2022-10-03 23:25:34,518 - mmdet - INFO - Environment info: ------------------------------------------------------------ sys.platform: linux Python: 3.7.3 (default, Jan 22 2021, 20:04:44) [GCC 8.3.0] CUDA available: True GPU 0,1,2,3,4,5,6,7: A100-SXM-80GB CUDA_HOME: /usr/local/cuda NVCC: Cuda compilation tools, release 11.3, V11.3.109 GCC: x86_64-linux-gnu-gcc (Debian 8.3.0-6) 8.3.0 PyTorch: 1.10.0 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 v2.2.3 (Git Hash 7336ca9f055cf1bfa13efb658fe15dc9b41f0740) - OpenMP 201511 (a.k.a. OpenMP 4.5) - LAPACK is enabled (usually provided by MKL) - NNPACK is enabled - CPU capability usage: AVX512 - CUDA Runtime 11.3 - NVCC architecture flags: -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 8.2 - Magma 2.5.2 - Build settings: BLAS_INFO=mkl, BUILD_TYPE=Release, CUDA_VERSION=11.3, CUDNN_VERSION=8.2.0, 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 -DEDGE_PROFILER_USE_KINETO -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=1.10.0, 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: 0.11.1+cu113 OpenCV: 4.6.0 MMCV: 1.6.1 MMCV Compiler: GCC 9.3 MMCV CUDA Compiler: 11.3 MMDetection: 2.25.2+87c120c ------------------------------------------------------------ 2022-10-03 23:25:35,633 - mmdet - INFO - Distributed training: True 2022-10-03 23:25:36,764 - mmdet - INFO - Config: model = dict( type='RetinaNet', backbone=dict( type='ResNet', depth=50, num_stages=4, out_indices=(0, 1, 2, 3), frozen_stages=1, norm_cfg=dict(type='SyncBN', requires_grad=True), norm_eval=True, style='pytorch', init_cfg=dict(type='Pretrained', checkpoint='torchvision://resnet50')), neck=dict( type='FPN', in_channels=[256, 512, 1024, 2048], out_channels=256, start_level=1, add_extra_convs='on_input', num_outs=5, norm_cfg=dict(type='SyncBN', requires_grad=True)), bbox_head=dict( type='RetinaHead', num_classes=20, in_channels=256, stacked_convs=4, feat_channels=256, anchor_generator=dict( type='AnchorGenerator', octave_base_scale=4, scales_per_octave=3, ratios=[0.5, 1.0, 2.0], strides=[8, 16, 32, 64, 128]), bbox_coder=dict( type='DeltaXYWHBBoxCoder', target_means=[0.0, 0.0, 0.0, 0.0], target_stds=[1.0, 1.0, 1.0, 1.0]), loss_cls=dict( type='FocalLoss', use_sigmoid=True, gamma=2.0, alpha=0.25, loss_weight=1.0), loss_bbox=dict(type='L1Loss', loss_weight=1.0)), train_cfg=dict( assigner=dict( type='MaxIoUAssigner', pos_iou_thr=0.5, neg_iou_thr=0.4, min_pos_iou=0, ignore_iof_thr=-1), allowed_border=-1, pos_weight=-1, debug=False), test_cfg=dict( nms_pre=1000, min_bbox_size=0, score_thr=0.05, nms=dict(type='nms', iou_threshold=0.5), max_per_img=100)) dataset_type = 'VOCDataset' data_root = 'data/VOCdevkit/' img_norm_cfg = dict( mean=[123.675, 116.28, 103.53], std=[58.395, 57.12, 57.375], to_rgb=True) train_pipeline = [ dict(type='LoadImageFromFile'), dict(type='LoadAnnotations', with_bbox=True), dict( type='Resize', img_scale=[(1333, 480), (1333, 512), (1333, 544), (1333, 576), (1333, 608), (1333, 640), (1333, 672), (1333, 704), (1333, 736), (1333, 768), (1333, 800)], multiscale_mode='value', keep_ratio=True), dict(type='RandomFlip', flip_ratio=0.5), dict( type='Normalize', mean=[123.675, 116.28, 103.53], std=[58.395, 57.12, 57.375], to_rgb=True), dict(type='Pad', size_divisor=32), dict(type='DefaultFormatBundle'), dict(type='Collect', keys=['img', 'gt_bboxes', 'gt_labels']) ] test_pipeline = [ dict(type='LoadImageFromFile'), dict( type='MultiScaleFlipAug', img_scale=(1333, 800), flip=False, transforms=[ dict(type='Resize', keep_ratio=True), 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='Pad', size_divisor=32), dict(type='ImageToTensor', keys=['img']), dict(type='Collect', keys=['img']) ]) ] data = dict( samples_per_gpu=2, workers_per_gpu=2, train=dict( type='VOCDataset', ann_file=[ 'data/VOCdevkit/VOC2007/ImageSets/Main/trainval.txt', 'data/VOCdevkit/VOC2012/ImageSets/Main/trainval.txt' ], img_prefix=['data/VOCdevkit/VOC2007/', 'data/VOCdevkit/VOC2012/'], pipeline=[ dict(type='LoadImageFromFile'), dict(type='LoadAnnotations', with_bbox=True), dict( type='Resize', img_scale=[(1333, 480), (1333, 512), (1333, 544), (1333, 576), (1333, 608), (1333, 640), (1333, 672), (1333, 704), (1333, 736), (1333, 768), (1333, 800)], multiscale_mode='value', keep_ratio=True), dict(type='RandomFlip', flip_ratio=0.5), dict( type='Normalize', mean=[123.675, 116.28, 103.53], std=[58.395, 57.12, 57.375], to_rgb=True), dict(type='Pad', size_divisor=32), dict(type='DefaultFormatBundle'), dict(type='Collect', keys=['img', 'gt_bboxes', 'gt_labels']) ]), val=dict( type='VOCDataset', ann_file='data/VOCdevkit/VOC2007/ImageSets/Main/test.txt', img_prefix='data/VOCdevkit/VOC2007/', pipeline=[ dict(type='LoadImageFromFile'), dict( type='MultiScaleFlipAug', img_scale=(1333, 800), flip=False, transforms=[ dict(type='Resize', keep_ratio=True), 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='Pad', size_divisor=32), dict(type='ImageToTensor', keys=['img']), dict(type='Collect', keys=['img']) ]) ]), test=dict( type='VOCDataset', ann_file='data/VOCdevkit/VOC2007/ImageSets/Main/test.txt', img_prefix='data/VOCdevkit/VOC2007/', pipeline=[ dict(type='LoadImageFromFile'), dict( type='MultiScaleFlipAug', img_scale=(1333, 800), flip=False, transforms=[ dict(type='Resize', keep_ratio=True), 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='Pad', size_divisor=32), dict(type='ImageToTensor', keys=['img']), dict(type='Collect', keys=['img']) ]) ])) evaluation = dict(interval=12000, metric='mAP', save_best='auto') optimizer = dict(type='SGD', lr=0.015, momentum=0.9, weight_decay=5e-05) optimizer_config = dict(grad_clip=None) lr_config = dict( policy='step', warmup='linear', warmup_iters=500, warmup_ratio=0.001, step=[9000, 11000], by_epoch=False) runner = dict(type='IterBasedRunner', max_iters=12000) checkpoint_config = dict(interval=12000) log_config = dict(interval=50, hooks=[dict(type='TextLoggerHook')]) custom_hooks = [ dict(type='NumClassCheckHook'), dict( type='MMDetWandbHook', init_kwargs=dict(project='I2B', group='finetune'), interval=50, num_eval_images=0, log_checkpoint=False) ] dist_params = dict(backend='nccl') log_level = 'INFO' load_from = 'pretrain/selfsup_retinanet_mstrain-soft-teacher_sampler-2048_temp0.5/final_model.pth' resume_from = None workflow = [('train', 1)] opencv_num_threads = 0 mp_start_method = 'fork' auto_scale_lr = dict(enable=False, base_batch_size=16) custom_imports = None norm_cfg = dict(type='SyncBN', requires_grad=True) work_dir = 'work_dirs/finetune_retinanet_12k_voc0712_lr1.5e-2_wd5e-5' auto_resume = False gpu_ids = range(0, 8) 2022-10-03 23:25:36,764 - mmdet - INFO - Set random seed to 42, deterministic: False 2022-10-03 23:25:37,080 - mmdet - INFO - initialize ResNet with init_cfg {'type': 'Pretrained', 'checkpoint': 'torchvision://resnet50'} 2022-10-03 23:25:46,723 - mmdet - INFO - initialize FPN with init_cfg {'type': 'Xavier', 'layer': 'Conv2d', 'distribution': 'uniform'} 2022-10-03 23:25:46,781 - mmdet - INFO - initialize RetinaHead with init_cfg {'type': 'Normal', 'layer': 'Conv2d', 'std': 0.01, 'override': {'type': 'Normal', 'name': 'retina_cls', 'std': 0.01, 'bias_prob': 0.01}} Name of parameter - Initialization information backbone.conv1.weight - torch.Size([64, 3, 7, 7]): PretrainedInit: load from torchvision://resnet50 backbone.bn1.weight - torch.Size([64]): PretrainedInit: load from torchvision://resnet50 backbone.bn1.bias - torch.Size([64]): PretrainedInit: load from torchvision://resnet50 backbone.layer1.0.conv1.weight - torch.Size([64, 64, 1, 1]): PretrainedInit: load from torchvision://resnet50 backbone.layer1.0.bn1.weight - torch.Size([64]): PretrainedInit: load from torchvision://resnet50 backbone.layer1.0.bn1.bias - torch.Size([64]): PretrainedInit: load from torchvision://resnet50 backbone.layer1.0.conv2.weight - torch.Size([64, 64, 3, 3]): PretrainedInit: load from torchvision://resnet50 backbone.layer1.0.bn2.weight - torch.Size([64]): PretrainedInit: load from torchvision://resnet50 backbone.layer1.0.bn2.bias - torch.Size([64]): PretrainedInit: load from torchvision://resnet50 backbone.layer1.0.conv3.weight - torch.Size([256, 64, 1, 1]): PretrainedInit: load from torchvision://resnet50 backbone.layer1.0.bn3.weight - torch.Size([256]): PretrainedInit: load from torchvision://resnet50 backbone.layer1.0.bn3.bias - torch.Size([256]): PretrainedInit: load from torchvision://resnet50 backbone.layer1.0.downsample.0.weight - torch.Size([256, 64, 1, 1]): PretrainedInit: load from torchvision://resnet50 backbone.layer1.0.downsample.1.weight - torch.Size([256]): PretrainedInit: load from torchvision://resnet50 backbone.layer1.0.downsample.1.bias - torch.Size([256]): PretrainedInit: load from torchvision://resnet50 backbone.layer1.1.conv1.weight - torch.Size([64, 256, 1, 1]): PretrainedInit: load from torchvision://resnet50 backbone.layer1.1.bn1.weight - torch.Size([64]): PretrainedInit: load from torchvision://resnet50 backbone.layer1.1.bn1.bias - torch.Size([64]): PretrainedInit: load from torchvision://resnet50 backbone.layer1.1.conv2.weight - torch.Size([64, 64, 3, 3]): PretrainedInit: load from torchvision://resnet50 backbone.layer1.1.bn2.weight - torch.Size([64]): PretrainedInit: load from torchvision://resnet50 backbone.layer1.1.bn2.bias - torch.Size([64]): PretrainedInit: load from torchvision://resnet50 backbone.layer1.1.conv3.weight - torch.Size([256, 64, 1, 1]): PretrainedInit: load from torchvision://resnet50 backbone.layer1.1.bn3.weight - torch.Size([256]): PretrainedInit: load from torchvision://resnet50 backbone.layer1.1.bn3.bias - torch.Size([256]): PretrainedInit: load from torchvision://resnet50 backbone.layer1.2.conv1.weight - torch.Size([64, 256, 1, 1]): PretrainedInit: load from torchvision://resnet50 backbone.layer1.2.bn1.weight - torch.Size([64]): PretrainedInit: load from torchvision://resnet50 backbone.layer1.2.bn1.bias - torch.Size([64]): PretrainedInit: load from torchvision://resnet50 backbone.layer1.2.conv2.weight - torch.Size([64, 64, 3, 3]): PretrainedInit: load from torchvision://resnet50 backbone.layer1.2.bn2.weight - torch.Size([64]): PretrainedInit: load from torchvision://resnet50 backbone.layer1.2.bn2.bias - torch.Size([64]): PretrainedInit: load from torchvision://resnet50 backbone.layer1.2.conv3.weight - torch.Size([256, 64, 1, 1]): PretrainedInit: load from torchvision://resnet50 backbone.layer1.2.bn3.weight - torch.Size([256]): PretrainedInit: load from torchvision://resnet50 backbone.layer1.2.bn3.bias - torch.Size([256]): PretrainedInit: load from torchvision://resnet50 backbone.layer2.0.conv1.weight - torch.Size([128, 256, 1, 1]): PretrainedInit: load from torchvision://resnet50 backbone.layer2.0.bn1.weight - torch.Size([128]): PretrainedInit: load from torchvision://resnet50 backbone.layer2.0.bn1.bias - torch.Size([128]): PretrainedInit: load from torchvision://resnet50 backbone.layer2.0.conv2.weight - torch.Size([128, 128, 3, 3]): PretrainedInit: load from torchvision://resnet50 backbone.layer2.0.bn2.weight - torch.Size([128]): PretrainedInit: load from torchvision://resnet50 backbone.layer2.0.bn2.bias - torch.Size([128]): PretrainedInit: load from torchvision://resnet50 backbone.layer2.0.conv3.weight - torch.Size([512, 128, 1, 1]): PretrainedInit: load from torchvision://resnet50 backbone.layer2.0.bn3.weight - torch.Size([512]): PretrainedInit: load from torchvision://resnet50 backbone.layer2.0.bn3.bias - torch.Size([512]): PretrainedInit: load from torchvision://resnet50 backbone.layer2.0.downsample.0.weight - torch.Size([512, 256, 1, 1]): PretrainedInit: load from torchvision://resnet50 backbone.layer2.0.downsample.1.weight - torch.Size([512]): PretrainedInit: load from torchvision://resnet50 backbone.layer2.0.downsample.1.bias - torch.Size([512]): PretrainedInit: load from torchvision://resnet50 backbone.layer2.1.conv1.weight - torch.Size([128, 512, 1, 1]): PretrainedInit: load from torchvision://resnet50 backbone.layer2.1.bn1.weight - torch.Size([128]): PretrainedInit: load from torchvision://resnet50 backbone.layer2.1.bn1.bias - torch.Size([128]): PretrainedInit: load from torchvision://resnet50 backbone.layer2.1.conv2.weight - torch.Size([128, 128, 3, 3]): PretrainedInit: load from torchvision://resnet50 backbone.layer2.1.bn2.weight - torch.Size([128]): PretrainedInit: load from torchvision://resnet50 backbone.layer2.1.bn2.bias - torch.Size([128]): PretrainedInit: load from torchvision://resnet50 backbone.layer2.1.conv3.weight - torch.Size([512, 128, 1, 1]): PretrainedInit: load from torchvision://resnet50 backbone.layer2.1.bn3.weight - torch.Size([512]): PretrainedInit: load from torchvision://resnet50 backbone.layer2.1.bn3.bias - torch.Size([512]): PretrainedInit: load from torchvision://resnet50 backbone.layer2.2.conv1.weight - torch.Size([128, 512, 1, 1]): PretrainedInit: load from torchvision://resnet50 backbone.layer2.2.bn1.weight - torch.Size([128]): PretrainedInit: load from torchvision://resnet50 backbone.layer2.2.bn1.bias - torch.Size([128]): PretrainedInit: load from torchvision://resnet50 backbone.layer2.2.conv2.weight - torch.Size([128, 128, 3, 3]): PretrainedInit: load from torchvision://resnet50 backbone.layer2.2.bn2.weight - torch.Size([128]): PretrainedInit: load from torchvision://resnet50 backbone.layer2.2.bn2.bias - torch.Size([128]): PretrainedInit: load from torchvision://resnet50 backbone.layer2.2.conv3.weight - torch.Size([512, 128, 1, 1]): PretrainedInit: load from torchvision://resnet50 backbone.layer2.2.bn3.weight - torch.Size([512]): PretrainedInit: load from torchvision://resnet50 backbone.layer2.2.bn3.bias - torch.Size([512]): PretrainedInit: load from torchvision://resnet50 backbone.layer2.3.conv1.weight - torch.Size([128, 512, 1, 1]): PretrainedInit: load from torchvision://resnet50 backbone.layer2.3.bn1.weight - torch.Size([128]): PretrainedInit: load from torchvision://resnet50 backbone.layer2.3.bn1.bias - torch.Size([128]): PretrainedInit: load from torchvision://resnet50 backbone.layer2.3.conv2.weight - torch.Size([128, 128, 3, 3]): PretrainedInit: load from torchvision://resnet50 backbone.layer2.3.bn2.weight - torch.Size([128]): PretrainedInit: load from torchvision://resnet50 backbone.layer2.3.bn2.bias - torch.Size([128]): PretrainedInit: load from torchvision://resnet50 backbone.layer2.3.conv3.weight - torch.Size([512, 128, 1, 1]): PretrainedInit: load from torchvision://resnet50 backbone.layer2.3.bn3.weight - torch.Size([512]): PretrainedInit: load from torchvision://resnet50 backbone.layer2.3.bn3.bias - torch.Size([512]): PretrainedInit: load from torchvision://resnet50 backbone.layer3.0.conv1.weight - torch.Size([256, 512, 1, 1]): PretrainedInit: load from torchvision://resnet50 backbone.layer3.0.bn1.weight - torch.Size([256]): PretrainedInit: load from torchvision://resnet50 backbone.layer3.0.bn1.bias - torch.Size([256]): PretrainedInit: load from torchvision://resnet50 backbone.layer3.0.conv2.weight - torch.Size([256, 256, 3, 3]): PretrainedInit: load from torchvision://resnet50 backbone.layer3.0.bn2.weight - torch.Size([256]): PretrainedInit: load from torchvision://resnet50 backbone.layer3.0.bn2.bias - torch.Size([256]): PretrainedInit: load from torchvision://resnet50 backbone.layer3.0.conv3.weight - torch.Size([1024, 256, 1, 1]): PretrainedInit: load from torchvision://resnet50 backbone.layer3.0.bn3.weight - torch.Size([1024]): PretrainedInit: load from torchvision://resnet50 backbone.layer3.0.bn3.bias - torch.Size([1024]): PretrainedInit: load from torchvision://resnet50 backbone.layer3.0.downsample.0.weight - torch.Size([1024, 512, 1, 1]): PretrainedInit: load from torchvision://resnet50 backbone.layer3.0.downsample.1.weight - torch.Size([1024]): PretrainedInit: load from torchvision://resnet50 backbone.layer3.0.downsample.1.bias - torch.Size([1024]): PretrainedInit: load from torchvision://resnet50 backbone.layer3.1.conv1.weight - torch.Size([256, 1024, 1, 1]): PretrainedInit: load from torchvision://resnet50 backbone.layer3.1.bn1.weight - torch.Size([256]): PretrainedInit: load from torchvision://resnet50 backbone.layer3.1.bn1.bias - torch.Size([256]): PretrainedInit: load from torchvision://resnet50 backbone.layer3.1.conv2.weight - torch.Size([256, 