60248, decode.loss_ce: 0.1304, decode.acc_seg: 76.1358, aux.loss_ce: 0.0826, aux.acc_seg: 74.4946, loss: 0.2130 +2022-05-05 20:42:13,914 - mmseg - INFO - Iter [65950/80000] lr: 2.522e-07, eta: 2:26:26, time: 0.594, data_time: 0.005, memory: 60248, decode.loss_ce: 0.1247, decode.acc_seg: 77.2322, aux.loss_ce: 0.0825, aux.acc_seg: 75.4630, loss: 0.2072 +2022-05-05 20:42:43,657 - mmseg - INFO - Saving checkpoint at 66000 iterations +2022-05-05 20:43:04,485 - mmseg - INFO - Exp name: upernet_beit_adapter_large_512_80k_cocostuff10k_ss.py +2022-05-05 20:43:04,488 - mmseg - INFO - Iter [66000/80000] lr: 2.513e-07, eta: 2:25:59, time: 1.009, data_time: 0.006, memory: 60248, decode.loss_ce: 0.1296, decode.acc_seg: 75.4056, aux.loss_ce: 0.0853, aux.acc_seg: 73.6079, loss: 0.2149 +2022-05-05 20:43:34,422 - mmseg - INFO - Iter [66050/80000] lr: 2.504e-07, eta: 2:25:27, time: 0.601, data_time: 0.007, memory: 60248, decode.loss_ce: 0.1229, decode.acc_seg: 76.9967, aux.loss_ce: 0.0790, aux.acc_seg: 75.3445, loss: 0.2019 +2022-05-05 20:44:03,976 - mmseg - INFO - Iter [66100/80000] lr: 2.495e-07, eta: 2:24:55, time: 0.591, data_time: 0.004, memory: 60248, decode.loss_ce: 0.1337, decode.acc_seg: 74.7299, aux.loss_ce: 0.0880, aux.acc_seg: 72.7948, loss: 0.2217 +2022-05-05 20:44:33,504 - mmseg - INFO - Iter [66150/80000] lr: 2.486e-07, eta: 2:24:24, time: 0.591, data_time: 0.006, memory: 60248, decode.loss_ce: 0.1249, decode.acc_seg: 75.0443, aux.loss_ce: 0.0795, aux.acc_seg: 73.4049, loss: 0.2044 +2022-05-05 20:45:03,031 - mmseg - INFO - Iter [66200/80000] lr: 2.477e-07, eta: 2:23:52, time: 0.591, data_time: 0.004, memory: 60248, decode.loss_ce: 0.1330, decode.acc_seg: 76.3456, aux.loss_ce: 0.0876, aux.acc_seg: 74.4340, loss: 0.2206 +2022-05-05 20:45:32,544 - mmseg - INFO - Iter [66250/80000] lr: 2.468e-07, eta: 2:23:20, time: 0.590, data_time: 0.005, memory: 60248, decode.loss_ce: 0.1284, decode.acc_seg: 76.0378, aux.loss_ce: 0.0817, aux.acc_seg: 74.4049, loss: 0.2101 +2022-05-05 20:46:02,144 - mmseg - INFO - Iter [66300/80000] lr: 2.459e-07, eta: 2:22:49, time: 0.592, data_time: 0.004, memory: 60248, decode.loss_ce: 0.1276, decode.acc_seg: 76.4897, aux.loss_ce: 0.0817, aux.acc_seg: 74.8690, loss: 0.2093 +2022-05-05 20:46:34,181 - mmseg - INFO - Iter [66350/80000] lr: 2.450e-07, eta: 2:22:18, time: 0.641, data_time: 0.055, memory: 60248, decode.loss_ce: 0.1266, decode.acc_seg: 75.0189, aux.loss_ce: 0.0836, aux.acc_seg: 73.0968, loss: 0.2102 +2022-05-05 20:47:03,665 - mmseg - INFO - Iter [66400/80000] lr: 2.441e-07, eta: 2:21:46, time: 0.590, data_time: 0.005, memory: 60248, decode.loss_ce: 0.1243, decode.acc_seg: 76.9551, aux.loss_ce: 0.0813, aux.acc_seg: 75.2455, loss: 0.2056 +2022-05-05 20:47:33,013 - mmseg - INFO - Iter [66450/80000] lr: 2.432e-07, eta: 2:21:14, time: 0.587, data_time: 0.004, memory: 60248, decode.loss_ce: 0.1328, decode.acc_seg: 76.1470, aux.loss_ce: 0.0863, aux.acc_seg: 74.3708, loss: 0.2191 +2022-05-05 20:48:02,389 - mmseg - INFO - Iter [66500/80000] lr: 2.423e-07, eta: 2:20:43, time: 0.587, data_time: 0.004, memory: 60248, decode.loss_ce: 0.1282, decode.acc_seg: 75.9748, aux.loss_ce: 0.0855, aux.acc_seg: 74.0815, loss: 0.2137 +2022-05-05 20:48:31,934 - mmseg - INFO - Iter [66550/80000] lr: 2.414e-07, eta: 2:20:11, time: 0.591, data_time: 0.004, memory: 60248, decode.loss_ce: 0.1301, decode.acc_seg: 77.1729, aux.loss_ce: 0.0824, aux.acc_seg: 75.6090, loss: 0.2125 +2022-05-05 20:49:01,338 - mmseg - INFO - Iter [66600/80000] lr: 2.405e-07, eta: 2:19:39, time: 0.588, data_time: 0.004, memory: 60248, decode.loss_ce: 0.1294, decode.acc_seg: 75.7498, aux.loss_ce: 0.0839, aux.acc_seg: 74.0700, loss: 0.2133 +2022-05-05 20:49:30,938 - mmseg - INFO - Iter [66650/80000] lr: 2.396e-07, eta: 2:19:08, time: 0.592, data_time: 0.004, memory: 60248, decode.loss_ce: 0.1304, decode.acc_seg: 78.0209, aux.loss_ce: 0.0855, aux.acc_seg: 76.1242, loss: 0.2158 +2022-05-05 20:50:00,267 - mmseg - INFO - Iter [66700/80000] lr: 2.387e-07, eta: 2:18:36, time: 0.587, data_time: 0.004, memory: 60248, decode.loss_ce: 0.1273, decode.acc_seg: 75.5319, aux.loss_ce: 0.0830, aux.acc_seg: 73.7519, loss: 0.2102 +2022-05-05 20:50:29,790 - mmseg - INFO - Iter [66750/80000] lr: 2.378e-07, eta: 2:18:05, time: 0.590, data_time: 0.004, memory: 60248, decode.loss_ce: 0.1319, decode.acc_seg: 76.6879, aux.loss_ce: 0.0861, aux.acc_seg: 74.9346, loss: 0.2181 +2022-05-05 20:50:59,211 - mmseg - INFO - Iter [66800/80000] lr: 2.369e-07, eta: 2:17:33, time: 0.588, data_time: 0.005, memory: 60248, decode.loss_ce: 0.1263, decode.acc_seg: 76.0582, aux.loss_ce: 0.0830, aux.acc_seg: 74.2912, loss: 0.2093 +2022-05-05 20:51:28,807 - mmseg - INFO - Iter [66850/80000] lr: 2.360e-07, eta: 2:17:01, time: 0.592, data_time: 0.004, memory: 60248, decode.loss_ce: 0.1431, decode.acc_seg: 76.2156, aux.loss_ce: 0.0891, aux.acc_seg: 74.5041, loss: 0.2322 +2022-05-05 20:52:00,697 - mmseg - INFO - Iter [66900/80000] lr: 2.351e-07, eta: 2:16:30, time: 0.638, data_time: 0.053, memory: 60248, decode.loss_ce: 0.1275, decode.acc_seg: 76.5104, aux.loss_ce: 0.0808, aux.acc_seg: 74.9233, loss: 0.2083 +2022-05-05 20:52:30,005 - mmseg - INFO - Iter [66950/80000] lr: 2.342e-07, eta: 2:15:59, time: 0.586, data_time: 0.004, memory: 60248, decode.loss_ce: 0.1350, decode.acc_seg: 78.0347, aux.loss_ce: 0.0871, aux.acc_seg: 76.3057, loss: 0.2221 +2022-05-05 20:52:59,281 - mmseg - INFO - Saving checkpoint at 67000 iterations +2022-05-05 20:53:19,385 - mmseg - INFO - Exp name: upernet_beit_adapter_large_512_80k_cocostuff10k_ss.py +2022-05-05 20:53:19,388 - mmseg - INFO - Iter [67000/80000] lr: 2.333e-07, eta: 2:15:31, time: 0.987, data_time: 0.004, memory: 60248, decode.loss_ce: 0.1226, decode.acc_seg: 76.1230, aux.loss_ce: 0.0811, aux.acc_seg: 74.3616, loss: 0.2037 +2022-05-05 20:53:48,793 - mmseg - INFO - Iter [67050/80000] lr: 2.324e-07, eta: 2:14:59, time: 0.589, data_time: 0.005, memory: 60248, decode.loss_ce: 0.1363, decode.acc_seg: 75.9870, aux.loss_ce: 0.0884, aux.acc_seg: 74.0380, loss: 0.2246 +2022-05-05 20:54:18,455 - mmseg - INFO - Iter [67100/80000] lr: 2.315e-07, eta: 2:14:28, time: 0.593, data_time: 0.005, memory: 60248, decode.loss_ce: 0.1367, decode.acc_seg: 76.0632, aux.loss_ce: 0.0890, aux.acc_seg: 74.2059, loss: 0.2257 +2022-05-05 20:54:47,835 - mmseg - INFO - Iter [67150/80000] lr: 2.306e-07, eta: 2:13:56, time: 0.587, data_time: 0.005, memory: 60248, decode.loss_ce: 0.1305, decode.acc_seg: 76.2709, aux.loss_ce: 0.0841, aux.acc_seg: 74.4765, loss: 0.2146 +2022-05-05 20:55:17,276 - mmseg - INFO - Iter [67200/80000] lr: 2.297e-07, eta: 2:13:24, time: 0.589, data_time: 0.005, memory: 60248, decode.loss_ce: 0.1200, decode.acc_seg: 75.2780, aux.loss_ce: 0.0790, aux.acc_seg: 73.5347, loss: 0.1990 +2022-05-05 20:55:46,759 - mmseg - INFO - Iter [67250/80000] lr: 2.288e-07, eta: 2:12:53, time: 0.589, data_time: 0.005, memory: 60248, decode.loss_ce: 0.1247, decode.acc_seg: 75.9447, aux.loss_ce: 0.0840, aux.acc_seg: 73.9663, loss: 0.2087 +2022-05-05 20:56:16,313 - mmseg - INFO - Iter [67300/80000] lr: 2.280e-07, eta: 2:12:21, time: 0.591, data_time: 0.005, memory: 60248, decode.loss_ce: 0.1307, decode.acc_seg: 76.6248, aux.loss_ce: 0.0860, aux.acc_seg: 74.6497, loss: 0.2167 +2022-05-05 20:56:45,721 - mmseg - INFO - Iter [67350/80000] lr: 2.271e-07, eta: 2:11:50, time: 0.588, data_time: 0.004, memory: 60248, decode.loss_ce: 0.1277, decode.acc_seg: 75.0862, aux.loss_ce: 0.0823, aux.acc_seg: 73.3230, loss: 0.2100 +2022-05-05 20:57:15,253 - mmseg - INFO - Iter [67400/80000] lr: 2.262e-07, eta: 2:11:18, time: 0.591, data_time: 0.006, memory: 60248, decode.loss_ce: 0.1288, decode.acc_seg: 77.0636, aux.loss_ce: 0.0841, aux.acc_seg: 75.2545, loss: 0.2130 +2022-05-05 20:57:47,762 - mmseg - INFO - Iter [67450/80000] lr: 2.253e-07, eta: 2:10:47, time: 0.650, data_time: 0.054, memory: 60248, decode.loss_ce: 0.1232, decode.acc_seg: 75.3999, aux.loss_ce: 0.0811, aux.acc_seg: 73.6463, loss: 0.2043 +2022-05-05 20:58:17,468 - mmseg - INFO - Iter [67500/80000] lr: 2.244e-07, eta: 2:10:15, time: 0.594, data_time: 0.004, memory: 60248, decode.loss_ce: 0.1296, decode.acc_seg: 75.2745, aux.loss_ce: 0.0830, aux.acc_seg: 73.5854, loss: 0.2127 +2022-05-05 20:58:46,951 - mmseg - INFO - Iter [67550/80000] lr: 2.235e-07, eta: 2:09:44, time: 0.590, data_time: 0.004, memory: 60248, decode.loss_ce: 0.1238, decode.acc_seg: 76.2612, aux.loss_ce: 0.0810, aux.acc_seg: 74.5156, loss: 0.2049 +2022-05-05 20:59:16,930 - mmseg - INFO - Iter [67600/80000] lr: 2.226e-07, eta: 2:09:12, time: 0.600, data_time: 0.006, memory: 60248, decode.loss_ce: 0.1198, decode.acc_seg: 76.8719, aux.loss_ce: 0.0789, aux.acc_seg: 75.1936, loss: 0.1987 +2022-05-05 20:59:46,438 - mmseg - INFO - Iter [67650/80000] lr: 2.217e-07, eta: 2:08:41, time: 0.588, data_time: 0.004, memory: 60248, decode.loss_ce: 0.1347, decode.acc_seg: 76.8266, aux.loss_ce: 0.0862, aux.acc_seg: 75.1322, loss: 0.2208 +2022-05-05 21:00:15,888 - mmseg - INFO - Iter [67700/80000] lr: 2.208e-07, eta: 2:08:09, time: 0.591, data_time: 0.006, memory: 60248, decode.loss_ce: 0.1267, decode.acc_seg: 75.6275, aux.loss_ce: 0.0842, aux.acc_seg: 73.8416, loss: 0.2110 +2022-05-05 21:00:45,527 - mmseg - INFO - Iter [67750/80000] lr: 2.199e-07, eta: 2:07:38, time: 0.593, data_time: 0.004, memory: 60248, decode.loss_ce: 0.1291, decode.acc_seg: 77.2929, aux.loss_ce: 0.0833, aux.acc_seg: 75.5593, loss: 0.2124 +2022-05-05 21:01:14,996 - mmseg - INFO - Iter [67800/80000] lr: 2.190e-07, eta: 2:07:06, time: 0.589, data_time: 0.005, memory: 60248, decode.loss_ce: 0.1269, decode.acc_seg: 75.9214, aux.loss_ce: 0.0839, aux.acc_seg: 73.9935, loss: 0.2107 +2022-05-05 21:01:44,373 - mmseg - INFO - Iter [67850/80000] lr: 2.181e-07, eta: 2:06:34, time: 0.587, data_time: 0.004, memory: 60248, decode.loss_ce: 0.1237, decode.acc_seg: 76.9363, aux.loss_ce: 0.0793, aux.acc_seg: 75.2937, loss: 0.2030 +2022-05-05 21:02:13,759 - mmseg - INFO - Iter [67900/80000] lr: 2.172e-07, eta: 2:06:03, time: 0.588, data_time: 0.004, memory: 60248, decode.loss_ce: 0.1274, decode.acc_seg: 76.9294, aux.loss_ce: 0.0829, aux.acc_seg: 75.1819, loss: 0.2103 +2022-05-05 21:02:43,215 - mmseg - INFO - Iter [67950/80000] lr: 2.163e-07, eta: 2:05:31, time: 0.589, data_time: 0.004, memory: 60248, decode.loss_ce: 0.1348, decode.acc_seg: 75.3655, aux.loss_ce: 0.0878, aux.acc_seg: 73.5493, loss: 0.2226 +2022-05-05 21:03:12,781 - mmseg - INFO - Saving checkpoint at 68000 iterations +2022-05-05 21:03:33,559 - mmseg - INFO - Exp name: upernet_beit_adapter_large_512_80k_cocostuff10k_ss.py +2022-05-05 21:03:33,561 - mmseg - INFO - Iter [68000/80000] lr: 2.154e-07, eta: 2:05:03, time: 1.005, data_time: 0.004, memory: 60248, decode.loss_ce: 0.1340, decode.acc_seg: 75.8528, aux.loss_ce: 0.0865, aux.acc_seg: 73.9479, loss: 0.2205 +2022-05-05 21:04:06,085 - mmseg - INFO - Iter [68050/80000] lr: 2.145e-07, eta: 2:04:32, time: 0.650, data_time: 0.054, memory: 60248, decode.loss_ce: 0.1288, decode.acc_seg: 77.0865, aux.loss_ce: 0.0845, aux.acc_seg: 75.3193, loss: 0.2133 +2022-05-05 21:04:35,949 - mmseg - INFO - Iter [68100/80000] lr: 2.136e-07, eta: 2:04:01, time: 0.599, data_time: 0.006, memory: 60248, decode.loss_ce: 0.1296, decode.acc_seg: 75.6117, aux.loss_ce: 0.0844, aux.acc_seg: 73.7691, loss: 0.2139 +2022-05-05 21:05:05,452 - mmseg - INFO - Iter [68150/80000] lr: 2.127e-07, eta: 2:03:29, time: 0.590, data_time: 0.005, memory: 60248, decode.loss_ce: 0.1241, decode.acc_seg: 77.0038, aux.loss_ce: 0.0792, aux.acc_seg: 75.4474, loss: 0.2033 +2022-05-05 21:05:34,907 - mmseg - INFO - Iter [68200/80000] lr: 2.118e-07, eta: 2:02:58, time: 0.589, data_time: 0.004, memory: 60248, decode.loss_ce: 0.1206, decode.acc_seg: 76.1491, aux.loss_ce: 0.0802, aux.acc_seg: 74.3210, loss: 0.2008 +2022-05-05 21:06:04,899 - mmseg - INFO - Iter [68250/80000] lr: 2.109e-07, eta: 2:02:26, time: 0.600, data_time: 0.005, memory: 60248, decode.loss_ce: 0.1332, decode.acc_seg: 76.1302, aux.loss_ce: 0.0880, aux.acc_seg: 74.0980, loss: 0.2212 +2022-05-05 21:06:34,296 - mmseg - INFO - Iter [68300/80000] lr: 2.100e-07, eta: 2:01:55, time: 0.588, data_time: 0.005, memory: 60248, decode.loss_ce: 0.1284, decode.acc_seg: 75.5878, aux.loss_ce: 0.0864, aux.acc_seg: 73.5066, loss: 0.2148 +2022-05-05 21:07:03,994 - mmseg - INFO - Iter [68350/80000] lr: 2.091e-07, eta: 2:01:23, time: 0.594, data_time: 0.005, memory: 60248, decode.loss_ce: 0.1289, decode.acc_seg: 75.8183, aux.loss_ce: 0.0850, aux.acc_seg: 74.0205, loss: 0.2139 +2022-05-05 21:07:33,775 - mmseg - INFO - Iter [68400/80000] lr: 2.082e-07, eta: 2:00:52, time: 0.595, data_time: 0.004, memory: 60248, decode.loss_ce: 0.1246, decode.acc_seg: 75.5849, aux.loss_ce: 0.0817, aux.acc_seg: 73.8787, loss: 0.2063 +2022-05-05 21:08:03,368 - mmseg - INFO - Iter [68450/80000] lr: 2.073e-07, eta: 2:00:20, time: 0.592, data_time: 0.005, memory: 60248, decode.loss_ce: 0.1236, decode.acc_seg: 76.3778, aux.loss_ce: 0.0801, aux.acc_seg: 74.7215, loss: 0.2037 +2022-05-05 21:08:32,873 - mmseg - INFO - Iter [68500/80000] lr: 2.064e-07, eta: 1:59:48, time: 0.590, data_time: 0.004, memory: 60248, decode.loss_ce: 0.1405, decode.acc_seg: 76.3303, aux.loss_ce: 0.0907, aux.acc_seg: 74.2896, loss: 0.2312 +2022-05-05 21:09:02,766 - mmseg - INFO - Iter [68550/80000] lr: 2.055e-07, eta: 1:59:17, time: 0.597, data_time: 0.004, memory: 60248, decode.loss_ce: 0.1295, decode.acc_seg: 77.4151, aux.loss_ce: 0.0848, aux.acc_seg: 75.6344, loss: 0.2143 +2022-05-05 21:09:34,904 - mmseg - INFO - Iter [68600/80000] lr: 2.046e-07, eta: 1:58:46, time: 0.643, data_time: 0.056, memory: 60248, decode.loss_ce: 0.1289, decode.acc_seg: 77.2221, aux.loss_ce: 0.0854, aux.acc_seg: 75.3316, loss: 0.2144 +2022-05-05 21:10:04,293 - mmseg - INFO - Iter [68650/80000] lr: 2.037e-07, eta: 1:58:14, time: 0.588, data_time: 0.005, memory: 60248, decode.loss_ce: 0.1241, decode.acc_seg: 77.0597, aux.loss_ce: 0.0824, aux.acc_seg: 75.1505, loss: 0.2064 +2022-05-05 21:10:33,843 - mmseg - INFO - Iter [68700/80000] lr: 2.028e-07, eta: 1:57:43, time: 0.591, data_time: 0.004, memory: 60248, decode.loss_ce: 0.1421, decode.acc_seg: 75.8458, aux.loss_ce: 0.0923, aux.acc_seg: 73.7844, loss: 0.2344 +2022-05-05 21:11:03,470 - mmseg - INFO - Iter [68750/80000] lr: 2.019e-07, eta: 1:57:11, time: 0.592, data_time: 0.004, memory: 60248, decode.loss_ce: 0.1224, decode.acc_seg: 75.0810, aux.loss_ce: 0.0804, aux.acc_seg: 73.4058, loss: 0.2028 +2022-05-05 21:11:32,974 - mmseg - INFO - Iter [68800/80000] lr: 2.010e-07, eta: 1:56:40, time: 0.590, data_time: 0.005, memory: 60248, decode.loss_ce: 0.1267, decode.acc_seg: 76.9078, aux.loss_ce: 0.0833, aux.acc_seg: 75.0716, loss: 0.2100 +2022-05-05 21:12:02,587 - mmseg - INFO - Iter [68850/80000] lr: 2.001e-07, eta: 1:56:08, time: 0.592, data_time: 0.004, memory: 60248, decode.loss_ce: 0.1391, decode.acc_seg: 76.0069, aux.loss_ce: 0.0904, aux.acc_seg: 74.1655, loss: 0.2296 +2022-05-05 21:12:32,132 - mmseg - INFO - Iter [68900/80000] lr: 1.992e-07, eta: 1:55:37, time: 0.591, data_time: 0.005, memory: 60248, decode.loss_ce: 0.1248, decode.acc_seg: 75.9194, aux.loss_ce: 0.0811, aux.acc_seg: 74.2397, loss: 0.2059 +2022-05-05 21:13:02,067 - mmseg - INFO - Iter [68950/80000] lr: 1.983e-07, eta: 1:55:05, time: 0.597, data_time: 0.004, memory: 60248, decode.loss_ce: 0.1239, decode.acc_seg: 76.5208, aux.loss_ce: 0.0819, aux.acc_seg: 74.6864, loss: 0.2058 +2022-05-05 21:13:31,555 - mmseg - INFO - Saving checkpoint at 69000 iterations +2022-05-05 21:13:52,952 - mmseg - INFO - Exp name: upernet_beit_adapter_large_512_80k_cocostuff10k_ss.py +2022-05-05 21:13:52,955 - mmseg - INFO - Iter [69000/80000] lr: 1.974e-07, eta: 1:54:37, time: 1.016, data_time: 0.006, memory: 60248, decode.loss_ce: 0.1207, decode.acc_seg: 75.4915, aux.loss_ce: 0.0806, aux.acc_seg: 73.6178, loss: 0.2013 +2022-05-05 21:14:22,586 - mmseg - INFO - Iter [69050/80000] lr: 1.965e-07, eta: 1:54:06, time: 0.596, data_time: 0.007, memory: 60248, decode.loss_ce: 0.1304, decode.acc_seg: 75.8475, aux.loss_ce: 0.0859, aux.acc_seg: 73.9407, loss: 0.2164 +2022-05-05 21:14:52,300 - mmseg - INFO - Iter [69100/80000] lr: 1.956e-07, eta: 1:53:34, time: 0.594, data_time: 0.004, memory: 60248, decode.loss_ce: 0.1286, decode.acc_seg: 75.9384, aux.loss_ce: 0.0827, aux.acc_seg: 74.2659, loss: 0.2113 +2022-05-05 21:15:24,898 - mmseg - INFO - Iter [69150/80000] lr: 1.947e-07, eta: 1:53:03, time: 0.651, data_time: 0.059, memory: 60248, decode.loss_ce: 0.1360, decode.acc_seg: 75.8813, aux.loss_ce: 0.0885, aux.acc_seg: 74.1354, loss: 0.2246 +2022-05-05 21:15:54,384 - mmseg - INFO - Iter [69200/80000] lr: 1.939e-07, eta: 1:52:31, time: 0.590, data_time: 0.005, memory: 60248, decode.loss_ce: 0.1261, decode.acc_seg: 75.7180, aux.loss_ce: 0.0808, aux.acc_seg: 74.0700, loss: 0.2069 +2022-05-05 21:16:24,045 - mmseg - INFO - Iter [69250/80000] lr: 1.930e-07, eta: 1:52:00, time: 0.593, data_time: 0.006, memory: 60248, decode.loss_ce: 0.1276, decode.acc_seg: 77.9566, aux.loss_ce: 0.0842, aux.acc_seg: 76.0417, loss: 0.2118 +2022-05-05 21:16:53,441 - mmseg - INFO - Iter [69300/80000] lr: 1.921e-07, eta: 1:51:28, time: 0.588, data_time: 0.005, memory: 60248, decode.loss_ce: 0.1281, decode.acc_seg: 76.5072, aux.loss_ce: 0.0846, aux.acc_seg: 74.6576, loss: 0.2127 +2022-05-05 21:17:22,931 - mmseg - INFO - Iter [69350/80000] lr: 1.912e-07, eta: 1:50:57, time: 0.590, data_time: 0.005, memory: 60248, decode.loss_ce: 0.1272, decode.acc_seg: 76.2534, aux.loss_ce: 0.0827, aux.acc_seg: 74.5897, loss: 0.2099 +2022-05-05 21:17:52,280 - mmseg - INFO - Iter [69400/80000] lr: 1.903e-07, eta: 1:50:25, time: 0.587, data_time: 0.005, memory: 60248, decode.loss_ce: 0.1278, decode.acc_seg: 76.0577, aux.loss_ce: 0.0851, aux.acc_seg: 74.1323, loss: 0.2129 +2022-05-05 21:18:22,017 - mmseg - INFO - Iter [69450/80000] lr: 1.894e-07, eta: 1:49:54, time: 0.595, data_time: 0.004, memory: 60248, decode.loss_ce: 0.1256, decode.acc_seg: 75.7570, aux.loss_ce: 0.0819, aux.acc_seg: 73.9577, loss: 0.2074 +2022-05-05 21:18:51,778 - mmseg - INFO - Iter [69500/80000] lr: 1.885e-07, eta: 1:49:22, time: 0.595, data_time: 0.004, memory: 60248, decode.loss_ce: 0.1277, decode.acc_seg: 76.5300, aux.loss_ce: 0.0822, aux.acc_seg: 74.8202, loss: 0.2099 +2022-05-05 21:19:21,297 - mmseg - INFO - Iter [69550/80000] lr: 1.876e-07, eta: 1:48:51, time: 0.590, data_time: 0.005, memory: 60248, decode.loss_ce: 0.1272, decode.acc_seg: 76.3530, aux.loss_ce: 0.0838, aux.acc_seg: 74.3450, loss: 0.2110 +2022-05-05 21:19:51,019 - mmseg - INFO - Iter [69600/80000] lr: 1.867e-07, eta: 1:48:19, time: 0.594, data_time: 0.005, memory: 60248, decode.loss_ce: 0.1261, decode.acc_seg: 77.2132, aux.loss_ce: 0.0825, aux.acc_seg: 75.3765, loss: 0.2086 +2022-05-05 21:20:20,377 - mmseg - INFO - Iter [69650/80000] lr: 1.858e-07, eta: 1:47:48, time: 0.588, data_time: 0.005, memory: 60248, decode.loss_ce: 0.1308, decode.acc_seg: 76.7271, aux.loss_ce: 0.0869, aux.acc_seg: 74.7640, loss: 0.2176 +2022-05-05 21:20:52,454 - mmseg - INFO - Iter [69700/80000] lr: 1.849e-07, eta: 1:47:17, time: 0.642, data_time: 0.055, memory: 60248, decode.loss_ce: 0.1319, decode.acc_seg: 76.5777, aux.loss_ce: 0.0858, aux.acc_seg: 74.8486, loss: 0.2177 +2022-05-05 21:21:21,845 - mmseg - INFO - Iter [69750/80000] lr: 1.840e-07, eta: 1:46:45, time: 0.588, data_time: 0.004, memory: 60248, decode.loss_ce: 0.1320, decode.acc_seg: 75.6789, aux.loss_ce: 0.0863, aux.acc_seg: 73.7023, loss: 0.2183 +2022-05-05 21:21:51,182 - mmseg - INFO - Iter [69800/80000] lr: 1.831e-07, eta: 1:46:14, time: 0.587, data_time: 0.004, memory: 60248, decode.loss_ce: 0.1262, decode.acc_seg: 77.5614, aux.loss_ce: 0.0835, aux.acc_seg: 75.7234, loss: 0.2097 +2022-05-05 21:22:21,084 - mmseg - INFO - Iter [69850/80000] lr: 1.822e-07, eta: 1:45:42, time: 0.598, data_time: 0.004, memory: 60248, decode.loss_ce: 0.1243, decode.acc_seg: 75.7115, aux.loss_ce: 0.0838, aux.acc_seg: 73.7449, loss: 0.2081 +2022-05-05 21:22:50,534 - mmseg - INFO - Iter [69900/80000] lr: 1.813e-07, eta: 1:45:11, time: 0.589, data_time: 0.004, memory: 60248, decode.loss_ce: 0.1276, decode.acc_seg: 74.8312, aux.loss_ce: 0.0827, aux.acc_seg: 73.1938, loss: 0.2103 +2022-05-05 21:23:20,047 - mmseg - INFO - Iter [69950/80000] lr: 1.804e-07, eta: 1:44:39, time: 0.590, data_time: 0.005, memory: 60248, decode.loss_ce: 0.1236, decode.acc_seg: 78.4696, aux.loss_ce: 0.0800, aux.acc_seg: 76.7585, loss: 0.2036 +2022-05-05 21:23:49,627 - mmseg - INFO - Saving checkpoint at 70000 iterations +2022-05-05 21:24:10,640 - mmseg - INFO - Exp name: upernet_beit_adapter_large_512_80k_cocostuff10k_ss.py +2022-05-05 21:24:10,642 - mmseg - INFO - Iter [70000/80000] lr: 1.795e-07, eta: 1:44:11, time: 1.010, data_time: 0.004, memory: 60248, decode.loss_ce: 0.1226, decode.acc_seg: 75.9507, aux.loss_ce: 0.0804, aux.acc_seg: 74.2243, loss: 0.2031 +2022-05-05 21:24:40,628 - mmseg - INFO - Iter [70050/80000] lr: 1.786e-07, eta: 1:43:39, time: 0.602, data_time: 0.006, memory: 60248, decode.loss_ce: 0.1193, decode.acc_seg: 75.2304, aux.loss_ce: 0.0787, aux.acc_seg: 73.5251, loss: 0.1980 +2022-05-05 21:25:10,326 - mmseg - INFO - Iter [70100/80000] lr: 1.777e-07, eta: 1:43:08, time: 0.594, data_time: 0.005, memory: 60248, decode.loss_ce: 0.1215, decode.acc_seg: 75.9733, aux.loss_ce: 0.0787, aux.acc_seg: 74.3171, loss: 0.2002 +2022-05-05 21:25:39,918 - mmseg - INFO - Iter [70150/80000] lr: 1.768e-07, eta: 1:42:36, time: 0.592, data_time: 0.004, memory: 60248, decode.loss_ce: 0.1337, decode.acc_seg: 76.1434, aux.loss_ce: 0.0895, aux.acc_seg: 74.1904, loss: 0.2232 +2022-05-05 21:26:09,682 - mmseg - INFO - Iter [70200/80000] lr: 1.759e-07, eta: 1:42:05, time: 0.595, data_time: 0.007, memory: 60248, decode.loss_ce: 0.1274, decode.acc_seg: 75.9409, aux.loss_ce: 0.0846, aux.acc_seg: 74.0580, loss: 0.2120 +2022-05-05 21:26:39,111 - mmseg - INFO - Iter [70250/80000] lr: 1.750e-07, eta: 1:41:33, time: 0.589, data_time: 0.005, memory: 60248, decode.loss_ce: 0.1266, decode.acc_seg: 76.9182, aux.loss_ce: 0.0841, aux.acc_seg: 75.1943, loss: 0.2108 +2022-05-05 21:27:11,643 - mmseg - INFO - Iter [70300/80000] lr: 1.741e-07, eta: 1:41:02, time: 0.651, data_time: 0.056, memory: 60248, decode.loss_ce: 0.1230, decode.acc_seg: 76.2525, aux.loss_ce: 0.0798, aux.acc_seg: 74.6330, loss: 0.2028 +2022-05-05 21:27:40,841 - mmseg - INFO - Iter [70350/80000] lr: 1.732e-07, eta: 1:40:31, time: 0.584, data_time: 0.004, memory: 60248, decode.loss_ce: 0.1324, decode.acc_seg: 77.1028, aux.loss_ce: 0.0857, aux.acc_seg: 75.2955, loss: 0.2181 +2022-05-05 21:28:10,397 - mmseg - INFO - Iter [70400/80000] lr: 1.723e-07, eta: 1:39:59, time: 0.591, data_time: 0.005, memory: 60248, decode.loss_ce: 0.1271, decode.acc_seg: 75.7184, aux.loss_ce: 0.0826, aux.acc_seg: 73.9109, loss: 0.2097 +2022-05-05 21:28:39,768 - mmseg - INFO - Iter [70450/80000] lr: 1.714e-07, eta: 1:39:28, time: 0.587, data_time: 0.004, memory: 60248, decode.loss_ce: 0.1172, decode.acc_seg: 75.5175, aux.loss_ce: 0.0754, aux.acc_seg: 73.9074, loss: 0.1926 +2022-05-05 21:29:09,324 - mmseg - INFO - Iter [70500/80000] lr: 1.705e-07, eta: 1:38:56, time: 0.591, data_time: 0.004, memory: 60248, decode.loss_ce: 0.1242, decode.acc_seg: 77.4654, aux.loss_ce: 0.0817, aux.acc_seg: 75.7841, loss: 0.2059 +2022-05-05 21:29:38,790 - mmseg - INFO - Iter [70550/80000] lr: 1.696e-07, eta: 1:38:25, time: 0.589, data_time: 0.004, memory: 60248, decode.loss_ce: 0.1349, decode.acc_seg: 76.7861, aux.loss_ce: 0.0894, aux.acc_seg: 74.7883, loss: 0.2243 +2022-05-05 21:30:08,415 - mmseg - INFO - Iter [70600/80000] lr: 1.687e-07, eta: 1:37:53, time: 0.592, data_time: 0.004, memory: 60248, decode.loss_ce: 0.1256, decode.acc_seg: 76.1229, aux.loss_ce: 0.0832, aux.acc_seg: 74.3318, loss: 0.2088 +2022-05-05 21:30:37,827 - mmseg - INFO - Iter [70650/80000] lr: 1.678e-07, eta: 1:37:22, time: 0.588, data_time: 0.004, memory: 60248, decode.loss_ce: 0.1270, decode.acc_seg: 75.8742, aux.loss_ce: 0.0825, aux.acc_seg: 74.1407, loss: 0.2095 +2022-05-05 21:31:07,509 - mmseg - INFO - Iter [70700/80000] lr: 1.669e-07, eta: 1:36:50, time: 0.594, data_time: 0.005, memory: 60248, decode.loss_ce: 0.1227, decode.acc_seg: 