256, 3, 3]): PretrainedInit: load from torchvision://resnet50 backbone.layer3.1.bn2.weight - torch.Size([256]): PretrainedInit: load from torchvision://resnet50 backbone.layer3.1.bn2.bias - torch.Size([256]): PretrainedInit: load from torchvision://resnet50 backbone.layer3.1.conv3.weight - torch.Size([1024, 256, 1, 1]): PretrainedInit: load from torchvision://resnet50 backbone.layer3.1.bn3.weight - torch.Size([1024]): PretrainedInit: load from torchvision://resnet50 backbone.layer3.1.bn3.bias - torch.Size([1024]): PretrainedInit: load from torchvision://resnet50 backbone.layer3.2.conv1.weight - torch.Size([256, 1024, 1, 1]): PretrainedInit: load from torchvision://resnet50 backbone.layer3.2.bn1.weight - torch.Size([256]): PretrainedInit: load from torchvision://resnet50 backbone.layer3.2.bn1.bias - torch.Size([256]): PretrainedInit: load from torchvision://resnet50 backbone.layer3.2.conv2.weight - torch.Size([256, 256, 3, 3]): PretrainedInit: load from torchvision://resnet50 backbone.layer3.2.bn2.weight - torch.Size([256]): PretrainedInit: load from torchvision://resnet50 backbone.layer3.2.bn2.bias - torch.Size([256]): PretrainedInit: load from torchvision://resnet50 backbone.layer3.2.conv3.weight - torch.Size([1024, 256, 1, 1]): PretrainedInit: load from torchvision://resnet50 backbone.layer3.2.bn3.weight - torch.Size([1024]): PretrainedInit: load from torchvision://resnet50 backbone.layer3.2.bn3.bias - torch.Size([1024]): PretrainedInit: load from torchvision://resnet50 backbone.layer3.3.conv1.weight - torch.Size([256, 1024, 1, 1]): PretrainedInit: load from torchvision://resnet50 backbone.layer3.3.bn1.weight - torch.Size([256]): PretrainedInit: load from torchvision://resnet50 backbone.layer3.3.bn1.bias - torch.Size([256]): PretrainedInit: load from torchvision://resnet50 backbone.layer3.3.conv2.weight - torch.Size([256, 256, 3, 3]): PretrainedInit: load from torchvision://resnet50 backbone.layer3.3.bn2.weight - torch.Size([256]): PretrainedInit: load from torchvision://resnet50 backbone.layer3.3.bn2.bias - torch.Size([256]): PretrainedInit: load from torchvision://resnet50 backbone.layer3.3.conv3.weight - torch.Size([1024, 256, 1, 1]): PretrainedInit: load from torchvision://resnet50 backbone.layer3.3.bn3.weight - torch.Size([1024]): PretrainedInit: load from torchvision://resnet50 backbone.layer3.3.bn3.bias - torch.Size([1024]): PretrainedInit: load from torchvision://resnet50 backbone.layer3.4.conv1.weight - torch.Size([256, 1024, 1, 1]): PretrainedInit: load from torchvision://resnet50 backbone.layer3.4.bn1.weight - torch.Size([256]): PretrainedInit: load from torchvision://resnet50 backbone.layer3.4.bn1.bias - torch.Size([256]): PretrainedInit: load from torchvision://resnet50 backbone.layer3.4.conv2.weight - torch.Size([256, 256, 3, 3]): PretrainedInit: load from torchvision://resnet50 backbone.layer3.4.bn2.weight - torch.Size([256]): PretrainedInit: load from torchvision://resnet50 backbone.layer3.4.bn2.bias - torch.Size([256]): PretrainedInit: load from torchvision://resnet50 backbone.layer3.4.conv3.weight - torch.Size([1024, 256, 1, 1]): PretrainedInit: load from torchvision://resnet50 backbone.layer3.4.bn3.weight - torch.Size([1024]): PretrainedInit: load from torchvision://resnet50 backbone.layer3.4.bn3.bias - torch.Size([1024]): PretrainedInit: load from torchvision://resnet50 backbone.layer3.5.conv1.weight - torch.Size([256, 1024, 1, 1]): PretrainedInit: load from torchvision://resnet50 backbone.layer3.5.bn1.weight - torch.Size([256]): PretrainedInit: load from torchvision://resnet50 backbone.layer3.5.bn1.bias - torch.Size([256]): PretrainedInit: load from torchvision://resnet50 backbone.layer3.5.conv2.weight - torch.Size([256, 256, 3, 3]): PretrainedInit: load from torchvision://resnet50 backbone.layer3.5.bn2.weight - torch.Size([256]): PretrainedInit: load from torchvision://resnet50 backbone.layer3.5.bn2.bias - torch.Size([256]): PretrainedInit: load from torchvision://resnet50 backbone.layer3.5.conv3.weight - torch.Size([1024, 256, 1, 1]): PretrainedInit: load from torchvision://resnet50 backbone.layer3.5.bn3.weight - torch.Size([1024]): PretrainedInit: load from torchvision://resnet50 backbone.layer3.5.bn3.bias - torch.Size([1024]): PretrainedInit: load from torchvision://resnet50 backbone.layer4.0.conv1.weight - torch.Size([512, 1024, 1, 1]): PretrainedInit: load from torchvision://resnet50 backbone.layer4.0.bn1.weight - torch.Size([512]): PretrainedInit: load from torchvision://resnet50 backbone.layer4.0.bn1.bias - torch.Size([512]): PretrainedInit: load from torchvision://resnet50 backbone.layer4.0.conv2.weight - torch.Size([512, 512, 3, 3]): PretrainedInit: load from torchvision://resnet50 backbone.layer4.0.bn2.weight - torch.Size([512]): PretrainedInit: load from torchvision://resnet50 backbone.layer4.0.bn2.bias - torch.Size([512]): PretrainedInit: load from torchvision://resnet50 backbone.layer4.0.conv3.weight - torch.Size([2048, 512, 1, 1]): PretrainedInit: load from torchvision://resnet50 backbone.layer4.0.bn3.weight - torch.Size([2048]): PretrainedInit: load from torchvision://resnet50 backbone.layer4.0.bn3.bias - torch.Size([2048]): PretrainedInit: load from torchvision://resnet50 backbone.layer4.0.downsample.0.weight - torch.Size([2048, 1024, 1, 1]): PretrainedInit: load from torchvision://resnet50 backbone.layer4.0.downsample.1.weight - torch.Size([2048]): PretrainedInit: load from torchvision://resnet50 backbone.layer4.0.downsample.1.bias - torch.Size([2048]): PretrainedInit: load from torchvision://resnet50 backbone.layer4.1.conv1.weight - torch.Size([512, 2048, 1, 1]): PretrainedInit: load from torchvision://resnet50 backbone.layer4.1.bn1.weight - torch.Size([512]): PretrainedInit: load from torchvision://resnet50 backbone.layer4.1.bn1.bias - torch.Size([512]): PretrainedInit: load from torchvision://resnet50 backbone.layer4.1.conv2.weight - torch.Size([512, 512, 3, 3]): PretrainedInit: load from torchvision://resnet50 backbone.layer4.1.bn2.weight - torch.Size([512]): PretrainedInit: load from torchvision://resnet50 backbone.layer4.1.bn2.bias - torch.Size([512]): PretrainedInit: load from torchvision://resnet50 backbone.layer4.1.conv3.weight - torch.Size([2048, 512, 1, 1]): PretrainedInit: load from torchvision://resnet50 backbone.layer4.1.bn3.weight - torch.Size([2048]): PretrainedInit: load from torchvision://resnet50 backbone.layer4.1.bn3.bias - torch.Size([2048]): PretrainedInit: load from torchvision://resnet50 backbone.layer4.2.conv1.weight - torch.Size([512, 2048, 1, 1]): PretrainedInit: load from torchvision://resnet50 backbone.layer4.2.bn1.weight - torch.Size([512]): PretrainedInit: load from torchvision://resnet50 backbone.layer4.2.bn1.bias - torch.Size([512]): PretrainedInit: load from torchvision://resnet50 backbone.layer4.2.conv2.weight - torch.Size([512, 512, 3, 3]): PretrainedInit: load from torchvision://resnet50 backbone.layer4.2.bn2.weight - torch.Size([512]): PretrainedInit: load from torchvision://resnet50 backbone.layer4.2.bn2.bias - torch.Size([512]): PretrainedInit: load from torchvision://resnet50 backbone.layer4.2.conv3.weight - torch.Size([2048, 512, 1, 1]): PretrainedInit: load from torchvision://resnet50 backbone.layer4.2.bn3.weight - torch.Size([2048]): PretrainedInit: load from torchvision://resnet50 backbone.layer4.2.bn3.bias - torch.Size([2048]): PretrainedInit: load from torchvision://resnet50 neck.lateral_convs.0.conv.weight - torch.Size([256, 512, 1, 1]): XavierInit: gain=1, distribution=uniform, bias=0 neck.lateral_convs.0.bn.weight - torch.Size([256]): The value is the same before and after calling `init_weights` of RetinaNet neck.lateral_convs.0.bn.bias - torch.Size([256]): The value is the same before and after calling `init_weights` of RetinaNet neck.lateral_convs.1.conv.weight - torch.Size([256, 1024, 1, 1]): XavierInit: gain=1, distribution=uniform, bias=0 neck.lateral_convs.1.bn.weight - torch.Size([256]): The value is the same before and after calling `init_weights` of RetinaNet neck.lateral_convs.1.bn.bias - torch.Size([256]): The value is the same before