75.4852, aux.loss_ce: 0.0806, aux.acc_seg: 73.6672, loss: 0.2033 +2022-05-05 21:31:37,373 - mmseg - INFO - Iter [70750/80000] lr: 1.660e-07, eta: 1:36:19, time: 0.598, data_time: 0.007, memory: 60248, decode.loss_ce: 0.1249, decode.acc_seg: 76.4887, aux.loss_ce: 0.0826, aux.acc_seg: 74.6146, loss: 0.2075 +2022-05-05 21:32:06,720 - mmseg - INFO - Iter [70800/80000] lr: 1.651e-07, eta: 1:35:48, time: 0.587, data_time: 0.005, memory: 60248, decode.loss_ce: 0.1261, decode.acc_seg: 76.5251, aux.loss_ce: 0.0813, aux.acc_seg: 74.8520, loss: 0.2074 +2022-05-05 21:32:39,383 - mmseg - INFO - Iter [70850/80000] lr: 1.642e-07, eta: 1:35:16, time: 0.653, data_time: 0.055, memory: 60248, decode.loss_ce: 0.1266, decode.acc_seg: 76.6827, aux.loss_ce: 0.0823, aux.acc_seg: 74.9773, loss: 0.2089 +2022-05-05 21:33:08,835 - mmseg - INFO - Iter [70900/80000] lr: 1.633e-07, eta: 1:34:45, time: 0.589, data_time: 0.005, memory: 60248, decode.loss_ce: 0.1247, decode.acc_seg: 76.3313, aux.loss_ce: 0.0832, aux.acc_seg: 74.4724, loss: 0.2079 +2022-05-05 21:33:38,445 - mmseg - INFO - Iter [70950/80000] lr: 1.624e-07, eta: 1:34:14, time: 0.591, data_time: 0.004, memory: 60248, decode.loss_ce: 0.1256, decode.acc_seg: 75.5688, aux.loss_ce: 0.0831, aux.acc_seg: 73.6300, loss: 0.2087 +2022-05-05 21:34:07,996 - mmseg - INFO - Saving checkpoint at 71000 iterations +2022-05-05 21:34:28,312 - mmseg - INFO - Exp name: upernet_beit_adapter_large_512_80k_cocostuff10k_ss.py +2022-05-05 21:34:28,322 - mmseg - INFO - Iter [71000/80000] lr: 1.615e-07, eta: 1:33:45, time: 0.997, data_time: 0.006, memory: 60248, decode.loss_ce: 0.1143, decode.acc_seg: 76.0879, aux.loss_ce: 0.0765, aux.acc_seg: 74.3416, loss: 0.1908 +2022-05-05 21:34:58,021 - mmseg - INFO - Iter [71050/80000] lr: 1.606e-07, eta: 1:33:13, time: 0.596, data_time: 0.007, memory: 60248, decode.loss_ce: 0.1203, decode.acc_seg: 76.1399, aux.loss_ce: 0.0786, aux.acc_seg: 74.5260, loss: 0.1988 +2022-05-05 21:35:27,669 - mmseg - INFO - Iter [71100/80000] lr: 1.598e-07, eta: 1:32:42, time: 0.593, data_time: 0.005, memory: 60248, decode.loss_ce: 0.1241, decode.acc_seg: 76.8690, aux.loss_ce: 0.0806, aux.acc_seg: 75.2253, loss: 0.2048 +2022-05-05 21:35:57,029 - mmseg - INFO - Iter [71150/80000] lr: 1.589e-07, eta: 1:32:10, time: 0.587, data_time: 0.004, memory: 60248, decode.loss_ce: 0.1234, decode.acc_seg: 75.9187, aux.loss_ce: 0.0805, aux.acc_seg: 74.1590, loss: 0.2039 +2022-05-05 21:36:26,480 - mmseg - INFO - Iter [71200/80000] lr: 1.580e-07, eta: 1:31:39, time: 0.589, data_time: 0.005, memory: 60248, decode.loss_ce: 0.1227, decode.acc_seg: 75.7977, aux.loss_ce: 0.0802, aux.acc_seg: 74.0803, loss: 0.2028 +2022-05-05 21:36:55,918 - mmseg - INFO - Iter [71250/80000] lr: 1.571e-07, eta: 1:31:07, time: 0.589, data_time: 0.004, memory: 60248, decode.loss_ce: 0.1269, decode.acc_seg: 76.6420, aux.loss_ce: 0.0833, aux.acc_seg: 74.7512, loss: 0.2102 +2022-05-05 21:37:25,588 - mmseg - INFO - Iter [71300/80000] lr: 1.562e-07, eta: 1:30:36, time: 0.593, data_time: 0.005, memory: 60248, decode.loss_ce: 0.1238, decode.acc_seg: 76.7389, aux.loss_ce: 0.0836, aux.acc_seg: 74.8579, loss: 0.2073 +2022-05-05 21:37:55,151 - mmseg - INFO - Iter [71350/80000] lr: 1.553e-07, eta: 1:30:04, time: 0.591, data_time: 0.005, memory: 60248, decode.loss_ce: 0.1293, decode.acc_seg: 76.9695, aux.loss_ce: 0.0827, aux.acc_seg: 75.3139, loss: 0.2120 +2022-05-05 21:38:27,375 - mmseg - INFO - Iter [71400/80000] lr: 1.544e-07, eta: 1:29:33, time: 0.644, data_time: 0.052, memory: 60248, decode.loss_ce: 0.1255, decode.acc_seg: 77.3473, aux.loss_ce: 0.0826, aux.acc_seg: 75.5254, loss: 0.2082 +2022-05-05 21:38:56,709 - mmseg - INFO - Iter [71450/80000] lr: 1.535e-07, eta: 1:29:02, time: 0.587, data_time: 0.005, memory: 60248, decode.loss_ce: 0.1258, decode.acc_seg: 75.2105, aux.loss_ce: 0.0842, aux.acc_seg: 73.2835, loss: 0.2100 +2022-05-05 21:39:26,272 - mmseg - INFO - Iter [71500/80000] lr: 1.526e-07, eta: 1:28:30, time: 0.591, data_time: 0.005, memory: 60248, decode.loss_ce: 0.1156, decode.acc_seg: 75.6634, aux.loss_ce: 0.0772, aux.acc_seg: 73.8581, loss: 0.1928 +2022-05-05 21:39:55,591 - mmseg - INFO - Iter [71550/80000] lr: 1.517e-07, eta: 1:27:59, time: 0.586, data_time: 0.005, memory: 60248, decode.loss_ce: 0.1245, decode.acc_seg: 77.5856, aux.loss_ce: 0.0836, aux.acc_seg: 75.6482, loss: 0.2081 +2022-05-05 21:40:25,022 - mmseg - INFO - Iter [71600/80000] lr: 1.508e-07, eta: 1:27:28, time: 0.589, data_time: 0.005, memory: 60248, decode.loss_ce: 0.1219, decode.acc_seg: 76.6053, aux.loss_ce: 0.0802, aux.acc_seg: 74.8511, loss: 0.2020 +2022-05-05 21:40:54,501 - mmseg - INFO - Iter [71650/80000] lr: 1.499e-07, eta: 1:26:56, time: 0.590, data_time: 0.005, memory: 60248, decode.loss_ce: 0.1346, decode.acc_seg: 77.2515, aux.loss_ce: 0.0872, aux.acc_seg: 75.4666, loss: 0.2217 +2022-05-05 21:41:24,100 - mmseg - INFO - Iter [71700/80000] lr: 1.490e-07, eta: 1:26:25, time: 0.592, data_time: 0.004, memory: 60248, decode.loss_ce: 0.1279, decode.acc_seg: 75.3555, aux.loss_ce: 0.0847, aux.acc_seg: 73.5130, loss: 0.2126 +2022-05-05 21:41:53,439 - mmseg - INFO - Iter [71750/80000] lr: 1.481e-07, eta: 1:25:53, time: 0.587, data_time: 0.004, memory: 60248, decode.loss_ce: 0.1254, decode.acc_seg: 77.5567, aux.loss_ce: 0.0800, aux.acc_seg: 75.8910, loss: 0.2054 +2022-05-05 21:42:22,975 - mmseg - INFO - Iter [71800/80000] lr: 1.472e-07, eta: 1:25:22, time: 0.591, data_time: 0.005, memory: 60248, decode.loss_ce: 0.1207, decode.acc_seg: 75.9918, aux.loss_ce: 0.0795, aux.acc_seg: 74.1966, loss: 0.2002 +2022-05-05 21:42:52,588 - mmseg - INFO - Iter [71850/80000] lr: 1.463e-07, eta: 1:24:50, time: 0.592, data_time: 0.005, memory: 60248, decode.loss_ce: 0.1263, decode.acc_seg: 77.5873, aux.loss_ce: 0.0820, aux.acc_seg: 75.7757, loss: 0.2083 +2022-05-05 21:43:22,133 - mmseg - INFO - Iter [71900/80000] lr: 1.454e-07, eta: 1:24:19, time: 0.591, data_time: 0.005, memory: 60248, decode.loss_ce: 0.1215, decode.acc_seg: 75.5551, aux.loss_ce: 0.0801, aux.acc_seg: 73.8324, loss: 0.2016 +2022-05-05 21:43:54,178 - mmseg - INFO - Iter [71950/80000] lr: 1.445e-07, eta: 1:23:48, time: 0.641, data_time: 0.054, memory: 60248, decode.loss_ce: 0.1161, decode.acc_seg: 76.6506, aux.loss_ce: 0.0771, aux.acc_seg: 74.8918, loss: 0.1932 +2022-05-05 21:44:23,770 - mmseg - INFO - Saving checkpoint at 72000 iterations +2022-05-05 21:44:44,760 - mmseg - INFO - Exp name: upernet_beit_adapter_large_512_80k_cocostuff10k_ss.py +2022-05-05 21:44:44,762 - mmseg - INFO - Iter [72000/80000] lr: 1.436e-07, eta: 1:23:19, time: 1.010, data_time: 0.004, memory: 60248, decode.loss_ce: 0.1225, decode.acc_seg: 76.4202, aux.loss_ce: 0.0813, aux.acc_seg: 74.5403, loss: 0.2038 +2022-05-05 21:45:14,895 - mmseg - INFO - per class results: +2022-05-05 21:45:14,904 - mmseg - INFO - ++------------------+-------+-------+ +| Class | IoU | Acc | ++------------------+-------+-------+ +| person | 87.67 | 95.24 | +| bicycle | 76.0 | 92.95 | +| car | 64.5 | 71.58 | +| motorcycle | 87.74 | 96.54 | +| airplane | 88.73 | 96.27 | +| bus | 86.73 | 93.48 | +| train | 74.13 | 98.0 | +| truck | 76.54 | 89.79 | +| boat | 72.67 | 88.74 | +| traffic light | 72.55 | 92.15 | +| fire hydrant | 84.14 | 98.19 | +| stop sign | 91.18 | 98.2 | +| parking meter | 75.34 | 78.89 | +| bench | 53.6 | 69.8 | +| bird | 74.73 | 84.23 | +| cat | 92.38 | 97.31 | +| dog | 91.55 | 96.86 | +| horse | 89.39 | 96.48 | +| sheep | 86.03 | 92.74 | +| cow | 94.33 | 98.98 | +| elephant | 91.99 | 97.6 | +| bear | 85.51 | 96.05 | +| zebra | 90.67 | 96.94 | +| giraffe | 86.12 | 95.65 | +| backpack | 21.86 | 54.21 | +| umbrella | 77.0 | 88.97 | +| handbag | 16.53 | 23.11 | +| tie | 58.53 | 58.53 | +| suitcase | 76.27 | 96.85 | +| frisbee | 94.08 | 97.26 | +| skis | 38.78 | 54.76 | +| snowboard | 63.72 | 78.75 | +| sports ball | 85.9 | 91.2 | +| kite | 68.31 | 88.84 | +| baseball bat | 50.98 | 65.34 | +| baseball glove | 1.85 | 1.88 | +| skateboard | 67.78 | 88.12 | +| surfboard | 89.75 | 95.42 | +| tennis racket | 65.55 | 67.77 | +| bottle | 73.83 | 84.74 | +| wine glass | 83.17 | 91.95 | +| cup | 66.75 | 90.13 | +| fork | 52.96 | 69.87 | +| knife | 76.91 | 87.23 | +| spoon | 48.25 | 66.02 | +| bowl | 55.98 | 70.85 | +| banana | 76.65 | 87.34 | +| apple | 72.53 | 89.54 | +| sandwich | 85.46 | 97.2 | +| orange | 69.19 | 92.06 | +| broccoli | 94.53 | 97.45 | +| carrot | 39.71 | 69.95 | +| hot dog | 51.37 | 97.12 | +| pizza | 92.87 | 95.14 | +| donut | 67.11 | 90.94 | +| cake | 58.56 | 68.74 | +| chair | 58.55 | 75.75 | +| couch | 72.95 | 94.86 | +| potted plant | 37.14 | 48.65 | +| bed | 73.69 | 84.21 | +| dining table | 61.75 | 77.68 | +| toilet | 88.13 | 97.24 | +| tv | 69.15 | 92.07 | +| laptop | 86.33 | 98.27 | +| mouse | 72.7 | 80.08 | +| remote | 68.47 | 91.86 | +| keyboard | 83.4 | 98.46 | +| cell phone | 80.82 | 97.19 | +| microwave | 52.33 | 73.91 | +| oven | 63.35 | 85.84 | +| toaster | 52.35 | 52.83 | +| sink | 70.39 | 78.9 | +| refrigerator | 84.51 | 90.43 | +| book | 79.61 | 89.55 | +| clock | 77.01 | 86.89 | +| vase | 62.36 | 91.96 | +| scissors | 78.96 | 91.31 | +| teddy bear | 84.76 | 94.54 | +| hair drier | 0.0 | 0.0 | +| toothbrush | 15.9 | 30.37 | +| banner | 23.63 | 39.23 | +| blanket | 10.22 | 10.34 | +| branch | 1.46 | 1.49 | +| bridge | 2.49 | 3.23 | +| building-other | 55.63 | 75.94 | +| bush | 26.85 | 35.4 | +| cabinet | 15.43 | 26.41 | +| cage | 3.09 | 11.74 | +| cardboard | 23.92 | 28.88 | +| carpet | 59.43 | 76.32 | +| ceiling-other | 71.34 | 86.04 | +| ceiling-tile | 12.61 | 14.12 | +| cloth | 2.71 | 3.8 | +| clothes | 20.91 | 30.2 | +| clouds | 51.51 | 66.02 | +| counter | 35.2 | 43.02 | +| cupboard | 55.25 | 77.64 | +| curtain | 65.47 | 82.47 | +| desk-stuff | 40.27 | 45.05 | +| dirt | 31.11 | 49.53 | +| door-stuff | 49.16 | 62.14 | +| fence | 43.42 | 75.21 | +| floor-marble | 0.0 | 0.0 | +| floor-other | 44.95 | 59.65 | +| floor-stone | 19.81 | 28.03 | +| floor-tile | 61.08 | 75.45 | +| floor-wood | 70.72 | 86.76 | +| flower | 16.15 | 40.57 | +| fog | 0.0 | 0.0 | +| food-other | 39.63 | 53.94 | +| fruit | 59.52 | 69.6 | +| furniture-other | 14.65 | 19.69 | +| grass | 73.62 | 84.92 | +| gravel | 27.78 | 33.22 | +| ground-other | 8.66 | 17.84 | +| hill | 28.61 | 40.61 | +| house | 26.06 | 38.32 | +| leaves | 12.23 | 18.61 | +| light | 41.04 | 53.18 | +| mat | 20.25 | 26.74 | +| metal | 15.2 | 18.51 | +| mirror-stuff | 44.36 | 59.4 | +| moss | 0.0 | 0.0 | +| mountain | 31.98 | 47.66 | +| mud | 11.56 | 21.68 | +| napkin | 14.99 | 21.69 | +| net | 21.38 | 23.96 | +| paper | 56.03 | 66.99 | +| pavement | 56.61 | 73.78 | +| pillow | 0.0 | 0.0 | +| plant-other | 28.46 | 37.73 | +| plastic | 19.86 | 24.07 | +| platform | 39.86 | 55.82 | +| playingfield | 69.17 | 81.54 | +| railing | 15.77 | 23.99 | +| railroad | 63.57 | 87.54 | +| river | 10.63 | 12.88 | +| road | 69.76 | 79.69 | +| rock | 51.62 | 72.9 | +| roof | 5.88 | 9.72 | +| rug | 55.02 | 78.09 | +| salad | 22.11 | 23.64 | +| sand | 74.91 | 87.33 | +| sea | 77.34 | 90.75 | +| shelf | 26.22 | 37.53 | +| sky-other | 60.97 | 76.89 | +| skyscraper | 6.92 | 9.91 | +| snow | 92.15 | 95.28 | +| solid-other | 0.0 | nan | +| stairs | 33.26 | 49.16 | +| stone | 6.77 | 10.28 | +| straw | 14.6 | 33.27 | +| structural-other | 18.88 | 26.48 | +| table | 21.09 | 30.67 | +| tent | 78.21 | 85.01 | +| textile-other | 20.36 | 23.49 | +| towel | 40.74 | 49.65 | +| tree | 77.01 | 89.5 | +| vegetable | 43.87 | 66.45 | +| wall-brick | 40.46 | 51.48 | +| wall-concrete | 20.04 | 25.33 | +| wall-other | 60.35 | 80.36 | +| wall-panel | 5.99 | 6.67 | +| wall-stone | 30.85 | 37.06 | +| wall-tile | 57.21 | 86.92 | +| wall-wood | 39.4 | 59.51 | +| water-other | 36.9 | 53.98 | +| waterdrops | nan | nan | +| window-blind | 24.31 | 47.85 | +| window-other | 46.48 | 60.28 | +| wood | 13.99 | 26.92 | ++------------------+-------+-------+ +2022-05-05 21:45:14,904 - mmseg - INFO - Summary: +2022-05-05 21:45:14,905 - mmseg - INFO - ++-------+-------+-------+ +| aAcc | mIoU | mAcc | ++-------+-------+-------+ +| 75.67 | 50.77 | 62.86 | ++-------+-------+-------+ +2022-05-05 21:45:14,909 - mmseg - INFO - Exp name: upernet_beit_adapter_large_512_80k_cocostuff10k_ss.py +2022-05-05 21:45:14,910 - mmseg - INFO - Iter(val) [125] aAcc: 0.7567, mIoU: 0.5077, mAcc: 0.6286, IoU.person: 0.8767, IoU.bicycle: 0.7600, IoU.car: 0.6450, IoU.motorcycle: 0.8774, IoU.airplane: 0.8873, IoU.bus: 0.8673, IoU.train: 0.7413, IoU.truck: 0.7654, IoU.boat: 0.7267, IoU.traffic light: 0.7255, IoU.fire hydrant: 0.8414, IoU.stop sign: 0.9118, IoU.parking meter: 0.7534, IoU.bench: 0.5360, IoU.bird: 0.7473, IoU.cat: 0.9238, IoU.dog: 0.9155, IoU.horse: 0.8939, IoU.sheep: 0.8603, IoU.cow: 0.9433, IoU.elephant: 0.9199, IoU.bear: 0.8551, IoU.zebra: 0.9067, IoU.giraffe: 0.8612, IoU.backpack: 0.2186, IoU.umbrella: 0.7700, IoU.handbag: 0.1653, IoU.tie: 0.5853, IoU.suitcase: 0.7627, IoU.frisbee: 0.9408, IoU.skis: 0.3878, IoU.snowboard: 0.6372, IoU.sports ball: 0.8590, IoU.kite: 0.6831, IoU.baseball bat: 0.5098, IoU.baseball glove: 0.0185, IoU.skateboard: 0.6778, IoU.surfboard: 0.8975, IoU.tennis racket: 0.6555, IoU.bottle: 0.7383, IoU.wine glass: 0.8317, IoU.cup: 0.6675, IoU.fork: 0.5296, IoU.knife: 0.7691, IoU.spoon: 0.4825, IoU.bowl: 0.5598, IoU.banana: 0.7665, IoU.apple: 0.7253, IoU.sandwich: 0.8546, IoU.orange: 0.6919, IoU.broccoli: 0.9453, IoU.carrot: 0.3971, IoU.hot dog: 0.5137, IoU.pizza: 0.9287, IoU.donut: 0.6711, IoU.cake: 0.5856, IoU.chair: 0.5855, IoU.couch: 0.7295, IoU.potted plant: 0.3714, IoU.bed: 0.7369, IoU.dining table: 0.6175, IoU.toilet: 0.8813, IoU.tv: 0.6915, IoU.laptop: 0.8633, IoU.mouse: 0.7270, IoU.remote: 0.6847, IoU.keyboard: 0.8340, IoU.cell phone: 0.8082, IoU.microwave: 0.5233, IoU.oven: 0.6335, IoU.toaster: 0.5235, IoU.sink: 0.7039, IoU.refrigerator: 0.8451, IoU.book: 0.7961, IoU.clock: 0.7701, IoU.vase: 0.6236, IoU.scissors: 0.7896, IoU.teddy bear: 0.8476, IoU.hair drier: 0.0000, IoU.toothbrush: 0.1590, IoU.banner: 0.2363, IoU.blanket: 0.1022, IoU.branch: 0.0146, IoU.bridge: 0.0249, IoU.building-other: 0.5563, IoU.bush: 0.2685, IoU.cabinet: 0.1543, IoU.cage: 0.0309, IoU.cardboard: 0.2392, IoU.carpet: 0.5943, IoU.ceiling-other: 0.7134, IoU.ceiling-tile: 0.1261, IoU.cloth: 0.0271, IoU.clothes: 0.2091, IoU.clouds: 0.5151, IoU.counter: 0.3520, IoU.cupboard: 0.5525, IoU.curtain: 0.6547, IoU.desk-stuff: 0.4027, IoU.dirt: 0.3111, IoU.door-stuff: 0.4916, IoU.fence: 0.4342, IoU.floor-marble: 0.0000, IoU.floor-other: 0.4495, IoU.floor-stone: 0.1981, IoU.floor-tile: 0.6108, IoU.floor-wood: 0.7072, IoU.flower: 0.1615, IoU.fog: 0.0000, IoU.food-other: 0.3963, IoU.fruit: 0.5952, IoU.furniture-other: 0.1465, IoU.grass: 0.7362, IoU.gravel: 0.2778, IoU.ground-other: 0.0866, IoU.hill: 0.2861, IoU.house: 0.2606, IoU.leaves: 0.1223, IoU.light: 0.4104, IoU.mat: 0.2025, IoU.metal: 0.1520, IoU.mirror-stuff: 0.4436, IoU.moss: 0.0000, IoU.mountain: 0.3198, IoU.mud: 0.1156, IoU.napkin: 0.1499, IoU.net: 0.2138, IoU.paper: 0.5603, IoU.pavement: 0.5661, IoU.pillow: 0.0000, IoU.plant-other: 0.2846, IoU.plastic: 0.1986, IoU.platform: 0.3986, IoU.playingfield: 0.6917, IoU.railing: 0.1577, IoU.railroad: 0.6357, IoU.river: 0.1063, IoU.road: 0.6976, IoU.rock: 0.5162, IoU.roof: 0.0588, IoU.rug: 0.5502, IoU.salad: 0.2211, IoU.sand: 0.7491, IoU.sea: 0.7734, IoU.shelf: 0.2622, IoU.sky-other: 0.6097, IoU.skyscraper: 0.0692, IoU.snow: 0.9215, IoU.solid-other: 0.0000, IoU.stairs: 0.3326, IoU.stone: 0.0677, IoU.straw: 0.1460, IoU.structural-other: 0.1888, IoU.table: 0.2109, IoU.tent: 0.7821, IoU.textile-other: 0.2036, IoU.towel: 0.4074, IoU.tree: 0.7701, IoU.vegetable: 0.4387, IoU.wall-brick: 0.4046, IoU.wall-concrete: 0.2004, IoU.wall-other: 0.6035, IoU.wall-panel: 0.0599, IoU.wall-stone: 0.3085, IoU.wall-tile: 0.5721, IoU.wall-wood: 0.3940, IoU.water-other: 0.3690, IoU.waterdrops: nan, IoU.window-blind: 0.2431, IoU.window-other: 0.4648, IoU.wood: 0.1399, Acc.person: 0.9524, Acc.bicycle: 0.9295, Acc.car: 0.7158, Acc.motorcycle: 0.9654, Acc.airplane: 0.9627, Acc.bus: 0.9348, Acc.train: 0.9800, Acc.truck: 0.8979, Acc.boat: 0.8874, Acc.traffic light: 0.9215, Acc.fire hydrant: 0.9819, Acc.stop sign: 0.9820, Acc.parking meter: 0.7889, Acc.bench: 0.6980, Acc.bird: 0.8423, Acc.cat: 0.9731, Acc.dog: 0.9686, Acc.horse: 0.9648, Acc.sheep: 0.9274, Acc.cow: 0.9898, Acc.elephant: 0.9760, Acc.bear: 0.9605, Acc.zebra: 0.9694, Acc.giraffe: 0.9565, Acc.backpack: 0.5421, Acc.umbrella: 0.8897, Acc.handbag: 0.2311, Acc.tie: 0.5853, Acc.suitcase: 0.9685, Acc.frisbee: 0.9726, Acc.skis: 0.5476, Acc.snowboard: 0.7875, Acc.sports ball: 0.9120, Acc.kite: 0.8884, Acc.baseball bat: 0.6534, Acc.baseball glove: 0.0188, Acc.skateboard: 0.8812, Acc.surfboard: 0.9542, Acc.tennis racket: 0.6777, Acc.bottle: 0.8474, Acc.wine glass: 0.9195, Acc.cup: 0.9013, Acc.fork: 0.6987, Acc.knife: 0.8723, Acc.spoon: 0.6602, Acc.bowl: 0.7085, Acc.banana: 0.8734, Acc.apple: 0.8954, Acc.sandwich: 0.9720, Acc.orange: 0.9206, Acc.broccoli: 0.9745, Acc.carrot: 0.6995, Acc.hot dog: 0.9712, Acc.pizza: 0.9514, Acc.donut: 0.9094, Acc.cake: 0.6874, Acc.chair: 0.7575, Acc.couch: 0.9486, Acc.potted plant: 0.4865, Acc.bed: 0.8421, Acc.dining table: 0.7768, Acc.toilet: 0.9724, Acc.tv: 0.9207, Acc.laptop: 0.9827, Acc.mouse: 0.8008, Acc.remote: 0.9186, Acc.keyboard: 0.9846, Acc.cell phone: 0.9719, Acc.microwave: 0.7391, Acc.oven: 0.8584, Acc.toaster: 0.5283, Acc.sink: 0.7890, Acc.refrigerator: 0.9043, Acc.book: 0.8955, Acc.clock: 0.8689, Acc.vase: 0.9196, Acc.scissors: 0.9131, Acc.teddy bear: 0.9454, Acc.hair drier: 0.0000, Acc.toothbrush: 0.3037, Acc.banner: 0.3923, Acc.blanket: 0.1034, Acc.branch: 0.0149, Acc.bridge: 0.0323, Acc.building-other: 0.7594, Acc.bush: 0.3540, Acc.cabinet: 0.2641, Acc.cage: 0.1174, Acc.cardboard: 0.2888, Acc.carpet: 0.7632, Acc.ceiling-other: 0.8604, Acc.ceiling-tile: 0.1412, Acc.cloth: 0.0380, Acc.clothes: 0.3020, Acc.clouds: 0.6602, Acc.counter: 0.4302, Acc.cupboard: 0.7764, Acc.curtain: 0.8247, Acc.desk-stuff: 0.4505, Acc.dirt: 0.4953, Acc.door-stuff: 0.6214, Acc.fence: 0.7521, Acc.floor-marble: 0.0000, Acc.floor-other: 0.5965, Acc.floor-stone: 0.2803, Acc.floor-tile: 0.7545, Acc.floor-wood: 0.8676, Acc.flower: 0.4057, Acc.fog: 0.0000, Acc.food-other: 0.5394, Acc.fruit: 0.6960, Acc.furniture-other: 0.1969, Acc.grass: 0.8492, Acc.gravel: 0.3322, Acc.ground-other: 0.1784, Acc.hill: 0.4061, Acc.house: 0.3832, Acc.leaves: 0.1861, Acc.light: 0.5318, Acc.mat: 0.2674, Acc.metal: 0.1851, Acc.mirror-stuff: 0.5940, Acc.moss: 0.0000, Acc.mountain: 0.4766, Acc.mud: 0.2168, Acc.napkin: 0.2169, Acc.net: 0.2396, Acc.paper: 0.6699, Acc.pavement: 0.7378, Acc.pillow: 0.0000, Acc.plant-other: 0.3773, Acc.plastic: 0.2407, Acc.platform: 0.5582, Acc.playingfield: 0.8154, Acc.railing: 0.2399, Acc.railroad: 0.8754, Acc.river: 0.1288, Acc.road: 0.7969, Acc.rock: 0.7290, Acc.roof: 0.0972, Acc.rug: 0.7809, Acc.salad: 0.2364, Acc.sand: 0.8733, Acc.sea: 0.9075, Acc.shelf: 0.3753, Acc.sky-other: 0.7689, Acc.skyscraper: 0.0991, Acc.snow: 0.9528, Acc.solid-other: nan, Acc.stairs: 0.4916, Acc.stone: 0.1028, Acc.straw: 0.3327, Acc.structural-other: 0.2648, Acc.table: 0.3067, Acc.tent: 0.8501, Acc.textile-other: 0.2349, Acc.towel: 0.4965, Acc.tree: 0.8950, Acc.vegetable: 0.6645, Acc.wall-brick: 0.5148, Acc.wall-concrete: 0.2533, Acc.wall-other: 0.8036, Acc.wall-panel: 0.0667, Acc.wall-stone: 0.3706, Acc.wall-tile: 0.8692, Acc.wall-wood: 0.5951, Acc.water-other: 0.5398, Acc.waterdrops: nan, Acc.window-blind: 0.4785, Acc.window-other: 0.6028, Acc.wood: 0.2692 +2022-05-05 21:45:44,507 - mmseg - INFO - Iter [72050/80000] lr: 1.427e-07, eta: 1:22:51, time: 1.196, data_time: 0.609, memory: 60248, decode.loss_ce: 0.1313, decode.acc_seg: 75.0693, aux.loss_ce: 0.0848, aux.acc_seg: 73.3312, loss: 0.2161 +2022-05-05 21:46:13,980 - mmseg - INFO - Iter [72100/80000] lr: 1.418e-07, eta: 1:22:19, time: 0.590, data_time: 0.005, memory: 60248, decode.loss_ce: 0.1260, decode.acc_seg: 76.8508, aux.loss_ce: 0.0830, aux.acc_seg: 75.1219, loss: 0.2090 +2022-05-05 21:46:43,353 - mmseg - INFO - Iter [72150/80000] lr: 1.409e-07, eta: 1:21:48, time: 0.588, data_time: 0.006, memory: 60248, decode.loss_ce: 0.1226, decode.acc_seg: 77.2565, aux.loss_ce: 0.0815, aux.acc_seg: 75.4270, loss: 0.2041 +2022-05-05 21:47:13,046 - mmseg - INFO - Iter [72200/80000] lr: 1.400e-07, eta: 1:21:16, time: 0.594, data_time: 0.005, memory: 60248, decode.loss_ce: 0.1252, decode.acc_seg: 75.4273, aux.loss_ce: 0.0815, aux.acc_seg: 73.6878, loss: 0.2066 +2022-05-05 21:47:42,863 - mmseg - INFO - Iter [72250/80000] lr: 1.391e-07, eta: 1:20:45, time: 0.596, data_time: 0.004, memory: 60248, decode.loss_ce: 0.1311, decode.acc_seg: 76.4871, aux.loss_ce: 0.0866, aux.acc_seg: 74.5100, loss: 0.2177 +2022-05-05 21:48:12,313 - mmseg - INFO - Iter [72300/80000] lr: 1.382e-07, eta: 1:20:13, time: 0.589, data_time: 0.005, memory: 60248, decode.loss_ce: 0.1328, decode.acc_seg: 76.4504, aux.loss_ce: 0.0899, aux.acc_seg: 74.4087, loss: 0.2227 +2022-05-05 21:48:42,067 - mmseg - INFO - Iter [72350/80000] lr: 1.373e-07, eta: 1:19:42, time: 0.595, data_time: 0.005, memory: 60248, decode.loss_ce: 0.1278, decode.acc_seg: 76.2755, aux.loss_ce: 0.0824, aux.acc_seg: 74.5291, loss: 0.2103 +2022-05-05 21:49:11,589 - mmseg - INFO - Iter [72400/80000] lr: 1.364e-07, eta: 1:19:11, time: 0.590, data_time: 0.005, memory: 60248, decode.loss_ce: 0.1244, decode.acc_seg: 76.9829, aux.loss_ce: 0.0835, aux.acc_seg: 75.0051, loss: 0.2078 +2022-05-05 21:49:41,215 - mmseg - INFO - Iter [72450/80000] lr: 1.355e-07, eta: 1:18:39, time: 0.592, data_time: 0.005, memory: 60248, decode.loss_ce: 0.1267, decode.acc_seg: 75.5565, aux.loss_ce: 0.0822, aux.acc_seg: 73.7831, loss: 0.2089 +2022-05-05 21:50:13,236 - mmseg - INFO - Iter [72500/80000] lr: 1.346e-07, eta: 1:18:08, time: 0.640, data_time: 0.054, memory: 60248, decode.loss_ce: 0.1225, decode.acc_seg: 75.9972, aux.loss_ce: 0.0804, aux.acc_seg: 74.2556, loss: 0.2029 +2022-05-05 21:50:42,811 - mmseg - INFO - Iter [72550/80000] lr: 1.337e-07, eta: 1:17:36, time: 0.592, data_time: 0.004, memory: 60248, decode.loss_ce: 0.1211, decode.acc_seg: 76.2561, aux.loss_ce: 0.0787, aux.acc_seg: 74.6002, loss: 0.1998 +2022-05-05 21:51:12,313 - mmseg - INFO - Iter [72600/80000] lr: 1.328e-07, eta: 1:17:05, time: 0.590, data_time: 0.004, memory: 60248, decode.loss_ce: 0.1310, decode.acc_seg: 77.1804, aux.loss_ce: 0.0861, aux.acc_seg: 75.2938, loss: 0.2171 +2022-05-05 21:51:41,974 - mmseg - INFO - Iter [72650/80000] lr: 1.319e-07, eta: 1:16:34, time: 0.593, data_time: 0.005, memory: 60248, decode.loss_ce: 0.1273, decode.acc_seg: 76.5113, aux.loss_ce: 0.0835, aux.acc_seg: 74.6306, loss: 0.2108 +2022-05-05 21:52:11,560 - mmseg - INFO - Iter [72700/80000] lr: 1.310e-07, eta: 1:16:02, time: 0.591, data_time: 0.005, memory: 60248, decode.loss_ce: 0.1259, decode.acc_seg: 76.4636, aux.loss_ce: 0.0840, aux.acc_seg: 74.5569, loss: 0.2098 +2022-05-05 21:52:41,058 - mmseg - INFO - Iter [72750/80000] lr: 1.301e-07, eta: 1:15:31, time: 0.590, data_time: 0.005, memory: 60248, decode.loss_ce: 0.1234, decode.acc_seg: 77.3459, aux.loss_ce: 0.0820, aux.acc_seg: 75.6072, loss: 0.2053 +2022-05-05 21:53:10,703 - mmseg - INFO - Iter [72800/80000] lr: 1.292e-07, eta: 1:14:59, time: 0.593, data_time: 0.005, memory: 60248, decode.loss_ce: 0.1221, decode.acc_seg: 76.6773, aux.loss_ce: 0.0809, aux.acc_seg: 74.9259, loss: 0.2030 +2022-05-05 21:53:40,255 - mmseg - INFO - Iter [72850/80000] lr: 1.283e-07, eta: 1:14:28, time: 0.591, data_time: 0.004, memory: 60248, decode.loss_ce: 0.1259, decode.acc_seg: 77.0791, aux.loss_ce: 0.0818, aux.acc_seg: 75.5156, loss: 0.2077 +2022-05-05 21:54:09,871 - mmseg - INFO - Iter [72900/80000] lr: 1.274e-07, eta: 1:13:57, time: 0.592, data_time: 0.004, memory: 60248, decode.loss_ce: 0.1263, decode.acc_seg: 75.4823, aux.loss_ce: 0.0811, aux.acc_seg: 73.6893, loss: 0.2074 +2022-05-05 21:54:39,523 - mmseg - INFO - Iter [72950/80000] lr: 1.265e-07, eta: 1:13:25, time: 0.593, data_time: 0.004, memory: 60248, decode.loss_ce: 0.1214, decode.acc_seg: 76.7129, aux.loss_ce: 0.0787, aux.acc_seg: 74.9819, loss: 0.2002 +2022-05-05 21:55:09,102 - mmseg - INFO - Saving checkpoint at 73000 iterations +2022-05-05 21:55:29,887 - mmseg - INFO - Exp name: upernet_beit_adapter_large_512_80k_cocostuff10k_ss.py +2022-05-05 21:55:29,896 - mmseg - INFO - Iter [73000/80000] lr: 1.257e-07, eta: 1:12:56, time: 1.005, data_time: 0.004, memory: 60248, decode.loss_ce: 0.1307, decode.acc_seg: 76.7885, aux.loss_ce: 0.0850, aux.acc_seg: 75.0787, loss: 0.2157 +2022-05-05 21:55:59,742 - mmseg - INFO - Iter [73050/80000] lr: 1.248e-07, eta: 1:12:24, time: 0.599, data_time: 0.007, memory: 60248, decode.loss_ce: 0.1161, decode.acc_seg: 75.7684, aux.loss_ce: 0.0779, aux.acc_seg: 74.0047, loss: 0.1940 +2022-05-05 21:56:31,538 - mmseg - INFO - Iter [73100/80000] lr: 1.239e-07, eta: 1:11:53, time: 0.636, data_time: 0.052, memory: 60248, decode.loss_ce: 0.1262, decode.acc_seg: 77.6860, aux.loss_ce: 0.0845, aux.acc_seg: 75.8375, loss: 0.2107 +2022-05-05 21:57:01,037 - mmseg - INFO - Iter [73150/80000] lr: 1.230e-07, eta: 1:11:22, time: 0.590, data_time: 0.004, memory: 60248, decode.loss_ce: 0.1263, decode.acc_seg: 77.0688, aux.loss_ce: 0.0846, aux.acc_seg: 75.1967, loss: 0.2109 +2022-05-05 21:57:30,465 - mmseg - INFO - Iter [73200/80000] lr: 1.221e-07, eta: 1:10:50, time: 0.588, data_time: 0.005, memory: 60248, decode.loss_ce: 0.1215, decode.acc_seg: 76.3297, aux.loss_ce: 0.0787, aux.acc_seg: 74.7466, loss: 0.2003 +2022-05-05 21:57:59,815 - mmseg - INFO - Iter [73250/80000] lr: 1.212e-07, eta: 1:10:19, time: 0.587, data_time: 0.005, memory: 60248, decode.loss_ce: 0.1217, decode.acc_seg: 75.8684, aux.loss_ce: 0.0796, aux.acc_seg: 74.1117, loss: 0.2012 +2022-05-05 21:58:29,299 - mmseg - INFO - Iter [73300/80000] lr: 1.203e-07, eta: 1:09:47, time: 0.590, data_time: 0.005, memory: 60248, decode.loss_ce: 0.1213, decode.acc_seg: 77.1900, aux.loss_ce: 0.0793, aux.acc_seg: 75.5609, loss: 0.2007 +2022-05-05 21:58:58,651 - mmseg - INFO - Iter [73350/80000] lr: 1.194e-07, eta: 1:09:16, time: 0.587, data_time: 0.004, memory: 60248, decode.loss_ce: 0.1256, decode.acc_seg: 76.3988, aux.loss_ce: 0.0833, aux.acc_seg: 74.6017, loss: 0.2089 +2022-05-05 21:59:28,099 - mmseg - INFO - Iter [73400/80000] lr: 1.185e-07, eta: 1:08:45, time: 0.589, data_time: 0.005, memory: 60248, decode.loss_ce: 0.1219, decode.acc_seg: 74.6701, aux.loss_ce: 0.0814, aux.acc_seg: 72.9199, loss: 0.2034 +2022-05-05 21:59:57,571 - mmseg - INFO - Iter [73450/80000] lr: 1.176e-07, eta: 1:08:13, time: 0.590, data_time: 0.005, memory: 60248, decode.loss_ce: 0.1272, decode.acc_seg: 75.0356, aux.loss_ce: 0.0824, aux.acc_seg: 73.3646, loss: 0.2096 +2022-05-05 22:00:27,154 - mmseg - INFO - Iter [73500/80000] lr: 1.167e-07, eta: 1:07:42, time: 0.592, data_time: 0.005, memory: 60248, decode.loss_ce: 0.1208, decode.acc_seg: 77.4071, aux.loss_ce: 0.0813, aux.acc_seg: 75.5382, loss: 0.2021 +2022-05-05 22:00:56,515 - mmseg - INFO - Iter [73550/80000] lr: 1.158e-07, eta: 1:07:10, time: 0.587, data_time: 0.005, memory: 60248, decode.loss_ce: 0.1256, decode.acc_seg: 76.4789, aux.loss_ce: 0.0816, aux.acc_seg: 74.8349, loss: 0.2073 +2022-05-05 22:01:25,976 - mmseg - INFO - Iter [73600/80000] lr: 1.149e-07, eta: 1:06:39, time: 0.589, data_time: 0.004, memory: 60248, decode.loss_ce: 0.1219, decode.acc_seg: 75.8592, aux.loss_ce: 0.0782, aux.acc_seg: 74.2336, loss: 0.2001 +2022-05-05 22:01:58,054 - mmseg - INFO - Iter [73650/80000] lr: 1.140e-07, eta: 1:06:08, time: 0.641, data_time: 0.060, memory: 60248, decode.loss_ce: 0.1256, decode.acc_seg: 75.2261, aux.loss_ce: 0.0828, aux.acc_seg: 73.5319, loss: 0.2084 +2022-05-05 22:02:27,838 - mmseg - INFO - Iter [73700/80000] lr: 1.131e-07, eta: 1:05:36, time: 0.597, data_time: 0.006, memory: 60248, decode.loss_ce: 0.1184, decode.acc_seg: 75.1174, aux.loss_ce: 0.0774, aux.acc_seg: 73.4759, loss: 0.1958 +2022-05-05 22:02:57,368 - mmseg - INFO - Iter [73750/80000] lr: 1.122e-07, eta: 1:05:05, time: 0.591, data_time: 0.004, memory: 60248, decode.loss_ce: 0.1213, decode.acc_seg: 76.0162, aux.loss_ce: 0.0815, aux.acc_seg: 74.1424, loss: 0.2028 +2022-05-05 22:03:26,895 - mmseg - INFO - Iter [73800/80000] lr: 1.113e-07, eta: 1:04:34, time: 0.590, data_time: 0.005, memory: 60248, decode.loss_ce: 0.1204, decode.acc_seg: 76.6490, aux.loss_ce: 0.0775, aux.acc_seg: 74.9718, loss: 0.1979 +2022-05-05 22:03:56,611 - mmseg - INFO - Iter [73850/80000] lr: 1.104e-07, eta: 1:04:02, time: 0.594, data_time: 0.004, memory: 60248, decode.loss_ce: 0.1201, decode.acc_seg: 75.7468, aux.loss_ce: 0.0777, aux.acc_seg: 74.0599, loss: 0.1978 +2022-05-05 22:04:26,350 - mmseg - INFO - Iter [73900/80000] lr: 1.095e-07, eta: 1:03:31, time: 0.595, data_time: 0.005, memory: 60248, decode.loss_ce: 0.1278, decode.acc_seg: 76.6449, aux.loss_ce: 0.0837, aux.acc_seg: 74.6549, loss: 0.2115 +2022-05-05 22:04:56,249 - mmseg - INFO - Iter [73950/80000] lr: 1.086e-07, eta: 1:03:00, time: 0.598, data_time: 0.004, memory: 60248, decode.loss_ce: 0.1239, decode.acc_seg: 77.5957, aux.loss_ce: 0.0828, aux.acc_seg: 75.8228, loss: 0.2066 +2022-05-05 22:05:25,634 - mmseg - INFO - Saving checkpoint at 74000 iterations +2022-05-05 22:05:48,089 - mmseg - INFO - Exp name: upernet_beit_adapter_large_512_80k_cocostuff10k_ss.py +2022-05-05 22:05:48,107 - mmseg - INFO - Iter [74000/80000] lr: 1.077e-07, eta: 1:02:30, time: 1.036, data_time: 0.005, memory: 60248, decode.loss_ce: 0.1327, decode.acc_seg: 76.6746, aux.loss_ce: 0.0857, aux.acc_seg: 74.9980, loss: 0.2183 +2022-05-05 22:06:18,101 - mmseg - INFO - Iter [74050/80000] lr: 1.068e-07, eta: 1:01:59, time: 0.601, data_time: 0.005, memory: 60248, decode.loss_ce: 0.1263, decode.acc_seg: 75.6280, aux.loss_ce: 0.0831, aux.acc_seg: 73.7969, loss: 0.2094 +2022-05-05 22:06:47,935 - mmseg - INFO - Iter [74100/80000] lr: 1.059e-07, eta: 1:01:27, time: 0.595, data_time: 0.004, memory: 60248, decode.loss_ce: 0.1333, decode.acc_seg: 77.2097, aux.loss_ce: 0.0872, aux.acc_seg: 75.3574, loss: 0.2205 +2022-05-05 22:07:17,561 - mmseg - INFO - Iter [74150/80000] lr: 1.050e-07, eta: 1:00:56, time: 0.593, data_time: 0.006, memory: 60248, decode.loss_ce: 0.1339, decode.acc_seg: 77.6853, aux.loss_ce: 0.0875, aux.acc_seg: 75.7236, loss: 0.2214 +2022-05-05 22:07:49,735 - mmseg - INFO - Iter [74200/80000] lr: 1.041e-07, eta: 1:00:25, time: 0.645, data_time: 0.055, memory: 60248, decode.loss_ce: 0.1250, decode.acc_seg: 76.2988, aux.loss_ce: 0.0815, aux.acc_seg: 74.6236, loss: 0.2066 +2022-05-05 22:08:19,694 - mmseg - INFO - Iter [74250/80000] lr: 1.032e-07, eta: 0:59:53, time: 0.599, data_time: 0.005, memory: 60248, decode.loss_ce: 0.1227, decode.acc_seg: 76.0673, aux.loss_ce: 0.0802, aux.acc_seg: 74.3505, loss: 0.2029 +2022-05-05 22:08:48,999 - mmseg - INFO - Iter [74300/80000] lr: 1.023e-07, eta: 0:59:22, time: 0.586, data_time: 0.005, memory: 60248, decode.loss_ce: 0.1221, decode.acc_seg: 76.1691, aux.loss_ce: 0.0807, aux.acc_seg: 74.3350, loss: 0.2028 +2022-05-05 22:09:18,704 - mmseg - INFO - Iter [74350/80000] lr: 1.014e-07, eta: 0:58:51, time: 0.594, data_time: 0.004, memory: 60248, decode.loss_ce: 0.1216, decode.acc_seg: 76.7306, aux.loss_ce: 0.0807, aux.acc_seg: 74.9621, loss: 0.2023 +2022-05-05 22:09:48,454 - mmseg - INFO - Iter [74400/80000] lr: 1.005e-07, eta: 0:58:19, time: 0.595, data_time: 0.005, memory: 60248, decode.loss_ce: 0.1305, decode.acc_seg: 74.8995, aux.loss_ce: 0.0843, aux.acc_seg: 73.1368, loss: 0.2148 +2022-05-05 22:10:18,012 - mmseg - INFO - Iter [74450/80000] lr: 9.963e-08, eta: 0:57:48, time: 0.591, data_time: 0.005, memory: 60248, decode.loss_ce: 0.1224, decode.acc_seg: 76.4343, aux.loss_ce: 0.0821, aux.acc_seg: 74.5304, loss: 0.2046 +2022-05-05 22:10:47,514 - mmseg - INFO - Iter [74500/80000] lr: 9.873e-08, eta: 0:57:16, time: 0.590, data_time: 0.004, memory: 60248, decode.loss_ce: 0.1182, decode.acc_seg: 76.0544, aux.loss_ce: 0.0779, aux.acc_seg: 74.2902, loss: 0.1961 +2022-05-05 22:11:16,930 - mmseg - INFO - Iter [74550/80000] lr: 9.783e-08, eta: 0:56:45, time: 0.588, data_time: 0.004, memory: 60248, decode.loss_ce: 0.1264, decode.acc_seg: 76.6951, aux.loss_ce: 0.0826, aux.acc_seg: 74.8671, loss: 0.2090 +2022-05-05 22:11:46,474 - mmseg - INFO - Iter [74600/80000] lr: 9.693e-08, eta: 0:56:14, time: 0.591, data_time: 0.007, memory: 60248, decode.loss_ce: 0.1251, decode.acc_seg: 76.5117, aux.loss_ce: 0.0828, aux.acc_seg: 74.6996, loss: 0.2079 +2022-05-05 22:12:15,777 - mmseg - INFO - Iter [74650/80000] lr: 9.604e-08, eta: 0:55:42, time: 0.586, data_time: 0.004, memory: 60248, decode.loss_ce: 0.1144, decode.acc_seg: 75.0833, aux.loss_ce: 0.0761, aux.acc_seg: 73.3480, loss: 0.1906 +2022-05-05 22:12:45,467 - mmseg - INFO - Iter [74700/80000] lr: 9.514e-08, eta: 0:55:11, time: 0.594, data_time: 0.005, memory: 60248, decode.loss_ce: 0.1179, decode.acc_seg: 76.4845, aux.loss_ce: 0.0763, aux.acc_seg: 74.8625, loss: 0.1942 +2022-05-05 22:13:17,260 - mmseg - INFO - Iter [74750/80000] lr: 9.424e-08, eta: 0:54:40, time: 0.636, data_time: 0.052, memory: 60248, decode.loss_ce: 0.1239, decode.acc_seg: 75.0498, aux.loss_ce: 0.0830, aux.acc_seg: 73.1133, loss: 0.2069 +2022-05-05 22:13:47,109 - mmseg - INFO - Iter [74800/80000] lr: 9.334e-08, eta: 0:54:08, time: 0.597, data_time: 0.004, memory: 60248, decode.loss_ce: 0.1252, decode.acc_seg: 77.4747, aux.loss_ce: 0.0830, aux.acc_seg: 75.6575, loss: 0.2082 +2022-05-05 22:14:16,947 - mmseg - INFO - Iter [74850/80000] lr: 9.245e-08, eta: 0:53:37, time: 0.597, data_time: 0.005, memory: 60248, decode.loss_ce: 0.1215, decode.acc_seg: 76.8244, aux.loss_ce: 0.0813, aux.acc_seg: 74.9759, loss: 0.2028 +2022-05-05 22:14:46,691 - mmseg - INFO - Iter [74900/80000] lr: 9.155e-08, eta: 0:53:06, time: 0.595, data_time: 0.004, memory: 60248, decode.loss_ce: 0.1243, decode.acc_seg: 76.3016, aux.loss_ce: 0.0829, aux.acc_seg: 74.4255, loss: 0.2072 +2022-05-05 22:15:16,461 - mmseg - INFO - Iter [74950/80000] lr: 9.065e-08, eta: 0:52:34, time: 0.595, data_time: 0.004, memory: 60248, decode.loss_ce: 0.1213, decode.acc_seg: 76.4076, aux.loss_ce: 0.0816, aux.acc_seg: 74.4648, loss: 0.2028 +2022-05-05 22:15:46,123 - mmseg - INFO - Saving checkpoint at 75000 iterations +2022-05-05 22:16:06,440 - mmseg - INFO - Exp name: upernet_beit_adapter_large_512_80k_cocostuff10k_ss.py +2022-05-05 22:16:06,448 - mmseg - INFO - Iter [75000/80000] lr: 8.976e-08, eta: 0:52:04, time: 0.998, data_time: 0.006, memory: 60248, decode.loss_ce: 0.1187, decode.acc_seg: 75.5019, aux.loss_ce: 0.0784, aux.acc_seg: 73.7973, loss: 0.1971 +2022-05-05 22:16:36,146 - mmseg - INFO - Iter [75050/80000] lr: 8.886e-08, eta: 0:51:33, time: 0.595, data_time: 0.007, memory: 60248, decode.loss_ce: 0.1223, decode.acc_seg: 75.8148, aux.loss_ce: 0.0804, aux.acc_seg: 74.1090, loss: 0.2026 +2022-05-05 22:17:05,715 - mmseg - INFO - Iter [75100/80000] lr: 8.796e-08, eta: 0:51:02, time: 0.592, data_time: 0.005, memory: 60248, decode.loss_ce: 0.1231, decode.acc_seg: 76.4397, aux.loss_ce: 0.0791, aux.acc_seg: 74.7316, loss: 0.2022 +2022-05-05 22:17:35,310 - mmseg - INFO - Iter [75150/80000] lr: 8.706e-08, eta: 0:50:30, time: 0.592, data_time: 0.005, memory: 60248, decode.loss_ce: 0.1310, decode.acc_seg: 76.8482, aux.loss_ce: 0.0855, aux.acc_seg: 75.0244, loss: 0.2165 +2022-05-05 22:18:04,925 - mmseg - INFO - Iter [75200/80000] lr: 8.617e-08, eta: 0:49:59, time: 0.592, data_time: 0.005, memory: 60248, decode.loss_ce: 0.1252, decode.acc_seg: 76.1617, aux.loss_ce: 0.0835, aux.acc_seg: 74.3010, loss: 0.2087 +2022-05-05 22:18:34,592 - mmseg - INFO - Iter [75250/80000] lr: 8.527e-08, eta: 0:49:28, time: 0.593, data_time: 0.004, memory: 60248, decode.loss_ce: 0.1222, decode.acc_seg: 76.4009, aux.loss_ce: 0.0804, aux.acc_seg: 74.6149, loss: 0.2026 +2022-05-05 22:19:04,251 - mmseg - INFO - Iter [75300/80000] lr: 8.437e-08, eta: 0:48:56, time: 0.593, data_time: 0.005, memory: 60248, decode.loss_ce: 0.1257, decode.acc_seg: 75.6334, aux.loss_ce: 0.0801, aux.acc_seg: 73.9642, loss: 0.2058 +2022-05-05 22:19:36,332 - mmseg - INFO - Iter [75350/80000] lr: 8.347e-08, eta: 0:48:25, time: 0.642, data_time: 0.052, memory: 60248, decode.loss_ce: 0.1205, decode.acc_seg: 76.7980, aux.loss_ce: 0.0808, aux.acc_seg: 74.7868, loss: 0.2013 +2022-05-05 22:20:06,028 - mmseg - INFO - Iter [75400/80000] lr: 8.258e-08, eta: 0:47:54, time: 0.593, data_time: 0.004, memory: 60248, decode.loss_ce: 0.1199, decode.acc_seg: 76.8578, aux.loss_ce: 0.0786, aux.acc_seg: 75.2248, loss: 0.1986 +2022-05-05 22:20:36,167 - mmseg - INFO - Iter [75450/80000] lr: 8.168e-08, eta: 0:47:23, time: 0.603, data_time: 0.007, memory: 60248, decode.loss_ce: 0.1247, decode.acc_seg: 76.8051, aux.loss_ce: 0.0830, aux.acc_seg: 75.0411, loss: 0.2076 +2022-05-05 22:21:05,490 - mmseg - INFO - Iter [75500/80000] lr: 8.078e-08, eta: 0:46:51, time: 0.587, data_time: 0.005, memory: 60248, decode.loss_ce: 0.1275, decode.acc_seg: 75.4830, aux.loss_ce: 0.0831, aux.acc_seg: 73.7357, loss: 0.2105 +2022-05-05 22:21:34,923 - mmseg - INFO - Iter [75550/80000] lr: 7.988e-08, eta: 0:46:20, time: 0.589, data_time: 0.005, memory: 60248, decode.loss_ce: 0.1246, decode.acc_seg: 77.1111, aux.loss_ce: 0.0847, aux.acc_seg: 75.1226, loss: 0.2093 +2022-05-05 22:22:04,717 - mmseg - INFO - Iter [75600/80000] lr: 7.899e-08, eta: 0:45:48, time: 0.596, data_time: 0.005, memory: 60248, decode.loss_ce: 0.1163, decode.acc_seg: 76.5083, aux.loss_ce: 0.0770, aux.acc_seg: 74.8543, loss: 0.1933 +2022-05-05 22:22:34,304 - mmseg - INFO - Iter [75650/80000] lr: 7.809e-08, eta: 0:45:17, time: 0.592, data_time: 0.005, memory: 60248, decode.loss_ce: 0.1292, decode.acc_seg: 75.6033, aux.loss_ce: 0.0845, aux.acc_seg: 73.7316, loss: 0.2137 +2022-05-05 22:23:03,855 - mmseg - INFO - Iter [75700/80000] lr: 7.719e-08, eta: 0:44:46, time: 0.591, data_time: 0.004, memory: 60248, decode.loss_ce: 0.1238, decode.acc_seg: 74.8040, aux.loss_ce: 0.0808, aux.acc_seg: 73.0353, loss: 0.2045 +2022-05-05 22:23:33,522 - mmseg - INFO - Iter [75750/80000] lr: 7.629e-08, eta: 0:44:15, time: 0.593, data_time: 0.005, memory: 60248, decode.loss_ce: 0.1220, decode.acc_seg: 76.4997, aux.loss_ce: 0.0804, aux.acc_seg: 74.6568, loss: 0.2024 +2022-05-05 22:24:03,226 - mmseg - INFO - Iter [75800/80000] lr: 7.540e-08, eta: 0:43:43, time: 0.594, data_time: 0.004, memory: 60248, decode.loss_ce: 0.1267, decode.acc_seg: 77.3748, aux.loss_ce: 0.0836, aux.acc_seg: 75.5988, loss: 0.2103 +2022-05-05 22:24:32,836 - mmseg - INFO - Iter [75850/80000] lr: 7.450e-08, eta: 0:43:12, time: 0.592, data_time: 0.004, memory: 60248, decode.loss_ce: 0.1173, decode.acc_seg: 76.7189, aux.loss_ce: 0.0787, aux.acc_seg: 74.9607, loss: 0.1960 +2022-05-05 22:25:05,114 - mmseg - INFO - Iter [75900/80000] lr: 7.360e-08, eta: 0:42:41, time: 0.646, data_time: 0.053, memory: 60248, decode.loss_ce: 0.1246, decode.acc_seg: 76.4395, aux.loss_ce: 0.0825, aux.acc_seg: 74.7331, loss: 0.2071 +2022-05-05 22:25:34,722 - mmseg - INFO - Iter [75950/80000] lr: 7.271e-08, eta: 0:42:09, time: 0.592, data_time: 0.005, memory: 60248, decode.loss_ce: 0.1238, decode.acc_seg: 77.3689, aux.loss_ce: 0.0824, aux.acc_seg: 75.6382, loss: 0.2061 +2022-05-05 22:26:04,114 - mmseg - INFO - Saving checkpoint at 76000 iterations +2022-05-05 22:26:24,340 - mmseg - INFO - Exp name: upernet_beit_adapter_large_512_80k_cocostuff10k_ss.py +2022-05-05 22:26:24,343 - mmseg - INFO - Iter [76000/80000] lr: 7.181e-08, eta: 0:41:39, time: 0.990, data_time: 0.005, memory: 60248, decode.loss_ce: 0.1188, decode.acc_seg: 76.8364, aux.loss_ce: 0.0823, aux.acc_seg: 74.7799, loss: 0.2011 +2022-05-05 22:26:54,419 - mmseg - INFO - Iter [76050/80000] lr: 7.091e-08, eta: 0:41:08, time: 0.602, data_time: 0.007, memory: 60248, decode.loss_ce: 0.1223, decode.acc_seg: 76.0669, aux.loss_ce: 0.0809, aux.acc_seg: 74.3177, loss: 0.2031 +2022-05-05 22:27:24,405 - mmseg - INFO - Iter [76100/80000] lr: 7.001e-08, eta: 0:40:36, time: 0.602, data_time: 0.007, memory: 60248, decode.loss_ce: 0.1248, decode.acc_seg: 75.3556, aux.loss_ce: 0.0813, aux.acc_seg: 73.5267, loss: 0.2061 +2022-05-05 22:27:54,383 - mmseg - INFO - Iter [76150/80000] lr: 6.912e-08, eta: 0:40:05, time: 0.600, data_time: 0.004, memory: 60248, decode.loss_ce: 0.1196, decode.acc_seg: 76.3668, aux.loss_ce: 0.0803, aux.acc_seg: 74.5622, loss: 0.1998 +2022-05-05 22:28:24,001 - mmseg - INFO - Iter [76200/80000] lr: 6.822e-08, eta: 0:39:34, time: 0.592, data_time: 0.006, memory: 60248, decode.loss_ce: 0.1206, decode.acc_seg: 76.2566, aux.loss_ce: 0.0798, aux.acc_seg: 74.5465, loss: 0.2004 +2022-05-05 22:28:53,292 - mmseg - INFO - Iter [76250/80000] lr: 6.732e-08, eta: 0:39:03, time: 0.586, data_time: 0.004, memory: 60248, decode.loss_ce: 0.1268, decode.acc_seg: 77.2208, aux.loss_ce: 0.0845, aux.acc_seg: 75.2434, loss: 0.2113 +2022-05-05 22:29:22,903 - mmseg - INFO - Iter [76300/80000] lr: 6.642e-08, eta: 0:38:31, time: 0.592, data_time: 0.004, memory: 60248, decode.loss_ce: 0.1225, decode.acc_seg: 75.8858, aux.loss_ce: 0.0828, aux.acc_seg: 73.8364, loss: 0.2053 +2022-05-05 22:29:52,229 - mmseg - INFO - Iter [76350/80000] lr: 6.553e-08, eta: 0:38:00, time: 0.587, data_time: 0.004, memory: 60248, decode.loss_ce: 0.1221, decode.acc_seg: 75.5728, aux.loss_ce: 0.0805, aux.acc_seg: 73.8589, loss: 0.2026 +2022-05-05 22:30:21,862 - mmseg - INFO - Iter [76400/80000] lr: 6.463e-08, eta: 0:37:29, time: 0.592, data_time: 0.005, memory: 60248, decode.loss_ce: 0.1248, decode.acc_seg: 77.7847, aux.loss_ce: 0.0813, aux.acc_seg: 76.0692, loss: 0.2061 +2022-05-05 22:30:54,368 - mmseg - INFO - Iter [76450/80000] lr: 6.373e-08, eta: 0:36:57, time: 0.650, data_time: 0.059, memory: 60248, decode.loss_ce: 0.1211, decode.acc_seg: 76.4809, aux.loss_ce: 0.0800, aux.acc_seg: 74.7783, loss: 0.2011 +2022-05-05 22:31:23,989 - mmseg - INFO - Iter [76500/80000] lr: 6.283e-08, eta: 0:36:26, time: 0.593, data_time: 0.005, memory: 60248, decode.loss_ce: 0.1206, decode.acc_seg: 76.2870, aux.loss_ce: 0.0793, aux.acc_seg: 74.4691, loss: 0.1998 +2022-05-05 22:31:53,450 - mmseg - INFO - Iter [76550/80000] lr: 6.194e-08, eta: 0:35:55, time: 0.589, data_time: 0.004, memory: 60248, decode.loss_ce: 0.1292, decode.acc_seg: 76.3296, aux.loss_ce: 0.0853, aux.acc_seg: 74.4816, loss: 0.2145 +2022-05-05 22:32:23,029 - mmseg - INFO - Iter [76600/80000] lr: 6.104e-08, eta: 0:35:23, time: 0.592, data_time: 0.004, memory: 60248, decode.loss_ce: 0.1235, decode.acc_seg: 76.4430, aux.loss_ce: 0.0811, aux.acc_seg: 74.7218, loss: 0.2046 +2022-05-05 22:32:52,550 - mmseg - INFO - Iter [76650/80000] lr: 6.014e-08, eta: 0:34:52, time: 0.590, data_time: 0.004, memory: 60248, decode.loss_ce: 0.1191, decode.acc_seg: 76.0436, aux.loss_ce: 0.0796, aux.acc_seg: 74.2801, loss: 0.1986 +2022-05-05 22:33:22,059 - mmseg - INFO - Iter [76700/80000] lr: 5.924e-08, eta: 0:34:21, time: 0.590, data_time: 0.005, memory: 60248, decode.loss_ce: 0.1264, decode.acc_seg: 75.9838, aux.loss_ce: 0.0836, aux.acc_seg: 74.1074, loss: 0.2100 +2022-05-05 22:33:51,589 - mmseg - INFO - Iter [76750/80000] lr: 5.835e-08, eta: 0:33:50, time: 0.591, data_time: 0.005, memory: 60248, decode.loss_ce: 0.1257, decode.acc_seg: 75.9941, aux.loss_ce: 0.0839, aux.acc_seg: 74.0621, loss: 0.2096 +2022-05-05 22:34:21,458 - mmseg - INFO - Iter [76800/80000] lr: 5.745e-08, eta: 0:33:18, time: 0.595, data_time: 0.004, memory: 60248, decode.loss_ce: 0.1183, decode.acc_seg: 77.8349, aux.loss_ce: 0.0787, aux.acc_seg: 75.9600, loss: 0.1970 +2022-05-05 22:34:50,862 - mmseg - INFO - Iter [76850/80000] lr: 5.655e-08, eta: 0:32:47, time: 0.590, data_time: 0.007, memory: 60248, decode.loss_ce: 0.1236, decode.acc_seg: 76.0989, aux.loss_ce: 0.0823, aux.acc_seg: 74.2406, loss: 0.2059 +2022-05-05 22:35:20,479 - mmseg - INFO - Iter [76900/80000] lr: 5.566e-08, eta: 0:32:16, time: 0.592, data_time: 0.005, memory: 60248, decode.loss_ce: 0.1251, decode.acc_seg: 75.6418, aux.loss_ce: 0.0835, aux.acc_seg: 73.7651, loss: 0.2085 +2022-05-05 22:35:50,166 - mmseg - INFO - Iter [76950/80000] lr: 5.476e-08, eta: 0:31:44, time: 0.594, data_time: 0.005, memory: 60248, decode.loss_ce: 0.1200, decode.acc_seg: 76.2847, aux.loss_ce: 0.0801, aux.acc_seg: 74.5876, loss: 0.2001 +2022-05-05 22:36:22,450 - mmseg - INFO - Saving checkpoint at 77000 iterations +2022-05-05 22:36:43,526 - mmseg - INFO - Exp name: upernet_beit_adapter_large_512_80k_cocostuff10k_ss.py +2022-05-05 22:36:43,533 - mmseg - INFO - Iter [77000/80000] lr: 5.386e-08, eta: 0:31:14, time: 1.065, data_time: 0.058, memory: 60248, decode.loss_ce: 0.1207, decode.acc_seg: 75.7635, aux.loss_ce: 0.0805, aux.acc_seg: 73.9792, loss: 0.2013 +2022-05-05 22:37:13,216 - mmseg - INFO - Iter [77050/80000] lr: 5.296e-08, eta: 0:30:43, time: 0.596, data_time: 0.007, memory: 60248, decode.loss_ce: 0.1242, decode.acc_seg: 75.6647, aux.loss_ce: 0.0811, aux.acc_seg: 73.8557, loss: 0.2052 +2022-05-05 22:37:42,990 - mmseg - INFO - Iter [77100/80000] lr: 5.207e-08, eta: 0:30:11, time: 0.595, data_time: 0.004, memory: 60248, decode.loss_ce: 0.1233, decode.acc_seg: 76.3905, aux.loss_ce: 0.0834, aux.acc_seg: 74.5312, loss: 0.2067 +2022-05-05 22:38:12,552 - mmseg - INFO - Iter [77150/80000] lr: 5.117e-08, eta: 0:29:40, time: 0.592, data_time: 0.005, memory: 60248, decode.loss_ce: 0.1201, decode.acc_seg: 75.9893, aux.loss_ce: 0.0801, aux.acc_seg: 74.0722, loss: 0.2002 +2022-05-05 22:38:42,505 - mmseg - INFO - Iter [77200/80000] lr: 5.027e-08, eta: 0:29:09, time: 0.597, data_time: 0.004, memory: 60248, decode.loss_ce: 0.1257, decode.acc_seg: 75.3241, aux.loss_ce: 0.0820, aux.acc_seg: 73.5020, loss: 0.2077 +2022-05-05 22:39:11,873 - mmseg - INFO - Iter [77250/80000] lr: 4.937e-08, eta: 0:28:37, time: 0.589, data_time: 0.006, memory: 60248, decode.loss_ce: 0.1191, decode.acc_seg: 76.0965, aux.loss_ce: 0.0776, aux.acc_seg: 74.4442, loss: 0.1967 +2022-05-05 22:39:41,493 - mmseg - INFO - Iter [77300/80000] lr: 4.848e-08, eta: 0:28:06, time: 0.592, data_time: 0.004, memory: 60248, decode.loss_ce: 0.1287, decode.acc_seg: 75.1012, aux.loss_ce: 0.0842, aux.acc_seg: 73.2075, loss: 0.2130 +2022-05-05 22:40:11,496 - mmseg - INFO - Iter [77350/80000] lr: 4.758e-08, eta: 0:27:35, time: 0.600, data_time: 0.004, memory: 60248, decode.loss_ce: 0.1240, decode.acc_seg: 76.8134, aux.loss_ce: 0.0826, aux.acc_seg: 75.0576, loss: 0.2067 +2022-05-05 22:40:41,085 - mmseg - INFO - Iter [77400/80000] lr: 4.668e-08, eta: 0:27:04, time: 0.592, data_time: 0.004, memory: 60248, decode.loss_ce: 0.1239, decode.acc_seg: 77.7596, aux.loss_ce: 0.0825, aux.acc_seg: 75.8429, loss: 0.2065 +2022-05-05 22:41:10,700 - mmseg - INFO - Iter [77450/80000] lr: 4.578e-08, eta: 0:26:32, time: 0.592, data_time: 0.004, memory: 60248, decode.loss_ce: 0.1259, decode.acc_seg: 76.1227, aux.loss_ce: 0.0824, aux.acc_seg: 74.4147, loss: 0.2083 +2022-05-05 22:41:40,199 - mmseg - INFO - Iter [77500/80000] lr: 4.489e-08, eta: 0:26:01, time: 0.590, data_time: 0.004, memory: 60248, decode.loss_ce: 0.1270, decode.acc_seg: 76.5524, aux.loss_ce: 0.0851, aux.acc_seg: 74.5102, loss: 0.2121 +2022-05-05 22:42:09,787 - mmseg - INFO - Iter [77550/80000] lr: 4.399e-08, eta: 0:25:30, time: 0.592, data_time: 0.005, memory: 60248, decode.loss_ce: 0.1220, decode.acc_seg: 76.9486, aux.loss_ce: 0.0821, aux.acc_seg: 75.0099, loss: 0.2041 +2022-05-05 22:42:42,030 - mmseg - INFO - Iter [77600/80000] lr: 4.309e-08, eta: 0:24:59, time: 0.645, data_time: 0.053, memory: 60248, decode.loss_ce: 0.1219, decode.acc_seg: 77.3794, aux.loss_ce: 0.0814, aux.acc_seg: 75.5959, loss: 0.2033 +2022-05-05 22:43:11,822 - mmseg - INFO - Iter [77650/80000] lr: 4.219e-08, eta: 0:24:27, time: 0.596, data_time: 0.005, memory: 60248, decode.loss_ce: 0.1178, decode.acc_seg: 77.0854, aux.loss_ce: 0.0785, aux.acc_seg: 75.2989, loss: 0.1963 +2022-05-05 22:43:41,186 - mmseg - INFO - Iter [77700/80000] lr: 4.130e-08, eta: 0:23:56, time: 0.587, data_time: 0.004, memory: 60248, decode.loss_ce: 0.1218, decode.acc_seg: 77.4526, aux.loss_ce: 0.0819, aux.acc_seg: 75.6396, loss: 0.2037 +2022-05-05 22:44:10,617 - mmseg - INFO - Iter [77750/80000] lr: 4.040e-08, eta: 0:23:25, time: 0.589, data_time: 0.004, memory: 60248, decode.loss_ce: 0.1288, decode.acc_seg: 77.1502, aux.loss_ce: 0.0829, aux.acc_seg: 75.4318, loss: 0.2116 +2022-05-05 22:44:40,047 - mmseg - INFO - Iter [77800/80000] lr: 3.950e-08, eta: 