and after calling `init_weights` of RetinaNet neck.lateral_convs.2.conv.weight - torch.Size([256, 2048, 1, 1]): XavierInit: gain=1, distribution=uniform, bias=0 neck.lateral_convs.2.bn.weight - torch.Size([256]): The value is the same before and after calling `init_weights` of RetinaNet neck.lateral_convs.2.bn.bias - torch.Size([256]): The value is the same before and after calling `init_weights` of RetinaNet neck.fpn_convs.0.conv.weight - torch.Size([256, 256, 3, 3]): XavierInit: gain=1, distribution=uniform, bias=0 neck.fpn_convs.0.bn.weight - torch.Size([256]): The value is the same before and after calling `init_weights` of RetinaNet neck.fpn_convs.0.bn.bias - torch.Size([256]): The value is the same before and after calling `init_weights` of RetinaNet neck.fpn_convs.1.conv.weight - torch.Size([256, 256, 3, 3]): XavierInit: gain=1, distribution=uniform, bias=0 neck.fpn_convs.1.bn.weight - torch.Size([256]): The value is the same before and after calling `init_weights` of RetinaNet neck.fpn_convs.1.bn.bias - torch.Size([256]): The value is the same before and after calling `init_weights` of RetinaNet neck.fpn_convs.2.conv.weight - torch.Size([256, 256, 3, 3]): XavierInit: gain=1, distribution=uniform, bias=0 neck.fpn_convs.2.bn.weight - torch.Size([256]): The value is the same before and after calling `init_weights` of RetinaNet neck.fpn_convs.2.bn.bias - torch.Size([256]): The value is the same before and after calling `init_weights` of RetinaNet neck.fpn_convs.3.conv.weight - torch.Size([256, 2048, 3, 3]): XavierInit: gain=1, distribution=uniform, bias=0 neck.fpn_convs.3.bn.weight - torch.Size([256]): The value is the same before and after calling `init_weights` of RetinaNet neck.fpn_convs.3.bn.bias - torch.Size([256]): The value is the same before and after calling `init_weights` of RetinaNet neck.fpn_convs.4.conv.weight - torch.Size([256, 256, 3, 3]): XavierInit: gain=1, distribution=uniform, bias=0 neck.fpn_convs.4.bn.weight - torch.Size([256]): The value is the same before and after calling `init_weights` of RetinaNet neck.fpn_convs.4.bn.bias - torch.Size([256]): The value is the same before and after calling `init_weights` of RetinaNet bbox_head.cls_convs.0.conv.weight - torch.Size([256, 256, 3, 3]): NormalInit: mean=0, std=0.01, bias=0 bbox_head.cls_convs.0.conv.bias - torch.Size([256]): The value is the same before and after calling `init_weights` of RetinaNet bbox_head.cls_convs.1.conv.weight - torch.Size([256, 256, 3, 3]): NormalInit: mean=0, std=0.01, bias=0 bbox_head.cls_convs.1.conv.bias - torch.Size([256]): The value is the same before and after calling `init_weights` of RetinaNet bbox_head.cls_convs.2.conv.weight - torch.Size([256, 256, 3, 3]): NormalInit: mean=0, std=0.01, bias=0 bbox_head.cls_convs.2.conv.bias - torch.Size([256]): The value is the same before and after calling `init_weights` of RetinaNet bbox_head.cls_convs.3.conv.weight - torch.Size([256, 256, 3, 3]): NormalInit: mean=0, std=0.01, bias=0 bbox_head.cls_convs.3.conv.bias - torch.Size([256]): The value is the same before and after calling `init_weights` of RetinaNet bbox_head.reg_convs.0.conv.weight - torch.Size([256, 256, 3, 3]): NormalInit: mean=0, std=0.01, bias=0 bbox_head.reg_convs.0.conv.bias - torch.Size([256]): The value is the same before and after calling `init_weights` of RetinaNet bbox_head.reg_convs.1.conv.weight - torch.Size([256, 256, 3, 3]): NormalInit: mean=0, std=0.01, bias=0 bbox_head.reg_convs.1.conv.bias - torch.Size([256]): The value is the same before and after calling `init_weights` of RetinaNet bbox_head.reg_convs.2.conv.weight - torch.Size([256, 256, 3, 3]): NormalInit: mean=0, std=0.01, bias=0 bbox_head.reg_convs.2.conv.bias - torch.Size([256]): The value is the same before and after calling `init_weights` of RetinaNet bbox_head.reg_convs.3.conv.weight - torch.Size([256, 256, 3, 3]): NormalInit: mean=0, std=0.01, bias=0 bbox_head.reg_convs.3.conv.bias - torch.Size([256]): The value is the same before and after calling `init_weights` of RetinaNet bbox_head.retina_cls.weight - torch.Size([180, 256, 3, 3]): NormalInit: mean=0, std=0.01, bias=-4.59511985013459 bbox_head.retina_cls.bias - torch.Size([180]): NormalInit: mean=0, std=0.01, bias=-4.59511985013459 bbox_head.retina_reg.weight - torch.Size([36, 256, 3, 3]): NormalInit: mean=0, std=0.01, bias=0 bbox_head.retina_reg.bias - torch.Size([36]): NormalInit: mean=0, std=0.01, bias=0 2022-10-03 23:25:48,644 - mmdet - INFO - Automatic scaling of learning rate (LR) has been disabled. 2022-10-03 23:25:49,424 - mmdet - INFO - load checkpoint from local path: pretrain/selfsup_retinanet_mstrain-soft-teacher_sampler-2048_temp0.5/final_model.pth 2022-10-03 23:25:49,532 - mmdet - WARNING - The model and loaded state dict do not match exactly unexpected key in source state_dict: neck.lateral_convs.0.conv.bias, neck.lateral_convs.1.conv.bias, neck.lateral_convs.2.conv.bias, neck.fpn_convs.0.conv.bias, neck.fpn_convs.1.conv.bias, neck.fpn_convs.2.conv.bias, neck.fpn_convs.3.conv.bias, neck.fpn_convs.4.conv.bias missing keys in source state_dict: neck.lateral_convs.0.bn.weight, neck.lateral_convs.0.bn.bias, neck.lateral_convs.0.bn.running_mean, neck.lateral_convs.0.bn.running_var, neck.lateral_convs.1.bn.weight, neck.lateral_convs.1.bn.bias, neck.lateral_convs.1.bn.running_mean, neck.lateral_convs.1.bn.running_var, neck.lateral_convs.2.bn.weight, neck.lateral_convs.2.bn.bias, neck.lateral_convs.2.bn.running_mean, neck.lateral_convs.2.bn.running_var, neck.fpn_convs.0.bn.weight, neck.fpn_convs.0.bn.bias, neck.fpn_convs.0.bn.running_mean, neck.fpn_convs.0.bn.running_var, neck.fpn_convs.1.bn.weight, neck.fpn_convs.1.bn.bias, neck.fpn_convs.1.bn.running_mean, neck.fpn_convs.1.bn.running_var, neck.fpn_convs.2.bn.weight, neck.fpn_convs.2.bn.bias, neck.fpn_convs.2.bn.running_mean, neck.fpn_convs.2.bn.running_var, neck.fpn_convs.3.bn.weight, neck.fpn_convs.3.bn.bias, neck.fpn_convs.3.bn.running_mean, neck.fpn_convs.3.bn.running_var, neck.fpn_convs.4.bn.weight, neck.fpn_convs.4.bn.bias, neck.fpn_convs.4.bn.running_mean, neck.fpn_convs.4.bn.running_var, bbox_head.retina_cls.weight, bbox_head.retina_cls.bias, bbox_head.retina_reg.weight, bbox_head.retina_reg.bias 2022-10-03 23:25:49,538 - mmdet - INFO - Start running, host: tiger@n136-144-086, work_dir: /home/tiger/code/mmdet/work_dirs/finetune_retinanet_12k_voc0712_lr1.5e-2_wd5e-5 2022-10-03 23:25:49,538 - mmdet - INFO - Hooks will be executed in the following order: before_run: (VERY_HIGH ) StepLrUpdaterHook (NORMAL ) CheckpointHook (NORMAL ) MMDetWandbHook (LOW ) DistEvalHook (VERY_LOW ) TextLoggerHook -------------------- before_train_epoch: (VERY_HIGH ) StepLrUpdaterHook (NORMAL ) NumClassCheckHook (NORMAL ) MMDetWandbHook (LOW ) IterTimerHook (LOW ) DistEvalHook (VERY_LOW ) TextLoggerHook -------------------- before_train_iter: (VERY_HIGH ) StepLrUpdaterHook (LOW ) IterTimerHook (LOW ) DistEvalHook -------------------- after_train_iter: (ABOVE_NORMAL) OptimizerHook (NORMAL ) CheckpointHook (NORMAL ) MMDetWandbHook (LOW ) IterTimerHook (LOW ) DistEvalHook (VERY_LOW ) TextLoggerHook -------------------- after_train_epoch: (NORMAL ) CheckpointHook (NORMAL ) MMDetWandbHook (LOW ) DistEvalHook (VERY_LOW ) TextLoggerHook -------------------- before_val_epoch: (NORMAL ) NumClassCheckHook (NORMAL ) MMDetWandbHook (LOW ) IterTimerHook (VERY_LOW ) TextLoggerHook -------------------- before_val_iter: (LOW ) IterTimerHook -------------------- after_val_iter: (LOW ) IterTimerHook -------------------- after_val_epoch: (NORMAL ) MMDetWandbHook (VERY_LOW ) TextLoggerHook -------------------- after_run: (NORMAL ) MMDetWandbHook (VERY_LOW ) TextLoggerHook -------------------- 2022-10-03 23:25:49,539 - mmdet - INFO - workflow: [('train', 1)], max: 12000 iters 2022-10-03 23:25:49,539 - mmdet - INFO - Checkpoints will be saved to /home/tiger/code/mmdet/work_dirs/finetune_retinanet_12k_voc0712_lr1.5e-2_wd5e-5 by HardDiskBackend. 