0:22:53, time: 0.588, data_time: 0.005, memory: 60248, decode.loss_ce: 0.1211, decode.acc_seg: 76.0208, aux.loss_ce: 0.0814, aux.acc_seg: 74.1797, loss: 0.2026 +2022-05-05 22:45:09,351 - mmseg - INFO - Iter [77850/80000] lr: 3.860e-08, eta: 0:22:22, time: 0.587, data_time: 0.005, memory: 60248, decode.loss_ce: 0.1167, decode.acc_seg: 77.5202, aux.loss_ce: 0.0787, aux.acc_seg: 75.7893, loss: 0.1954 +2022-05-05 22:45:39,173 - mmseg - INFO - Iter [77900/80000] lr: 3.771e-08, eta: 0:21:51, time: 0.596, data_time: 0.005, memory: 60248, decode.loss_ce: 0.1259, decode.acc_seg: 75.6880, aux.loss_ce: 0.0810, aux.acc_seg: 73.9890, loss: 0.2069 +2022-05-05 22:46:08,570 - mmseg - INFO - Iter [77950/80000] lr: 3.681e-08, eta: 0:21:20, time: 0.588, data_time: 0.004, memory: 60248, decode.loss_ce: 0.1291, decode.acc_seg: 76.3729, aux.loss_ce: 0.0844, aux.acc_seg: 74.6806, loss: 0.2135 +2022-05-05 22:46:38,260 - mmseg - INFO - Saving checkpoint at 78000 iterations +2022-05-05 22:46:58,301 - mmseg - INFO - Exp name: upernet_beit_adapter_large_512_80k_cocostuff10k_ss.py +2022-05-05 22:46:58,304 - mmseg - INFO - Iter [78000/80000] lr: 3.591e-08, eta: 0:20:49, time: 0.992, data_time: 0.005, memory: 60248, decode.loss_ce: 0.1184, decode.acc_seg: 75.1405, aux.loss_ce: 0.0794, aux.acc_seg: 73.2980, loss: 0.1978 +2022-05-05 22:47:27,977 - mmseg - INFO - Iter [78050/80000] lr: 3.502e-08, eta: 0:20:18, time: 0.596, data_time: 0.006, memory: 60248, decode.loss_ce: 0.1214, decode.acc_seg: 76.0367, aux.loss_ce: 0.0785, aux.acc_seg: 74.4108, loss: 0.1999 +2022-05-05 22:47:57,640 - mmseg - INFO - Iter [78100/80000] lr: 3.412e-08, eta: 0:19:46, time: 0.593, data_time: 0.004, memory: 60248, decode.loss_ce: 0.1220, decode.acc_seg: 77.7676, aux.loss_ce: 0.0807, aux.acc_seg: 76.0483, loss: 0.2027 +2022-05-05 22:48:29,720 - mmseg - INFO - Iter [78150/80000] lr: 3.322e-08, eta: 0:19:15, time: 0.642, data_time: 0.055, memory: 60248, decode.loss_ce: 0.1209, decode.acc_seg: 76.8275, aux.loss_ce: 0.0791, aux.acc_seg: 75.2277, loss: 0.2000 +2022-05-05 22:48:59,436 - mmseg - INFO - Iter [78200/80000] lr: 3.232e-08, eta: 0:18:44, time: 0.594, data_time: 0.004, memory: 60248, decode.loss_ce: 0.1165, decode.acc_seg: 77.5460, aux.loss_ce: 0.0775, aux.acc_seg: 75.7788, loss: 0.1940 +2022-05-05 22:49:28,904 - mmseg - INFO - Iter [78250/80000] lr: 3.143e-08, eta: 0:18:13, time: 0.589, data_time: 0.004, memory: 60248, decode.loss_ce: 0.1196, decode.acc_seg: 75.8698, aux.loss_ce: 0.0799, aux.acc_seg: 74.0541, loss: 0.1995 +2022-05-05 22:49:58,747 - mmseg - INFO - Iter [78300/80000] lr: 3.053e-08, eta: 0:17:41, time: 0.597, data_time: 0.005, memory: 60248, decode.loss_ce: 0.1242, decode.acc_seg: 75.4186, aux.loss_ce: 0.0830, aux.acc_seg: 73.4871, loss: 0.2073 +2022-05-05 22:50:28,831 - mmseg - INFO - Iter [78350/80000] lr: 2.963e-08, eta: 0:17:10, time: 0.602, data_time: 0.004, memory: 60248, decode.loss_ce: 0.1214, decode.acc_seg: 75.2457, aux.loss_ce: 0.0789, aux.acc_seg: 73.5573, loss: 0.2003 +2022-05-05 22:50:58,479 - mmseg - INFO - Iter [78400/80000] lr: 2.873e-08, eta: 0:16:39, time: 0.593, data_time: 0.004, memory: 60248, decode.loss_ce: 0.1223, decode.acc_seg: 75.3077, aux.loss_ce: 0.0780, aux.acc_seg: 73.6432, loss: 0.2003 +2022-05-05 22:51:27,914 - mmseg - INFO - Iter [78450/80000] lr: 2.784e-08, eta: 0:16:08, time: 0.588, data_time: 0.005, memory: 60248, decode.loss_ce: 0.1295, decode.acc_seg: 76.9076, aux.loss_ce: 0.0858, aux.acc_seg: 75.0071, loss: 0.2153 +2022-05-05 22:51:57,334 - mmseg - INFO - Iter [78500/80000] lr: 2.694e-08, eta: 0:15:36, time: 0.589, data_time: 0.005, memory: 60248, decode.loss_ce: 0.1210, decode.acc_seg: 76.3136, aux.loss_ce: 0.0782, aux.acc_seg: 74.6500, loss: 0.1993 +2022-05-05 22:52:26,826 - mmseg - INFO - Iter [78550/80000] lr: 2.604e-08, eta: 0:15:05, time: 0.590, data_time: 0.005, memory: 60248, decode.loss_ce: 0.1249, decode.acc_seg: 76.1350, aux.loss_ce: 0.0813, aux.acc_seg: 74.4225, loss: 0.2062 +2022-05-05 22:52:56,327 - mmseg - INFO - Iter [78600/80000] lr: 2.514e-08, eta: 0:14:34, time: 0.590, data_time: 0.005, memory: 60248, decode.loss_ce: 0.1180, decode.acc_seg: 75.7227, aux.loss_ce: 0.0802, aux.acc_seg: 73.9523, loss: 0.1982 +2022-05-05 22:53:25,744 - mmseg - INFO - Iter [78650/80000] lr: 2.425e-08, eta: 0:14:03, time: 0.588, data_time: 0.005, memory: 60248, decode.loss_ce: 0.1244, decode.acc_seg: 76.8945, aux.loss_ce: 0.0824, aux.acc_seg: 75.1305, loss: 0.2068 +2022-05-05 22:53:57,737 - mmseg - INFO - Iter [78700/80000] lr: 2.335e-08, eta: 0:13:31, time: 0.640, data_time: 0.054, memory: 60248, decode.loss_ce: 0.1243, decode.acc_seg: 76.2593, aux.loss_ce: 0.0816, aux.acc_seg: 74.4904, loss: 0.2059 +2022-05-05 22:54:27,388 - mmseg - INFO - Iter [78750/80000] lr: 2.245e-08, eta: 0:13:00, time: 0.592, data_time: 0.005, memory: 60248, decode.loss_ce: 0.1303, decode.acc_seg: 76.5476, aux.loss_ce: 0.0835, aux.acc_seg: 74.7370, loss: 0.2138 +2022-05-05 22:54:57,188 - mmseg - INFO - Iter [78800/80000] lr: 2.155e-08, eta: 0:12:29, time: 0.598, data_time: 0.006, memory: 60248, decode.loss_ce: 0.1234, decode.acc_seg: 77.2254, aux.loss_ce: 0.0805, aux.acc_seg: 75.5380, loss: 0.2039 +2022-05-05 22:55:26,698 - mmseg - INFO - Iter [78850/80000] lr: 2.066e-08, eta: 0:11:58, time: 0.590, data_time: 0.004, memory: 60248, decode.loss_ce: 0.1235, decode.acc_seg: 75.3847, aux.loss_ce: 0.0812, aux.acc_seg: 73.6368, loss: 0.2047 +2022-05-05 22:55:56,324 - mmseg - INFO - Iter [78900/80000] lr: 1.976e-08, eta: 0:11:26, time: 0.592, data_time: 0.004, memory: 60248, decode.loss_ce: 0.1269, decode.acc_seg: 76.1518, aux.loss_ce: 0.0829, aux.acc_seg: 74.3630, loss: 0.2098 +2022-05-05 22:56:25,927 - mmseg - INFO - Iter [78950/80000] lr: 1.886e-08, eta: 0:10:55, time: 0.592, data_time: 0.004, memory: 60248, decode.loss_ce: 0.1127, decode.acc_seg: 76.3255, aux.loss_ce: 0.0767, aux.acc_seg: 74.6342, loss: 0.1894 +2022-05-05 22:56:55,661 - mmseg - INFO - Saving checkpoint at 79000 iterations +2022-05-05 22:57:17,135 - mmseg - INFO - Exp name: upernet_beit_adapter_large_512_80k_cocostuff10k_ss.py +2022-05-05 22:57:17,137 - mmseg - INFO - Iter [79000/80000] lr: 1.797e-08, eta: 0:10:24, time: 1.022, data_time: 0.005, memory: 60248, decode.loss_ce: 0.1223, decode.acc_seg: 76.5040, aux.loss_ce: 0.0813, aux.acc_seg: 74.7826, loss: 0.2036 +2022-05-05 22:57:47,200 - mmseg - INFO - Iter [79050/80000] lr: 1.707e-08, eta: 0:09:53, time: 0.604, data_time: 0.008, memory: 60248, decode.loss_ce: 0.1229, decode.acc_seg: 76.9011, aux.loss_ce: 0.0829, aux.acc_seg: 74.9811, loss: 0.2058 +2022-05-05 22:58:16,956 - mmseg - INFO - Iter [79100/80000] lr: 1.617e-08, eta: 0:09:22, time: 0.595, data_time: 0.005, memory: 60248, decode.loss_ce: 0.1205, decode.acc_seg: 78.3908, aux.loss_ce: 0.0792, aux.acc_seg: 76.5889, loss: 0.1997 +2022-05-05 22:58:46,332 - mmseg - INFO - Iter [79150/80000] lr: 1.527e-08, eta: 0:08:50, time: 0.587, data_time: 0.004, memory: 60248, decode.loss_ce: 0.1140, decode.acc_seg: 75.9388, aux.loss_ce: 0.0780, aux.acc_seg: 74.0596, loss: 0.1920 +2022-05-05 22:59:15,737 - mmseg - INFO - Iter [79200/80000] lr: 1.438e-08, eta: 0:08:19, time: 0.588, data_time: 0.004, memory: 60248, decode.loss_ce: 0.1230, decode.acc_seg: 76.4369, aux.loss_ce: 0.0822, aux.acc_seg: 74.5235, loss: 0.2052 +2022-05-05 22:59:48,021 - mmseg - INFO - Iter [79250/80000] lr: 1.348e-08, eta: 0:07:48, time: 0.646, data_time: 0.054, memory: 60248, decode.loss_ce: 0.1229, decode.acc_seg: 76.4206, aux.loss_ce: 0.0797, aux.acc_seg: 74.6194, loss: 0.2025 +2022-05-05 23:00:17,653 - mmseg - INFO - Iter [79300/80000] lr: 1.258e-08, eta: 0:07:17, time: 0.593, data_time: 0.005, memory: 60248, decode.loss_ce: 0.1212, decode.acc_seg: 77.7638, aux.loss_ce: 0.0811, aux.acc_seg: 75.9652, loss: 0.2023 +2022-05-05 23:00:47,050 - mmseg - INFO - Iter [79350/80000] lr: 1.168e-08, eta: 0:06:45, time: 0.588, data_time: 0.004, memory: 60248, decode.loss_ce: 0.1174, decode.acc_seg: 76.3007, aux.loss_ce: 0.0784, aux.acc_seg: 74.5514, loss: 0.1958 +2022-05-05 23:01:16,494 - mmseg - INFO - Iter [79400/80000] lr: 1.079e-08, eta: 0:06:14, time: 0.589, data_time: 0.005, memory: 60248, decode.loss_ce: 0.1216, decode.acc_seg: 77.3991, aux.loss_ce: 0.0799, aux.acc_seg: 75.6832, loss: 0.2014 +2022-05-05 23:01:46,025 - mmseg - INFO - Iter [79450/80000] lr: 9.889e-09, eta: 0:05:43, time: 0.590, data_time: 0.005, memory: 60248, decode.loss_ce: 0.1205, decode.acc_seg: 75.5754, aux.loss_ce: 0.0811, aux.acc_seg: 73.7424, loss: 0.2016 +2022-05-05 23:02:15,498 - mmseg - INFO - Iter [79500/80000] lr: 8.992e-09, eta: 0:05:12, time: 0.590, data_time: 0.005, memory: 60248, decode.loss_ce: 0.1266, decode.acc_seg: 76.6567, aux.loss_ce: 0.0822, aux.acc_seg: 74.9270, loss: 0.2088 +2022-05-05 23:02:44,998 - mmseg - INFO - Iter [79550/80000] lr: 8.094e-09, eta: 0:04:40, time: 0.590, data_time: 0.005, memory: 60248, decode.loss_ce: 0.1207, decode.acc_seg: 77.2257, aux.loss_ce: 0.0802, aux.acc_seg: 75.4421, loss: 0.2009 +2022-05-05 23:03:14,281 - mmseg - INFO - Iter [79600/80000] lr: 7.197e-09, eta: 0:04:09, time: 0.586, data_time: 0.004, memory: 60248, decode.loss_ce: 0.1223, decode.acc_seg: 75.7744, aux.loss_ce: 0.0818, aux.acc_seg: 73.8956, loss: 0.2041 +2022-05-05 23:03:43,709 - mmseg - INFO - Iter [79650/80000] lr: 6.300e-09, eta: 0:03:38, time: 0.588, data_time: 0.004, memory: 60248, decode.loss_ce: 0.1270, decode.acc_seg: 76.9031, aux.loss_ce: 0.0866, aux.acc_seg: 74.8497, loss: 0.2136 +2022-05-05 23:04:13,502 - mmseg - INFO - Iter [79700/80000] lr: 5.402e-09, eta: 0:03:07, time: 0.596, data_time: 0.004, memory: 60248, decode.loss_ce: 0.1228, decode.acc_seg: 76.3590, aux.loss_ce: 0.0832, aux.acc_seg: 74.3766, loss: 0.2060 +2022-05-05 23:04:42,864 - mmseg - INFO - Iter [79750/80000] lr: 4.505e-09, eta: 0:02:36, time: 0.588, data_time: 0.005, memory: 60248, decode.loss_ce: 0.1279, decode.acc_seg: 76.4065, aux.loss_ce: 0.0823, aux.acc_seg: 74.5732, loss: 0.2102 +2022-05-05 23:05:12,131 - mmseg - INFO - Iter [79800/80000] lr: 3.607e-09, eta: 0:02:04, time: 0.585, data_time: 0.004, memory: 60248, decode.loss_ce: 0.1315, decode.acc_seg: 76.6351, aux.loss_ce: 0.0862, aux.acc_seg: 74.8451, loss: 0.2176 +2022-05-05 23:05:44,016 - mmseg - INFO - Iter [79850/80000] lr: 2.710e-09, eta: 0:01:33, time: 0.638, data_time: 0.053, memory: 60248, decode.loss_ce: 0.1207, decode.acc_seg: 76.5838, aux.loss_ce: 0.0790, aux.acc_seg: 74.7769, loss: 0.1997 +2022-05-05 23:06:13,414 - mmseg - INFO - Iter [79900/80000] lr: 1.813e-09, eta: 0:01:02, time: 0.588, data_time: 0.004, memory: 60248, decode.loss_ce: 0.1280, decode.acc_seg: 76.8260, aux.loss_ce: 0.0858, aux.acc_seg: 74.8854, loss: 0.2137 +2022-05-05 23:06:42,847 - mmseg - INFO - Iter [79950/80000] lr: 9.153e-10, eta: 0:00:31, time: 0.589, data_time: 0.004, memory: 60248, decode.loss_ce: 0.1201, decode.acc_seg: 76.7750, aux.loss_ce: 0.0813, aux.acc_seg: 74.8470, loss: 0.2014 +2022-05-05 23:07:12,231 - mmseg - INFO - Saving checkpoint at 80000 iterations +2022-05-05 23:07:33,738 - mmseg - INFO - Exp name: upernet_beit_adapter_large_512_80k_cocostuff10k_ss.py +2022-05-05 23:07:33,745 - mmseg - INFO - Iter [80000/80000] lr: 1.795e-11, eta: 0:00:00, time: 1.015, data_time: 0.004, memory: 60248, decode.loss_ce: 0.1193, decode.acc_seg: 75.9520, aux.loss_ce: 0.0820, aux.acc_seg: 74.0020, loss: 0.2012 +2022-05-05 23:08:04,198 - mmseg - INFO - per class results: +2022-05-05 23:08:04,206 - mmseg - INFO - ++------------------+-------+-------+ +| Class | IoU | Acc | ++------------------+-------+-------+ +| person | 87.62 | 95.39 | +| bicycle | 75.36 | 93.07 | +| car | 64.43 | 72.27 | +| motorcycle | 87.86 | 96.64 | +| airplane | 88.71 | 96.23 | +| bus | 86.26 | 92.62 | +| train | 74.36 | 97.7 | +| truck | 76.93 | 89.29 | +| boat | 72.23 | 88.69 | +| traffic light | 73.48 | 91.53 | +| fire hydrant | 84.75 | 98.13 | +| stop sign | 90.96 | 98.36 | +| parking meter | 76.55 | 80.13 | +| bench | 53.48 | 69.48 | +| bird | 74.94 | 84.76 | +| cat | 92.42 | 97.19 | +| dog | 91.42 | 97.08 | +| horse | 89.43 | 96.31 | +| sheep | 87.0 | 