2022-10-03 23:25:55,378 - mmdet - INFO - Iter [50/12000] lr: 1.484e-03, eta: 0:17:55, time: 0.090, data_time: 0.006, memory: 3221, loss_cls: 1.1629, loss_bbox: 0.6614, loss: 1.8243 2022-10-03 23:25:59,656 - mmdet - INFO - Iter [100/12000] lr: 2.982e-03, eta: 0:17:24, time: 0.086, data_time: 0.006, memory: 3222, loss_cls: 1.1584, loss_bbox: 0.5555, loss: 1.7139 2022-10-03 23:26:05,649 - mmdet - INFO - Iter [150/12000] lr: 4.481e-03, eta: 0:19:26, time: 0.120, data_time: 0.005, memory: 3223, loss_cls: 1.0891, loss_bbox: 0.4517, loss: 1.5408 2022-10-03 23:26:09,824 - mmdet - INFO - Iter [200/12000] lr: 5.979e-03, eta: 0:18:37, time: 0.083, data_time: 0.005, memory: 3223, loss_cls: 0.8258, loss_bbox: 0.4111, loss: 1.2369 2022-10-03 23:26:14,107 - mmdet - INFO - Iter [250/12000] lr: 7.478e-03, eta: 0:18:11, time: 0.086, data_time: 0.006, memory: 3223, loss_cls: 0.7845, loss_bbox: 0.4073, loss: 1.1919 2022-10-03 23:26:18,252 - mmdet - INFO - Iter [300/12000] lr: 8.976e-03, eta: 0:17:47, time: 0.083, data_time: 0.005, memory: 3223, loss_cls: 0.7312, loss_bbox: 0.3949, loss: 1.1262 2022-10-03 23:26:22,505 - mmdet - INFO - Iter [350/12000] lr: 1.047e-02, eta: 0:17:32, time: 0.085, data_time: 0.006, memory: 3223, loss_cls: 0.6597, loss_bbox: 0.3889, loss: 1.0485 2022-10-03 23:26:26,620 - mmdet - INFO - Iter [400/12000] lr: 1.197e-02, eta: 0:17:16, time: 0.082, data_time: 0.006, memory: 3223, loss_cls: 0.6312, loss_bbox: 0.3784, loss: 1.0096 2022-10-03 23:26:30,838 - mmdet - INFO - Iter [450/12000] lr: 1.347e-02, eta: 0:17:05, time: 0.084, data_time: 0.005, memory: 3223, loss_cls: 0.8423, loss_bbox: 0.4101, loss: 1.2524 2022-10-03 23:26:34,914 - mmdet - INFO - Iter [500/12000] lr: 1.497e-02, eta: 0:16:52, time: 0.081, data_time: 0.006, memory: 3223, loss_cls: 0.9053, loss_bbox: 0.4874, loss: 1.3928 2022-10-03 23:26:39,238 - mmdet - INFO - Iter [550/12000] lr: 1.500e-02, eta: 0:16:46, time: 0.087, data_time: 0.006, memory: 3223, loss_cls: 0.7680, loss_bbox: 0.4204, loss: 1.1885 2022-10-03 23:26:43,449 - mmdet - INFO - Iter [600/12000] lr: 1.500e-02, eta: 0:16:38, time: 0.084, data_time: 0.006, memory: 3223, loss_cls: 0.7605, loss_bbox: 0.4015, loss: 1.1619 2022-10-03 23:26:47,714 - mmdet - INFO - Iter [650/12000] lr: 1.500e-02, eta: 0:16:32, time: 0.085, data_time: 0.006, memory: 3223, loss_cls: 0.8102, loss_bbox: 0.3966, loss: 1.2068 2022-10-03 23:26:51,904 - mmdet - INFO - Iter [700/12000] lr: 1.500e-02, eta: 0:16:25, time: 0.084, data_time: 0.006, memory: 3224, loss_cls: 0.6460, loss_bbox: 0.3687, loss: 1.0146 2022-10-03 23:26:56,191 - mmdet - INFO - Iter [750/12000] lr: 1.500e-02, eta: 0:16:19, time: 0.086, data_time: 0.006, memory: 3224, loss_cls: 0.6535, loss_bbox: 0.3552, loss: 1.0088 2022-10-03 23:27:00,473 - mmdet - INFO - Iter [800/12000] lr: 1.500e-02, eta: 0:16:14, time: 0.086, data_time: 0.006, memory: 3224, loss_cls: 0.5858, loss_bbox: 0.3599, loss: 0.9457 2022-10-03 23:27:04,500 - mmdet - INFO - Iter [850/12000] lr: 1.500e-02, eta: 0:16:05, time: 0.081, data_time: 0.006, memory: 3224, loss_cls: 0.5724, loss_bbox: 0.3407, loss: 0.9132 2022-10-03 23:27:08,607 - mmdet - INFO - Iter [900/12000] lr: 1.500e-02, eta: 0:15:58, time: 0.082, data_time: 0.006, memory: 3224, loss_cls: 0.5498, loss_bbox: 0.3449, loss: 0.8947 2022-10-03 23:27:12,689 - mmdet - INFO - Iter [950/12000] lr: 1.500e-02, eta: 0:15:51, time: 0.082, data_time: 0.006, memory: 3224, loss_cls: 0.5324, loss_bbox: 0.3411, loss: 0.8735 2022-10-03 23:27:16,695 - mmdet - INFO - Exp name: retinanet_mstrain_12k_voc0712.py 2022-10-03 23:27:16,696 - mmdet - INFO - Iter [1000/12000] lr: 1.500e-02, eta: 0:15:43, time: 0.080, data_time: 0.005, memory: 3224, loss_cls: 0.5129, loss_bbox: 0.3193, loss: 0.8322 2022-10-03 23:27:20,708 - mmdet - INFO - Iter [1050/12000] lr: 1.500e-02, eta: 0:15:36, time: 0.080, data_time: 0.006, memory: 3224, loss_cls: 0.5172, loss_bbox: 0.3283, loss: 0.8456 2022-10-03 23:27:24,758 - mmdet - INFO - Iter [1100/12000] lr: 1.500e-02, eta: 0:15:30, time: 0.081, data_time: 0.006, memory: 3224, loss_cls: 0.4909, loss_bbox: 0.3207, loss: 0.8116 2022-10-03 23:27:29,067 - mmdet - INFO - Iter [1150/12000] lr: 1.500e-02, eta: 0:15:26, time: 0.086, data_time: 0.006, memory: 3224, loss_cls: 0.5034, loss_bbox: 0.3272, loss: 0.8305 2022-10-03 23:27:33,084 - mmdet - INFO - Iter [1200/12000] lr: 1.500e-02, eta: 0:15:19, time: 0.080, data_time: 0.006, memory: 3224, loss_cls: 0.4889, loss_bbox: 0.3240, loss: 0.8129 2022-10-03 23:27:38,387 - mmdet - INFO - Iter [1250/12000] lr: 1.500e-02, eta: 0:15:24, time: 0.106, data_time: 0.006, memory: 3224, loss_cls: 0.4536, loss_bbox: 0.3185, loss: 0.7721 2022-10-03 23:27:42,429 - mmdet - INFO - Iter [1300/12000] lr: 1.500e-02, eta: 0:15:18, time: 0.081, data_time: 0.005, memory: 3224, loss_cls: 0.4639, loss_bbox: 0.3065, loss: 0.7703 2022-10-03 23:27:46,548 - mmdet - INFO - Iter [1350/12000] lr: 1.500e-02, eta: 0:15:12, time: 0.082, data_time: 0.006, memory: 3224, loss_cls: 0.4371, loss_bbox: 0.3044, loss: 0.7415 2022-10-03 23:27:50,692 - mmdet - INFO - Iter [1400/12000] lr: 1.500e-02, eta: 0:15:07, time: 0.083, data_time: 0.006, memory: 3224, loss_cls: 0.4519, loss_bbox: 0.3134, loss: 0.7653 2022-10-03 23:27:54,677 - mmdet - INFO - Iter [1450/12000] lr: 1.500e-02, eta: 0:15:00, time: 0.080, data_time: 0.006, memory: 3224, loss_cls: 0.4309, loss_bbox: 0.3055, loss: 0.7364 2022-10-03 23:27:58,762 - mmdet - INFO - Iter [1500/12000] lr: 1.500e-02, eta: 0:14:55, time: 0.082, data_time: 0.006, memory: 3224, loss_cls: 0.4384, loss_bbox: 0.3167, loss: 0.7551 2022-10-03 23:28:02,790 - mmdet - INFO - Iter [1550/12000] lr: 1.500e-02, eta: 0:14:49, time: 0.081, data_time: 0.005, memory: 3224, loss_cls: 0.4355, loss_bbox: 0.3069, loss: 0.7424 2022-10-03 23:28:06,777 - mmdet - INFO - Iter [1600/12000] lr: 1.500e-02, eta: 0:14:43, time: 0.080, data_time: 0.006, memory: 3224, loss_cls: 0.4055, loss_bbox: 0.3089, loss: 0.7144 2022-10-03 23:28:10,767 - mmdet - INFO - Iter [1650/12000] lr: 1.500e-02, eta: 0:14:37, time: 0.080, data_time: 0.006, memory: 3224, loss_cls: 0.4069, loss_bbox: 0.3050, loss: 0.7119 2022-10-03 23:28:14,828 - mmdet - INFO - Iter [1700/12000] lr: 1.500e-02, eta: 0:14:32, time: 0.081, data_time: 0.006, memory: 3224, loss_cls: 0.4004, loss_bbox: 0.3055, loss: 0.7058 2022-10-03 23:28:19,091 - mmdet - INFO - Iter [1750/12000] lr: 1.500e-02, eta: 0:14:28, time: 0.085, data_time: 0.006, memory: 3224, loss_cls: 0.4183, loss_bbox: 0.3042, loss: 0.7225 2022-10-03 23:28:23,263 - mmdet - INFO - Iter [1800/12000] lr: 1.500e-02, eta: 0:14:23, time: 0.083, data_time: 0.006, memory: 3224, loss_cls: 0.4023, loss_bbox: 0.3023, loss: 0.7046 2022-10-03 23:28:27,267 - mmdet - INFO - Iter [1850/12000] lr: 1.500e-02, eta: 0:14:17, time: 0.080, data_time: 0.006, memory: 3224, loss_cls: 0.3761, loss_bbox: 0.2956, loss: 0.6717 2022-10-03 23:28:31,555 - mmdet - INFO - Iter [1900/12000] lr: 1.500e-02, eta: 0:14:14, time: 0.086, data_time: 0.006, memory: 3224, loss_cls: 0.4005, loss_bbox: 0.3044, loss: 0.7049 2022-10-03 23:28:35,749 - mmdet - INFO - Iter [1950/12000] lr: 1.500e-02, eta: 0:14:09, time: 0.084, data_time: 0.006, memory: 3224, loss_cls: 0.3999, loss_bbox: 0.2954, loss: 0.6952 2022-10-03 23:28:39,943 - mmdet - INFO - Exp name: retinanet_mstrain_12k_voc0712.py 2022-10-03 23:28:39,944 - mmdet - INFO - Iter [2000/12000] lr: 1.500e-02, eta: 0:14:05, time: 0.084, data_time: 0.006, memory: 3224, loss_cls: 0.3785, loss_bbox: 0.2902, loss: 0.6687 2022-10-03 23:28:43,964 - mmdet - INFO - Iter [2050/12000] lr: 1.500e-02, eta: 0:14:00, time: 0.080, data_time: 0.006, memory: 3224, loss_cls: 0.3586, loss_bbox: 0.2902, loss: 0.6489 2022-10-03 23:28:48,052 - mmdet - INFO - Iter [2100/12000] lr: 1.500e-02, eta: 0:13:55, time: 0.082, data_time: 0.006, memory: 3224, loss_cls: 0.3824, loss_bbox: 0.2926, loss: 0.6750 2022-10-03 23:28:52,112 - mmdet - INFO - Iter [2150/12000] lr: 1.500e-02, eta: 0:13:50, time: 0.081, data_time: 0.006, memory: 3224, loss_cls: 0.3551, loss_bbox: 0.2795, loss: 0.6346 2022-10-03 23:28:56,312 - mmdet - INFO - Iter [2200/12000] lr: 1.500e-02, eta: 0:13:45, time: 0.084, data_time: 0.006, memory: 3224, loss_cls: 0.3408, loss_bbox: 0.2830, loss: 0.6238 2022-10-03 23:29:00,350 - mmdet - INFO - Iter [2250/12000] lr: 1.500e-02, eta: 0:13:40, time: 0.081, data_time: 0.006, memory: 3224, loss_cls: 0.3448, loss_bbox: 0.2823, loss: 0.6270 2022-10-03 23:29:04,412 - mmdet - INFO - Iter [2300/12000] lr: 1.500e-02, eta: 0:13:36, time: 0.081, data_time: 0.006, memory: 3224, loss_cls: 0.3532, loss_bbox: 0.2838, loss: 0.6370 2022-10-03 23:29:08,485 - mmdet - INFO - Iter [2350/12000] lr: 1.500e-02, eta: 0:13:31, time: 0.081, data_time: 0.006, memory: 3224, loss_cls: 0.3550, loss_bbox: 0.2873, loss: 0.6422 2022-10-03 23:29:12,494 - mmdet - INFO - Iter [2400/12000] lr: 1.500e-02, eta: 0:13:26, time: 0.080, data_time: 0.006, memory: 3224, loss_cls: 0.3385, loss_bbox: 0.2863, loss: 0.6248 2022-10-03 23:29:16,498 - mmdet - INFO - Iter [2450/12000] lr: 1.500e-02, eta: 0:13:21, time: 0.080, data_time: 0.005, memory: 3224, loss_cls: 0.3352, loss_bbox: 0.2791, loss: 0.6143 2022-10-03 23:29:20,492 - mmdet - INFO - Iter [2500/12000] lr: 1.500e-02, eta: 0:13:16, time: 0.080, data_time: 0.006, memory: 3224, loss_cls: 0.3293, loss_bbox: 0.2816, loss: 0.6109 2022-10-03 23:29:24,513 - mmdet - INFO - Iter [2550/12000] lr: 1.500e-02, eta: 0:13:11, time: 0.080, data_time: 0.006, memory: 3224, loss_cls: 0.3459, loss_bbox: 0.2878, loss: 0.6337 2022-10-03 23:29:28,596 - mmdet - INFO - Iter [2600/12000] lr: 1.500e-02, eta: 0:13:07, time: 0.082, data_time: 0.006, memory: 3224, loss_cls: 0.3378, loss_bbox: 0.2843, loss: 0.6221 2022-10-03 23:29:32,760 - mmdet - INFO - Iter [2650/12000] lr: 1.500e-02, eta: 0:13:02, time: 0.083, data_time: 0.006, memory: 3224, loss_cls: 0.3347, loss_bbox: 0.2786, loss: 0.6133 2022-10-03 23:29:36,728 - mmdet - INFO - Iter [2700/12000] lr: 1.500e-02, eta: 0:12:57, time: 0.079, data_time: 0.006, memory: 3224, loss_cls: 0.3163, loss_bbox: 0.2768, loss: 0.5931 2022-10-03 23:29:40,777 - mmdet - INFO - Iter [2750/12000] lr: 1.500e-02, eta: 0:12:53, time: 0.081, data_time: 0.006, memory: 3224, loss_cls: 0.3499, loss_bbox: 0.2751, loss: 0.6250 2022-10-03 23:29:44,893 - mmdet - INFO - Iter [2800/12000] lr: 1.500e-02, eta: 0:12:48, time: 0.082, data_time: 0.005, memory: 3224, loss_cls: 0.3302, loss_bbox: 0.2774, loss: 0.6076 2022-10-03 23:29:48,991 - mmdet - INFO - Iter [2850/12000] lr: 1.500e-02, eta: 0:12:44, time: 0.082, data_time: 0.006, memory: 3224, loss_cls: 0.3143, loss_bbox: 0.2723, loss: 0.5866 2022-10-03 23:29:53,020 - mmdet - INFO - Iter [2900/12000] lr: 1.500e-02, eta: 0:12:39, time: 0.081, data_time: 0.006, memory: 3224, loss_cls: 0.3332, loss_bbox: 0.2821, loss: 0.6153 2022-10-03 23:29:57,164 - mmdet - INFO - Iter [2950/12000] lr: 1.500e-02, eta: 0:12:35, time: 0.083, data_time: 0.006, memory: 3224, loss_cls: 0.3081, loss_bbox: 0.2870, loss: 0.5952 2022-10-03 23:30:01,178 - mmdet - INFO - Exp name: retinanet_mstrain_12k_voc0712.py 2022-10-03 23:30:01,178 - mmdet - INFO - Iter [3000/12000] lr: 1.500e-02, eta: 0:12:30, time: 0.080, data_time: 0.006, memory: 3224, loss_cls: 0.3119, loss_bbox: 0.2731, loss: 0.5851 2022-10-03 23:30:05,167 - mmdet - INFO - Iter [3050/12000] lr: 1.500e-02, eta: 0:12:26, time: 0.080, data_time: 0.006, memory: 3224, loss_cls: 0.3114, loss_bbox: 0.2781, loss: 0.5895 2022-10-03 23:30:09,289 - mmdet - INFO - Iter [3100/12000] lr: 1.500e-02, eta: 0:12:21, time: 0.082, data_time: 0.005, memory: 3224, loss_cls: 0.2978, loss_bbox: 0.2683, loss: 0.5661 2022-10-03 23:30:13,342 - mmdet - INFO - Iter [3150/12000] lr: 1.500e-02, eta: 0:12:17, time: 0.081, data_time: 0.006, memory: 3224, loss_cls: 0.2990, loss_bbox: 0.2785, loss: 0.5775 2022-10-03 23:30:17,344 - mmdet - INFO - Iter [3200/12000] lr: 1.500e-02, eta: 0:12:12, time: 0.080, data_time: 0.006, memory: 3224, loss_cls: 0.3079, loss_bbox: 0.2673, loss: 0.5753 2022-10-03 23:30:21,436 - mmdet - INFO - Iter [3250/12000] lr: 1.500e-02, eta: 0:12:08, time: 0.082, data_time: 0.006, memory: 3224, loss_cls: 0.3240, loss_bbox: 0.2747, loss: 0.5987 2022-10-03 23:30:25,542 - mmdet - INFO - Iter [3300/12000] lr: 1.500e-02, eta: 0:12:04, time: 0.082, data_time: 0.006, memory: 3224, loss_cls: 0.3110, loss_bbox: 0.2722, loss: 0.5833 2022-10-03 23:30:29,587 - mmdet - INFO - Iter [3350/12000] lr: 1.500e-02, eta: 0:11:59, time: 0.081, data_time: 0.006, memory: 3224, loss_cls: 0.2929, loss_bbox: 0.2691, loss: 0.5621 2022-10-03 23:30:33,639 - mmdet - INFO - Iter [3400/12000] lr: 1.500e-02, eta: 0:11:55, time: 0.081, data_time: 0.006, memory: 3224, loss_cls: 0.2892, loss_bbox: 0.2625, loss: 0.5517 2022-10-03 23:30:37,892 - mmdet - INFO - Iter [3450/12000] lr: 1.500e-02, eta: 0:11:51, time: 0.085, data_time: 0.006, memory: 3224, loss_cls: 0.2942, loss_bbox: 0.2680, loss: 0.5622 2022-10-03 23:30:41,912 - mmdet - INFO - Iter [3500/12000] lr: 1.500e-02, eta: 0:11:46, time: 0.080, data_time: 0.006, memory: 3224, loss_cls: 0.2985, loss_bbox: 0.2610, loss: 0.5595 2022-10-03 23:30:45,927 - mmdet - INFO - Iter [3550/12000] lr: 1.500e-02, eta: 0:11:42, time: 0.080, data_time: 0.006, memory: 3224, loss_cls: 0.2857, loss_bbox: 0.2597, loss: 0.5454 2022-10-03 23:30:49,914 - mmdet - INFO - Iter [3600/12000] lr: 1.500e-02, eta: 0:11:37, time: 0.080, data_time: 0.006, memory: 3224, loss_cls: 0.2872, loss_bbox: 0.2613, loss: 0.5485 2022-10-03 23:30:53,850 - mmdet - INFO - Iter [3650/12000] lr: 1.500e-02, eta: 0:11:33, time: 0.079, data_time: 0.006, memory: 3224, loss_cls: 0.2985, loss_bbox: 0.2699, loss: 0.5684 2022-10-03 23:30:57,902 - mmdet - INFO - Iter [3700/12000] lr: 1.500e-02, eta: 0:11:28, time: 0.081, data_time: 0.006, memory: 3224, loss_cls: 0.2794, loss_bbox: 0.2603, loss: 0.5397 2022-10-03 23:31:01,903 - mmdet - INFO - Iter [3750/12000] lr: 1.500e-02, eta: 0:11:24, time: 0.080, data_time: 0.006, memory: 3224, loss_cls: 0.2825, loss_bbox: 0.2614, loss: 0.5439 2022-10-03 23:31:05,932 - mmdet - INFO - Iter [3800/12000] lr: 1.500e-02, eta: 0:11:19, time: 0.081, data_time: 0.006, memory: 3224, loss_cls: 0.2832, loss_bbox: 0.2694, loss: 0.5527 2022-10-03 23:31:09,947 - mmdet - INFO - Iter [3850/12000] lr: 1.500e-02, eta: 0:11:15, time: 0.080, data_time: 0.006, memory: 3224, loss_cls: 0.2898, loss_bbox: 0.2653, loss: 0.5550 2022-10-03 23:31:13,985 - mmdet - INFO - Iter [3900/12000] lr: 1.500e-02, eta: 0:11:11, time: 0.081, data_time: 0.006, memory: 3224, loss_cls: 0.2617, loss_bbox: 0.2559, loss: 0.5176 2022-10-03 23:31:17,999 - mmdet - INFO - Iter [3950/12000] lr: 1.500e-02, eta: 0:11:06, time: 0.080, data_time: 0.006, memory: 3224, loss_cls: 0.2774, loss_bbox: 0.2668, loss: 0.5442 2022-10-03 23:31:21,989 - mmdet - INFO - Exp name: retinanet_mstrain_12k_voc0712.py 2022-10-03 23:31:21,990 - mmdet - INFO - Iter [4000/12000] lr: 1.500e-02, eta: 0:11:02, time: 0.080, data_time: 0.006, memory: 3224, loss_cls: 0.2797, loss_bbox: 0.2677, loss: 0.5474 2022-10-03 23:31:25,993 - mmdet - INFO - Iter [4050/12000] lr: 1.500e-02, eta: 0:10:57, time: 0.080, data_time: 0.006, memory: 3224, loss_cls: 0.2798, loss_bbox: 0.2619, loss: 0.5417 2022-10-03 23:31:30,069 - mmdet - INFO - Iter [4100/12000] lr: 1.500e-02, eta: 0:10:53, time: 0.082, data_time: 0.006, memory: 3224, loss_cls: 0.2771, loss_bbox: 0.2648, loss: 0.5419 2022-10-03 23:31:34,132 - mmdet - INFO - Iter [4150/12000] lr: 1.500e-02, eta: 0:10:49, time: 0.081, data_time: 0.006, memory: 3224, loss_cls: 0.2628, loss_bbox: 0.2520, loss: 0.5149 2022-10-03 23:31:38,088 - mmdet - INFO - Iter [4200/12000] lr: 1.500e-02, eta: 0:10:44, time: 0.079, data_time: 0.006, memory: 3224, loss_cls: 0.2628, loss_bbox: 0.2463, loss: 0.5091 2022-10-03 23:31:42,091 - mmdet - INFO - Iter [4250/12000] lr: 1.500e-02, eta: 0:10:40, time: 0.080, data_time: 0.006, memory: 3224, loss_cls: 0.2621, loss_bbox: 0.2472, loss: 0.5094 2022-10-03 23:31:46,112 - mmdet - INFO - Iter [4300/12000] lr: 1.500e-02, eta: 0:10:36, time: 0.080, data_time: 0.006, memory: 3224, loss_cls: 0.2675, loss_bbox: 0.2574, loss: 0.5249 2022-10-03 23:31:50,251 - mmdet - INFO - Iter [4350/12000] lr: 1.500e-02, eta: 0:10:31, time: 0.083, data_time: 0.006, memory: 3224, loss_cls: 0.2620, loss_bbox: 0.2527, loss: 0.5147 2022-10-03 23:31:54,474 - mmdet - INFO - Iter [4400/12000] lr: 1.500e-02, eta: 0:10:27, time: 0.084, data_time: 0.006, memory: 3224, loss_cls: 0.2705, loss_bbox: 0.2546, loss: 0.5251 2022-10-03 23:31:58,523 - mmdet - INFO - Iter [4450/12000] lr: 1.500e-02, eta: 0:10:23, time: 0.081, data_time: 0.006, memory: 3224, loss_cls: 0.2602, loss_bbox: 0.2542, loss: 0.5143 2022-10-03 23:32:02,530 - mmdet - INFO - Iter [4500/12000] lr: 1.500e-02, eta: 0:10:19, time: 0.080, data_time: 0.006, memory: 3224, loss_cls: 0.2608, loss_bbox: 0.2560, loss: 0.5168 2022-10-03 23:32:06,487 - mmdet - INFO - Iter [4550/12000] lr: 1.500e-02, eta: 0:10:14, time: 0.079, data_time: 0.005, memory: 3224, loss_cls: 0.2590, loss_bbox: 0.2553, loss: 0.5143 2022-10-03 23:32:10,530 - mmdet - INFO - Iter [4600/12000] lr: 1.500e-02, eta: 0:10:10, time: 0.081, data_time: 0.006, memory: 3224, loss_cls: 0.2641, loss_bbox: 0.2479, loss: 0.5120 2022-10-03 23:32:14,604 - mmdet - INFO - Iter [4650/12000] lr: 1.500e-02, eta: 0:10:06, time: 0.081, data_time: 0.006, memory: 3224, loss_cls: 0.2534, loss_bbox: 0.2519, loss: 0.5053 2022-10-03 23:32:18,657 - mmdet - INFO - Iter [4700/12000] lr: 1.500e-02, eta: 0:10:02, time: 0.081, data_time: 0.006, memory: 3224, loss_cls: 0.2575, loss_bbox: 0.2584, loss: 0.5159 2022-10-03 23:32:22,641 - mmdet - INFO - Iter [4750/12000] lr: 1.500e-02, eta: 0:09:57, time: 0.080, data_time: 0.006, memory: 3224, loss_cls: 0.2542, loss_bbox: 0.2506, loss: 0.5048 2022-10-03 23:32:26,629 - mmdet - INFO - Iter [4800/12000] lr: 1.500e-02, eta: 0:09:53, time: 0.080, data_time: 0.006, memory: 3224, loss_cls: 0.2532, loss_bbox: 0.2537, loss: 0.5069 2022-10-03 23:32:30,627 - mmdet - INFO - Iter [4850/12000] lr: 1.500e-02, eta: 0:09:49, time: 0.080, data_time: 0.006, memory: 3224, loss_cls: 0.2557, loss_bbox: 0.2487, loss: 0.5044 2022-10-03 23:32:34,633 - mmdet - INFO - Iter [4900/12000] lr: 1.500e-02, eta: 0:09:44, time: 0.080, data_time: 0.006, memory: 3224, loss_cls: 0.2509, loss_bbox: 0.2476, loss: 0.4985 2022-10-03 23:32:38,691 - mmdet - INFO - Iter [4950/12000] lr: 1.500e-02, eta: 0:09:40, time: 0.081, data_time: 0.006, memory: 3224, loss_cls: 0.2586, loss_bbox: 0.2498, loss: 0.5084 2022-10-03 23:32:42,703 - mmdet - INFO - Exp name: retinanet_mstrain_12k_voc0712.py 2022-10-03 23:32:42,703 - mmdet - INFO - Iter [5000/12000] lr: 1.500e-02, eta: 0:09:36, time: 0.080, data_time: 0.006, memory: 3224, loss_cls: 0.2594, loss_bbox: 0.2504, loss: 0.5098 2022-10-03 23:32:46,796 - mmdet - INFO - Iter [5050/12000] lr: 1.500e-02, eta: 0:09:32, time: 0.082, data_time: 0.006, memory: 3224, loss_cls: 0.2681, loss_bbox: 0.2601, loss: 0.5282 2022-10-03 23:32:51,033 - mmdet - INFO - Iter [5100/12000] lr: 1.500e-02, eta: 0:09:28, time: 0.085, data_time: 0.006, memory: 3224, loss_cls: 0.2681, loss_bbox: 0.2526, loss: 0.5208 2022-10-03 23:32:55,077 - mmdet - INFO - Iter [5150/12000] lr: 1.500e-02, eta: 0:09:24, time: 0.081, data_time: 0.006, memory: 3224, loss_cls: 0.2772, loss_bbox: 0.2604, loss: 0.5376 2022-10-03 23:32:59,205 - mmdet - INFO - Iter [5200/12000] lr: 1.500e-02, eta: 0:09:20, time: 0.083, data_time: 0.006, memory: 3224, loss_cls: 0.2518, loss_bbox: 0.2492, loss: 0.5010 2022-10-03 23:33:03,230 - mmdet - INFO - Iter [5250/12000] lr: 1.500e-02, eta: 0:09:15, time: 0.080, data_time: 0.006, memory: 3224, loss_cls: 0.2322, loss_bbox: 0.2438, loss: 0.4760 2022-10-03 23:33:07,247 - mmdet - INFO - Iter [5300/12000] lr: 1.500e-02, eta: 0:09:11, time: 0.080, data_time: 0.005, memory: 3224, loss_cls: 0.2459, loss_bbox: 0.2391, loss: 0.4850 2022-10-03 23:33:11,416 - mmdet - INFO - Iter [5350/12000] lr: 1.500e-02, eta: 0:09:07, time: 0.083, data_time: 0.006, memory: 3224, loss_cls: 0.2367, loss_bbox: 0.2383, loss: 0.4750 2022-10-03 23:33:15,470 - mmdet - INFO - Iter [5400/12000] lr: 1.500e-02, eta: 0:09:03, time: 0.081, data_time: 0.006, memory: 3224, loss_cls: 0.2256, loss_bbox: 0.2401, loss: 0.4656 2022-10-03 23:33:19,550 - mmdet - INFO - Iter [5450/12000] lr: 1.500e-02, eta: 0:08:59, time: 0.082, data_time: 0.006, memory: 3224, loss_cls: 0.2442, loss_bbox: 0.2445, loss: 0.4888 2022-10-03 23:33:23,503 - mmdet - INFO - Iter [5500/12000] lr: 1.500e-02, eta: 0:08:54, time: 0.079, data_time: 0.006, memory: 3224, loss_cls: 0.2401, loss_bbox: 0.2421, loss: 0.4822 2022-10-03 23:33:27,517 - mmdet - INFO - Iter [5550/12000] lr: 1.500e-02, eta: 0:08:50, time: 0.080, data_time: 0.006, memory: 3224, loss_cls: 0.2480, loss_bbox: 0.2451, loss: 0.4932 2022-10-03 23:33:31,526 - mmdet - INFO - Iter [5600/12000] lr: 1.500e-02, eta: 0:08:46, time: 0.080, data_time: 0.006, memory: 3224, loss_cls: 0.2328, loss_bbox: 0.2398, loss: 0.4726 2022-10-03 23:33:35,585 - mmdet - INFO - Iter [5650/12000] lr: 1.500e-02, eta: 0:08:42, time: 0.081, data_time: 0.006, memory: 3224, loss_cls: 0.2306, loss_bbox: 0.2366, loss: 0.4672 2022-10-03 23:33:39,590 - mmdet - INFO - Iter [5700/12000] lr: 1.500e-02, eta: 0:08:38, time: 0.080, data_time: 0.006, memory: 3224, loss_cls: 0.2448, loss_bbox: 0.2429, loss: 0.4877 2022-10-03 23:33:43,583 - mmdet - INFO - Iter [5750/12000] lr: 1.500e-02, eta: 0:08:33, time: 0.080, data_time: 0.006, memory: 3224, loss_cls: 0.2457, loss_bbox: 0.2471, loss: 0.4928 2022-10-03 23:33:47,547 - mmdet - INFO - Iter [5800/12000] lr: 1.500e-02, eta: 0:08:29, time: 0.079, data_time: 0.006, memory: 3224, loss_cls: 0.2367, loss_bbox: 0.2458, loss: 0.4825 2022-10-03 23:33:51,620 - mmdet - INFO - Iter [5850/12000] lr: 1.500e-02, eta: 0:08:25, time: 0.081, data_time: 0.006, memory: 3224, loss_cls: 0.2548, loss_bbox: 0.2479, loss: 0.5027 2022-10-03 23:33:55,720 - mmdet - INFO - Iter [5900/12000] lr: 1.500e-02, eta: 0:08:21, time: 0.082, data_time: 0.006, memory: 3224, loss_cls: 0.2380, loss_bbox: 0.2433, loss: 0.4812 2022-10-03 23:33:59,801 - mmdet - INFO - Iter [5950/12000] lr: 1.500e-02, eta: 0:08:17, time: 0.082, data_time: 0.006, memory: 3224, loss_cls: 0.2395, loss_bbox: 0.2469, loss: 0.4864 2022-10-03 23:34:03,792 - mmdet - INFO - Exp name: retinanet_mstrain_12k_voc0712.py 2022-10-03 23:34:03,793 - mmdet - INFO - Iter [6000/12000] lr: 1.500e-02, eta: 0:08:12, time: 0.080, data_time: 0.005, memory: 3224, loss_cls: 0.2369, loss_bbox: 0.2395, loss: 0.4764 2022-10-03 23:34:07,771 - mmdet - INFO - Iter [6050/12000] lr: 1.500e-02, eta: 0:08:08, time: 0.080, data_time: 0.006, memory: 3224, loss_cls: 0.2330, loss_bbox: 0.2465, loss: 0.4794 2022-10-03 23:34:11,820 - mmdet - INFO - Iter [6100/12000] lr: 1.500e-02, eta: 0:08:04, time: 0.081, data_time: 0.006, memory: 3224, loss_cls: 0.2389, loss_bbox: 0.2384, loss: 0.4773 2022-10-03 23:34:15,828 - mmdet - INFO - Iter [6150/12000] lr: 1.500e-02, eta: 0:08:00, time: 0.080, data_time: 0.006, memory: 3224, loss_cls: 0.2498, loss_bbox: 0.2481, loss: 0.4979 2022-10-03 23:34:19,887 - mmdet - INFO - Iter [6200/12000] lr: 1.500e-02, eta: 0:07:56, time: 0.081, data_time: 0.006, memory: 3224, loss_cls: 0.2274, loss_bbox: 0.2364, loss: 0.4638 2022-10-03 23:34:23,879 - mmdet - INFO - Iter [6250/12000] lr: 1.500e-02, eta: 0:07:51, time: 0.080, data_time: 0.006, memory: 3224, loss_cls: 0.2375, loss_bbox: 0.2369, loss: 0.4744 2022-10-03 23:34:27,922 - mmdet - INFO - Iter [6300/12000] lr: 1.500e-02, eta: 0:07:47, time: 0.081, data_time: 0.006, memory: 3224, loss_cls: 0.2253, loss_bbox: 0.2289, loss: 0.4542 2022-10-03 23:34:31,934 - mmdet - INFO - Iter [6350/12000] lr: 1.500e-02, eta: 0:07:43, time: 0.080, data_time: 0.006, memory: 3224, loss_cls: 0.2235, loss_bbox: 0.2355, loss: 0.4591 2022-10-03 23:34:36,158 - mmdet - INFO - Iter [6400/12000] lr: 1.500e-02, eta: 0:07:39, time: 0.085, data_time: 0.006, memory: 3224, loss_cls: 0.2184, loss_bbox: 0.2300, loss: 0.4484 2022-10-03 23:34:40,332 - mmdet - INFO - Iter [6450/12000] lr: 1.500e-02, eta: 0:07:35, time: 0.083, data_time: 0.006, memory: 3224, loss_cls: 0.2324, loss_bbox: 0.2364, loss: 0.4689 2022-10-03 23:34:44,335 - mmdet - INFO - Iter [6500/12000] lr: 1.500e-02, eta: 0:07:31, time: 0.080, data_time: 0.006, memory: 3224, loss_cls: 0.2435, loss_bbox: 0.2395, loss: 0.4831 2022-10-03 23:34:48,486 - mmdet - INFO - Iter [6550/12000] lr: 1.500e-02, eta: 0:07:27, time: 0.083, data_time: 0.006, memory: 3224, loss_cls: 0.2383, loss_bbox: 