92.97 | +| cow | 94.71 | 98.82 | +| elephant | 91.68 | 97.71 | +| bear | 87.42 | 95.98 | +| zebra | 90.78 | 96.95 | +| giraffe | 86.11 | 95.89 | +| backpack | 21.65 | 54.42 | +| umbrella | 76.92 | 88.64 | +| handbag | 16.85 | 23.39 | +| tie | 59.48 | 59.48 | +| suitcase | 76.8 | 96.51 | +| frisbee | 93.93 | 96.63 | +| skis | 39.17 | 56.49 | +| snowboard | 63.84 | 78.11 | +| sports ball | 85.87 | 91.4 | +| kite | 68.85 | 90.11 | +| baseball bat | 50.21 | 63.39 | +| baseball glove | 2.53 | 2.57 | +| skateboard | 67.67 | 87.5 | +| surfboard | 89.99 | 94.75 | +| tennis racket | 65.61 | 67.88 | +| bottle | 73.89 | 85.23 | +| wine glass | 83.14 | 92.56 | +| cup | 66.7 | 90.98 | +| fork | 52.8 | 70.12 | +| knife | 76.59 | 87.68 | +| spoon | 47.59 | 63.97 | +| bowl | 56.82 | 69.66 | +| banana | 77.31 | 87.7 | +| apple | 72.54 | 89.48 | +| sandwich | 86.01 | 97.25 | +| orange | 68.93 | 92.1 | +| broccoli | 95.2 | 97.64 | +| carrot | 39.54 | 71.47 | +| hot dog | 51.5 | 96.19 | +| pizza | 94.28 | 96.33 | +| donut | 67.58 | 90.53 | +| cake | 55.94 | 65.12 | +| chair | 59.1 | 76.53 | +| couch | 74.2 | 93.91 | +| potted plant | 37.02 | 47.85 | +| bed | 73.16 | 84.79 | +| dining table | 61.28 | 77.93 | +| toilet | 88.9 | 96.69 | +| tv | 68.99 | 92.18 | +| laptop | 86.69 | 98.06 | +| mouse | 72.02 | 77.99 | +| remote | 67.69 | 91.89 | +| keyboard | 82.99 | 98.61 | +| cell phone | 80.44 | 97.43 | +| microwave | 52.16 | 74.2 | +| oven | 63.61 | 86.39 | +| toaster | 44.32 | 44.41 | +| sink | 70.26 | 78.27 | +| refrigerator | 84.36 | 90.02 | +| book | 79.18 | 89.69 | +| clock | 75.08 | 87.1 | +| vase | 62.46 | 91.0 | +| scissors | 78.67 | 92.41 | +| teddy bear | 84.48 | 95.01 | +| hair drier | 0.0 | 0.0 | +| toothbrush | 16.42 | 30.93 | +| banner | 25.0 | 42.32 | +| blanket | 4.59 | 4.63 | +| branch | 2.49 | 2.49 | +| bridge | 2.56 | 3.35 | +| building-other | 55.04 | 75.21 | +| bush | 27.95 | 36.98 | +| cabinet | 16.43 | 28.68 | +| cage | 0.71 | 2.58 | +| cardboard | 24.56 | 28.85 | +| carpet | 59.1 | 77.04 | +| ceiling-other | 71.12 | 86.47 | +| ceiling-tile | 12.56 | 14.17 | +| cloth | 3.18 | 4.68 | +| clothes | 20.85 | 30.29 | +| clouds | 50.93 | 64.46 | +| counter | 35.73 | 44.27 | +| cupboard | 55.73 | 74.92 | +| curtain | 65.75 | 82.7 | +| desk-stuff | 40.31 | 45.54 | +| dirt | 31.77 | 49.95 | +| door-stuff | 48.96 | 61.24 | +| fence | 44.03 | 74.23 | +| floor-marble | 0.0 | 0.0 | +| floor-other | 44.56 | 58.55 | +| floor-stone | 21.46 | 30.19 | +| floor-tile | 61.21 | 75.32 | +| floor-wood | 71.14 | 86.78 | +| flower | 16.82 | 42.09 | +| fog | 0.0 | 0.0 | +| food-other | 39.27 | 54.81 | +| fruit | 52.58 | 61.56 | +| furniture-other | 14.4 | 20.05 | +| grass | 72.8 | 85.13 | +| gravel | 25.69 | 29.84 | +| ground-other | 7.59 | 14.21 | +| hill | 27.38 | 38.88 | +| house | 24.83 | 37.27 | +| leaves | 13.05 | 18.56 | +| light | 40.81 | 53.73 | +| mat | 20.7 | 28.88 | +| metal | 15.63 | 18.3 | +| mirror-stuff | 44.47 | 59.22 | +| moss | 0.46 | 0.46 | +| mountain | 31.99 | 48.66 | +| mud | 11.81 | 21.86 | +| napkin | 23.18 | 29.72 | +| net | 24.34 | 27.34 | +| paper | 55.94 | 65.82 | +| pavement | 57.87 | 78.46 | +| pillow | 0.0 | 0.0 | +| plant-other | 30.19 | 40.05 | +| plastic | 19.57 | 24.38 | +| platform | 40.45 | 58.18 | +| playingfield | 69.49 | 82.15 | +| railing | 16.07 | 24.67 | +| railroad | 63.23 | 91.23 | +| river | 6.15 | 7.13 | +| road | 70.39 | 80.19 | +| rock | 51.14 | 70.24 | +| roof | 5.77 | 9.94 | +| rug | 53.76 | 76.56 | +| salad | 21.38 | 21.88 | +| sand | 74.69 | 87.18 | +| sea | 76.78 | 90.54 | +| shelf | 25.76 | 39.16 | +| sky-other | 61.32 | 78.14 | +| skyscraper | 6.87 | 9.84 | +| snow | 92.09 | 95.28 | +| solid-other | 0.0 | nan | +| stairs | 33.25 | 50.66 | +| stone | 6.88 | 11.46 | +| straw | 16.35 | 33.11 | +| structural-other | 17.94 | 24.21 | +| table | 20.28 | 29.03 | +| tent | 78.09 | 85.44 | +| textile-other | 18.96 | 21.52 | +| towel | 41.36 | 49.84 | +| tree | 77.5 | 89.45 | +| vegetable | 44.5 | 65.46 | +| wall-brick | 41.39 | 52.24 | +| wall-concrete | 19.14 | 24.47 | +| wall-other | 61.03 | 81.27 | +| wall-panel | 6.01 | 6.66 | +| wall-stone | 30.28 | 36.63 | +| wall-tile | 57.82 | 87.82 | +| wall-wood | 40.5 | 60.45 | +| water-other | 36.77 | 54.77 | +| waterdrops | nan | nan | +| window-blind | 23.81 | 47.0 | +| window-other | 46.98 | 60.61 | +| wood | 14.17 | 28.11 | ++------------------+-------+-------+ +2022-05-05 23:08:04,207 - mmseg - INFO - Summary: +2022-05-05 23:08:04,207 - mmseg - INFO - ++-------+-------+-------+ +| aAcc | mIoU | mAcc | ++-------+-------+-------+ +| 75.77 | 50.74 | 62.78 | ++-------+-------+-------+ +2022-05-05 23:08:04,210 - mmseg - INFO - Exp name: upernet_beit_adapter_large_512_80k_cocostuff10k_ss.py +2022-05-05 23:08:04,210 - mmseg - INFO - Iter(val) [125] aAcc: 0.7577, mIoU: 0.5074, mAcc: 0.6278, IoU.person: 0.8762, IoU.bicycle: 0.7536, IoU.car: 0.6443, IoU.motorcycle: 0.8786, IoU.airplane: 0.8871, IoU.bus: 0.8626, IoU.train: 0.7436, IoU.truck: 0.7693, IoU.boat: 0.7223, IoU.traffic light: 0.7348, IoU.fire hydrant: 0.8475, IoU.stop sign: 0.9096, IoU.parking meter: 0.7655, IoU.bench: 0.5348, IoU.bird: 0.7494, IoU.cat: 0.9242, IoU.dog: 0.9142, IoU.horse: 0.8943, IoU.sheep: 0.8700, IoU.cow: 0.9471, IoU.elephant: 0.9168, IoU.bear: 0.8742, IoU.zebra: 0.9078, IoU.giraffe: 0.8611, IoU.backpack: 0.2165, IoU.umbrella: 0.7692, IoU.handbag: 0.1685, IoU.tie: 0.5948, IoU.suitcase: 0.7680, IoU.frisbee: 0.9393, IoU.skis: 0.3917, IoU.snowboard: 0.6384, IoU.sports ball: 0.8587, IoU.kite: 0.6885, IoU.baseball bat: 0.5021, IoU.baseball glove: 0.0253, IoU.skateboard: 0.6767, IoU.surfboard: 0.8999, IoU.tennis racket: 0.6561, IoU.bottle: 0.7389, IoU.wine glass: 0.8314, IoU.cup: 0.6670, IoU.fork: 0.5280, IoU.knife: 0.7659, IoU.spoon: 0.4759, IoU.bowl: 0.5682, IoU.banana: 0.7731, IoU.apple: 0.7254, IoU.sandwich: 0.8601, IoU.orange: 0.6893, IoU.broccoli: 0.9520, IoU.carrot: 0.3954, IoU.hot dog: 0.5150, IoU.pizza: 0.9428, IoU.donut: 0.6758, IoU.cake: 0.5594, IoU.chair: 0.5910, IoU.couch: 0.7420, IoU.potted plant: 0.3702, IoU.bed: 0.7316, IoU.dining table: 0.6128, IoU.toilet: 0.8890, IoU.tv: 0.6899, IoU.laptop: 0.8669, IoU.mouse: 0.7202, IoU.remote: 0.6769, IoU.keyboard: 0.8299, IoU.cell phone: 0.8044, IoU.microwave: 0.5216, IoU.oven: 0.6361, IoU.toaster: 0.4432, IoU.sink: 0.7026, IoU.refrigerator: 0.8436, IoU.book: 0.7918, IoU.clock: 0.7508, IoU.vase: 0.6246, IoU.scissors: 0.7867, IoU.teddy bear: 0.8448, IoU.hair drier: 0.0000, IoU.toothbrush: 0.1642, IoU.banner: 0.2500, IoU.blanket: 0.0459, IoU.branch: 0.0249, IoU.bridge: 0.0256, IoU.building-other: 0.5504, IoU.bush: 0.2795, IoU.cabinet: 0.1643, IoU.cage: 0.0071, IoU.cardboard: 0.2456, IoU.carpet: 0.5910, IoU.ceiling-other: 0.7112, IoU.ceiling-tile: 0.1256, IoU.cloth: 0.0318, IoU.clothes: 0.2085, IoU.clouds: 0.5093, IoU.counter: 0.3573, IoU.cupboard: 0.5573, IoU.curtain: 0.6575, IoU.desk-stuff: 0.4031, IoU.dirt: 0.3177, IoU.door-stuff: 0.4896, IoU.fence: 0.4403, IoU.floor-marble: 0.0000, IoU.floor-other: 0.4456, IoU.floor-stone: 0.2146, IoU.floor-tile: 0.6121, IoU.floor-wood: 0.7114, IoU.flower: 0.1682, IoU.fog: 0.0000, IoU.food-other: 0.3927, IoU.fruit: 0.5258, IoU.furniture-other: 0.1440, IoU.grass: 0.7280, IoU.gravel: 0.2569, IoU.ground-other: 0.0759, IoU.hill: 0.2738, IoU.house: 0.2483, IoU.leaves: 0.1305, IoU.light: 0.4081, IoU.mat: 0.2070, IoU.metal: 0.1563, IoU.mirror-stuff: 0.4447, IoU.moss: 0.0046, IoU.mountain: 0.3199, IoU.mud: 0.1181, IoU.napkin: 0.2318, IoU.net: 0.2434, IoU.paper: 0.5594, IoU.pavement: 0.5787, IoU.pillow: 0.0000, IoU.plant-other: 0.3019, IoU.plastic: 0.1957, IoU.platform: 0.4045, IoU.playingfield: 0.6949, IoU.railing: 0.1607, IoU.railroad: 0.6323, IoU.river: 0.0615, IoU.road: 0.7039, IoU.rock: 0.5114, IoU.roof: 0.0577, IoU.rug: 0.5376, IoU.salad: 0.2138, IoU.sand: 0.7469, IoU.sea: 0.7678, IoU.shelf: 0.2576, IoU.sky-other: 0.6132, IoU.skyscraper: 0.0687, IoU.snow: 0.9209, IoU.solid-other: 0.0000, IoU.stairs: 0.3325, IoU.stone: 0.0688, IoU.straw: 0.1635, IoU.structural-other: 0.1794, IoU.table: 0.2028, IoU.tent: 0.7809, IoU.textile-other: 0.1896, IoU.towel: 0.4136, IoU.tree: 0.7750, IoU.vegetable: 0.4450, IoU.wall-brick: 0.4139, IoU.wall-concrete: 0.1914, IoU.wall-other: 0.6103, IoU.wall-panel: 0.0601, IoU.wall-stone: 0.3028, IoU.wall-tile: 0.5782, IoU.wall-wood: 0.4050, IoU.water-other: 0.3677, IoU.waterdrops: nan, IoU.window-blind: 0.2381, IoU.window-other: 0.4698, IoU.wood: 0.1417, Acc.person: 0.9539, Acc.bicycle: 0.9307, Acc.car: 0.7227, Acc.motorcycle: 0.9664, Acc.airplane: 0.9623, Acc.bus: 0.9262, Acc.train: 0.9770, Acc.truck: 0.8929, Acc.boat: 0.8869, Acc.traffic light: 0.9153, Acc.fire hydrant: 0.9813, Acc.stop sign: 0.9836, Acc.parking meter: 0.8013, Acc.bench: 0.6948, Acc.bird: 0.8476, Acc.cat: 0.9719, Acc.dog: 0.9708, Acc.horse: 0.9631, Acc.sheep: 0.9297, Acc.cow: 0.9882, Acc.elephant: 0.9771, Acc.bear: 0.9598, Acc.zebra: 0.9695, Acc.giraffe: 0.9589, Acc.backpack: 0.5442, Acc.umbrella: 0.8864, Acc.handbag: 0.2339, Acc.tie: 0.5948, Acc.suitcase: 0.9651, Acc.frisbee: 0.9663, Acc.skis: 0.5649, Acc.snowboard: 0.7811, Acc.sports ball: 0.9140, Acc.kite: 0.9011, Acc.baseball bat: 0.6339, Acc.baseball glove: 0.0257, Acc.skateboard: 0.8750, Acc.surfboard: 0.9475, Acc.tennis racket: 0.6788, Acc.bottle: 0.8523, Acc.wine glass: 0.9256, Acc.cup: 0.9098, Acc.fork: 0.7012, Acc.knife: 0.8768, Acc.spoon: 0.6397, Acc.bowl: 0.6966, Acc.banana: 0.8770, Acc.apple: 0.8948, Acc.sandwich: 0.9725, Acc.orange: 0.9210, Acc.broccoli: 0.9764, Acc.carrot: 0.7147, Acc.hot dog: 0.9619, Acc.pizza: 0.9633, Acc.donut: 0.9053, Acc.cake: 0.6512, Acc.chair: 0.7653, Acc.couch: 0.9391, Acc.potted plant: 0.4785, Acc.bed: 0.8479, Acc.dining table: 0.7793, Acc.toilet: 0.9669, Acc.tv: 0.9218, Acc.laptop: 0.9806, Acc.mouse: 0.7799, Acc.remote: 0.9189, Acc.keyboard: 0.9861, Acc.cell phone: 0.9743, Acc.microwave: 0.7420, Acc.oven: 0.8639, Acc.toaster: 0.4441, Acc.sink: 0.7827, Acc.refrigerator: 0.9002, Acc.book: 0.8969, Acc.clock: 0.8710, Acc.vase: 0.9100, Acc.scissors: 0.9241, Acc.teddy bear: 0.9501, Acc.hair drier: 0.0000, Acc.toothbrush: 0.3093, Acc.banner: 0.4232, Acc.blanket: 0.0463, Acc.branch: 0.0249, Acc.bridge: 0.0335, Acc.building-other: 0.7521, Acc.bush: 0.3698, Acc.cabinet: 0.2868, Acc.cage: 0.0258, Acc.cardboard: 0.2885, Acc.carpet: 0.7704, Acc.ceiling-other: 0.8647, Acc.ceiling-tile: 0.1417, Acc.cloth: 0.0468, Acc.clothes: 0.3029, Acc.clouds: 0.6446, Acc.counter: 0.4427, Acc.cupboard: 0.7492, Acc.curtain: 0.8270, Acc.desk-stuff: 0.4554, Acc.dirt: 0.4995, Acc.door-stuff: 0.6124, Acc.fence: 0.7423, Acc.floor-marble: 0.0000, Acc.floor-other: 0.5855, Acc.floor-stone: 0.3019, Acc.floor-tile: 0.7532, Acc.floor-wood: 0.8678, Acc.flower: 0.4209, Acc.fog: 0.0000, Acc.food-other: 0.5481, Acc.fruit: 0.6156, Acc.furniture-other: 0.2005, Acc.grass: 0.8513, Acc.gravel: 0.2984, Acc.ground-other: 0.1421, Acc.hill: 0.3888, Acc.house: 0.3727, Acc.leaves: 0.1856, Acc.light: 0.5373, Acc.mat: 0.2888, Acc.metal: 0.1830, Acc.mirror-stuff: 0.5922, Acc.moss: 0.0046, Acc.mountain: 0.4866, Acc.mud: 0.2186, Acc.napkin: 0.2972, Acc.net: 0.2734, Acc.paper: 0.6582, Acc.pavement: 0.7846, Acc.pillow: 0.0000, Acc.plant-other: 0.4005, Acc.plastic: 0.2438, Acc.platform: 0.5818, Acc.playingfield: 0.8215, Acc.railing: 0.2467, Acc.railroad: 0.9123, Acc.river: 0.0713, Acc.road: 0.8019, Acc.rock: 0.7024, Acc.roof: 0.0994, Acc.rug: 0.7656, Acc.salad: 0.2188, Acc.sand: 0.8718, Acc.sea: 0.9054, Acc.shelf: 0.3916, Acc.sky-other: 0.7814, Acc.skyscraper: 0.0984, Acc.snow: 0.9528, Acc.solid-other: nan, Acc.stairs: 0.5066, Acc.stone: 0.1146, Acc.straw: 0.3311, Acc.structural-other: 0.2421, Acc.table: 0.2903, Acc.tent: 0.8544, Acc.textile-other: 0.2152, Acc.towel: 0.4984, Acc.tree: 0.8945, Acc.vegetable: 0.6546, Acc.wall-brick: 0.5224, Acc.wall-concrete: 0.2447, Acc.wall-other: 0.8127, Acc.wall-panel: 0.0666, Acc.wall-stone: 0.3663, Acc.wall-tile: 0.8782, Acc.wall-wood: 0.6045, Acc.water-other: 0.5477, Acc.waterdrops: nan, Acc.window-blind: 0.4700, Acc.window-other: 0.6061, Acc.wood: 0.2811