0.2421, loss: 0.4804 2022-10-03 23:34:52,504 - mmdet - INFO - Iter [6600/12000] lr: 1.500e-02, eta: 0:07:23, time: 0.080, data_time: 0.005, memory: 3224, loss_cls: 0.2283, loss_bbox: 0.2329, loss: 0.4611 2022-10-03 23:34:56,575 - mmdet - INFO - Iter [6650/12000] lr: 1.500e-02, eta: 0:07:18, time: 0.081, data_time: 0.006, memory: 3224, loss_cls: 0.2189, loss_bbox: 0.2293, loss: 0.4481 2022-10-03 23:35:00,702 - mmdet - INFO - Iter [6700/12000] lr: 1.500e-02, eta: 0:07:14, time: 0.083, data_time: 0.006, memory: 3224, loss_cls: 0.2155, loss_bbox: 0.2316, loss: 0.4471 2022-10-03 23:35:04,665 - mmdet - INFO - Iter [6750/12000] lr: 1.500e-02, eta: 0:07:10, time: 0.079, data_time: 0.006, memory: 3224, loss_cls: 0.2328, loss_bbox: 0.2393, loss: 0.4722 2022-10-03 23:35:08,662 - mmdet - INFO - Iter [6800/12000] lr: 1.500e-02, eta: 0:07:06, time: 0.080, data_time: 0.005, memory: 3224, loss_cls: 0.2150, loss_bbox: 0.2267, loss: 0.4417 2022-10-03 23:35:12,647 - mmdet - INFO - Iter [6850/12000] lr: 1.500e-02, eta: 0:07:02, time: 0.080, data_time: 0.006, memory: 3224, loss_cls: 0.2233, loss_bbox: 0.2365, loss: 0.4599 2022-10-03 23:35:16,806 - mmdet - INFO - Iter [6900/12000] lr: 1.500e-02, eta: 0:06:58, time: 0.083, data_time: 0.006, memory: 3224, loss_cls: 0.2348, loss_bbox: 0.2479, loss: 0.4827 2022-10-03 23:35:20,900 - mmdet - INFO - Iter [6950/12000] lr: 1.500e-02, eta: 0:06:54, time: 0.082, data_time: 0.006, memory: 3224, loss_cls: 0.2296, loss_bbox: 0.2341, loss: 0.4637 2022-10-03 23:35:24,930 - mmdet - INFO - Exp name: retinanet_mstrain_12k_voc0712.py 2022-10-03 23:35:24,930 - mmdet - INFO - Iter [7000/12000] lr: 1.500e-02, eta: 0:06:50, time: 0.081, data_time: 0.006, memory: 3224, loss_cls: 0.2317, loss_bbox: 0.2416, loss: 0.4734 2022-10-03 23:35:28,924 - mmdet - INFO - Iter [7050/12000] lr: 1.500e-02, eta: 0:06:45, time: 0.080, data_time: 0.006, memory: 3224, loss_cls: 0.2193, loss_bbox: 0.2366, loss: 0.4560 2022-10-03 23:35:33,144 - mmdet - INFO - Iter [7100/12000] lr: 1.500e-02, eta: 0:06:41, time: 0.084, data_time: 0.006, memory: 3224, loss_cls: 0.2232, loss_bbox: 0.2417, loss: 0.4648 2022-10-03 23:35:37,317 - mmdet - INFO - Iter [7150/12000] lr: 1.500e-02, eta: 0:06:37, time: 0.083, data_time: 0.006, memory: 3224, loss_cls: 0.2292, loss_bbox: 0.2381, loss: 0.4673 2022-10-03 23:35:41,335 - mmdet - INFO - Iter [7200/12000] lr: 1.500e-02, eta: 0:06:33, time: 0.080, data_time: 0.006, memory: 3224, loss_cls: 0.2321, loss_bbox: 0.2379, loss: 0.4700 2022-10-03 23:35:45,276 - mmdet - INFO - Iter [7250/12000] lr: 1.500e-02, eta: 0:06:29, time: 0.079, data_time: 0.006, memory: 3224, loss_cls: 0.2142, loss_bbox: 0.2347, loss: 0.4490 2022-10-03 23:35:49,461 - mmdet - INFO - Iter [7300/12000] lr: 1.500e-02, eta: 0:06:25, time: 0.084, data_time: 0.006, memory: 3224, loss_cls: 0.2111, loss_bbox: 0.2279, loss: 0.4390 2022-10-03 23:35:53,549 - mmdet - INFO - Iter [7350/12000] lr: 1.500e-02, eta: 0:06:21, time: 0.082, data_time: 0.006, memory: 3224, loss_cls: 0.2049, loss_bbox: 0.2236, loss: 0.4284 2022-10-03 23:35:57,655 - mmdet - INFO - Iter [7400/12000] lr: 1.500e-02, eta: 0:06:17, time: 0.082, data_time: 0.006, memory: 3224, loss_cls: 0.2121, loss_bbox: 0.2243, loss: 0.4365 2022-10-03 23:36:01,893 - mmdet - INFO - Iter [7450/12000] lr: 1.500e-02, eta: 0:06:13, time: 0.085, data_time: 0.006, memory: 3224, loss_cls: 0.2258, loss_bbox: 0.2258, loss: 0.4517 2022-10-03 23:36:06,160 - mmdet - INFO - Iter [7500/12000] lr: 1.500e-02, eta: 0:06:09, time: 0.085, data_time: 0.006, memory: 3224, loss_cls: 0.2130, loss_bbox: 0.2297, loss: 0.4427 2022-10-03 23:36:10,458 - mmdet - INFO - Iter [7550/12000] lr: 1.500e-02, eta: 0:06:05, time: 0.086, data_time: 0.006, memory: 3224, loss_cls: 0.2112, loss_bbox: 0.2282, loss: 0.4394 2022-10-03 23:36:14,596 - mmdet - INFO - Iter [7600/12000] lr: 1.500e-02, eta: 0:06:01, time: 0.083, data_time: 0.006, memory: 3224, loss_cls: 0.2162, loss_bbox: 0.2296, loss: 0.4459 2022-10-03 23:36:18,558 - mmdet - INFO - Iter [7650/12000] lr: 1.500e-02, eta: 0:05:56, time: 0.079, data_time: 0.006, memory: 3224, loss_cls: 0.2151, loss_bbox: 0.2276, loss: 0.4427 2022-10-03 23:36:22,654 - mmdet - INFO - Iter [7700/12000] lr: 1.500e-02, eta: 0:05:52, time: 0.082, data_time: 0.006, memory: 3224, loss_cls: 0.2154, loss_bbox: 0.2197, loss: 0.4351 2022-10-03 23:36:26,888 - mmdet - INFO - Iter [7750/12000] lr: 1.500e-02, eta: 0:05:48, time: 0.085, data_time: 0.006, memory: 3224, loss_cls: 0.2141, loss_bbox: 0.2336, loss: 0.4477 2022-10-03 23:36:31,091 - mmdet - INFO - Iter [7800/12000] lr: 1.500e-02, eta: 0:05:44, time: 0.084, data_time: 0.006, memory: 3224, loss_cls: 0.2094, loss_bbox: 0.2219, loss: 0.4313 2022-10-03 23:36:35,109 - mmdet - INFO - Iter [7850/12000] lr: 1.500e-02, eta: 0:05:40, time: 0.080, data_time: 0.006, memory: 3224, loss_cls: 0.2152, loss_bbox: 0.2270, loss: 0.4422 2022-10-03 23:36:39,058 - mmdet - INFO - Iter [7900/12000] lr: 1.500e-02, eta: 0:05:36, time: 0.079, data_time: 0.006, memory: 3224, loss_cls: 0.2235, loss_bbox: 0.2284, loss: 0.4519 2022-10-03 23:36:43,089 - mmdet - INFO - Iter [7950/12000] lr: 1.500e-02, eta: 0:05:32, time: 0.081, data_time: 0.006, memory: 3224, loss_cls: 0.2086, loss_bbox: 0.2243, loss: 0.4329 2022-10-03 23:36:47,082 - mmdet - INFO - Exp name: retinanet_mstrain_12k_voc0712.py 2022-10-03 23:36:47,082 - mmdet - INFO - Iter [8000/12000] lr: 1.500e-02, eta: 0:05:28, time: 0.080, data_time: 0.006, memory: 3224, loss_cls: 0.2060, loss_bbox: 0.2271, loss: 0.4331 2022-10-03 23:36:51,090 - mmdet - INFO - Iter [8050/12000] lr: 1.500e-02, eta: 0:05:23, time: 0.080, data_time: 0.006, memory: 3224, loss_cls: 0.2273, loss_bbox: 0.2295, loss: 0.4568 2022-10-03 23:36:55,155 - mmdet - INFO - Iter [8100/12000] lr: 1.500e-02, eta: 0:05:19, time: 0.081, data_time: 0.006, memory: 3224, loss_cls: 0.2213, loss_bbox: 0.2310, loss: 0.4522 2022-10-03 23:36:59,214 - mmdet - INFO - Iter [8150/12000] lr: 1.500e-02, eta: 0:05:15, time: 0.081, data_time: 0.006, memory: 3224, loss_cls: 0.2237, loss_bbox: 0.2350, loss: 0.4587 2022-10-03 23:37:03,175 - mmdet - INFO - Iter [8200/12000] lr: 1.500e-02, eta: 0:05:11, time: 0.079, data_time: 0.005, memory: 3224, loss_cls: 0.2133, loss_bbox: 0.2278, loss: 0.4411 2022-10-03 23:37:07,150 - mmdet - INFO - Iter [8250/12000] lr: 1.500e-02, eta: 0:05:07, time: 0.079, data_time: 0.005, memory: 3224, loss_cls: 0.2180, loss_bbox: 0.2319, loss: 0.4499 2022-10-03 23:37:11,356 - mmdet - INFO - Iter [8300/12000] lr: 1.500e-02, eta: 0:05:03, time: 0.084, data_time: 0.006, memory: 3224, loss_cls: 0.2139, loss_bbox: 0.2265, loss: 0.4404 2022-10-03 23:37:15,482 - mmdet - INFO - Iter [8350/12000] lr: 1.500e-02, eta: 0:04:59, time: 0.083, data_time: 0.006, memory: 3224, loss_cls: 0.1983, loss_bbox: 0.2135, loss: 0.4118 2022-10-03 23:37:19,702 - mmdet - INFO - Iter [8400/12000] lr: 1.500e-02, eta: 0:04:55, time: 0.084, data_time: 0.006, memory: 3224, loss_cls: 0.1954, loss_bbox: 0.2159, loss: 0.4113 2022-10-03 23:37:23,798 - mmdet - INFO - Iter [8450/12000] lr: 1.500e-02, eta: 0:04:51, time: 0.082, data_time: 0.006, memory: 3224, loss_cls: 0.2016, loss_bbox: 0.2227, loss: 0.4243 2022-10-03 23:37:27,846 - mmdet - INFO - Iter [8500/12000] lr: 1.500e-02, eta: 0:04:46, time: 0.081, data_time: 0.006, memory: 3224, loss_cls: 0.2044, loss_bbox: 0.2293, loss: 0.4337 2022-10-03 23:37:31,839 - mmdet - INFO - Iter [8550/12000] lr: 1.500e-02, eta: 0:04:42, time: 0.080, data_time: 0.006, memory: 3224, loss_cls: 0.1912, loss_bbox: 0.2162, loss: 0.4074 2022-10-03 23:37:35,786 - mmdet - INFO - Iter [8600/12000] lr: 1.500e-02, eta: 0:04:38, time: 0.079, data_time: 0.006, memory: 3224, loss_cls: 0.1917, loss_bbox: 0.2146, loss: 0.4063 2022-10-03 23:37:39,875 - mmdet - INFO - Iter [8650/12000] lr: 1.500e-02, eta: 0:04:34, time: 0.082, data_time: 0.006, memory: 3224, loss_cls: 0.1972, loss_bbox: 0.2203, loss: 0.4175 2022-10-03 23:37:43,892 - mmdet - INFO - Iter [8700/12000] lr: 1.500e-02, eta: 0:04:30, time: 0.080, data_time: 0.006, memory: 3224, loss_cls: 0.2027, loss_bbox: 0.2158, loss: 0.4185 2022-10-03 23:37:47,911 - mmdet - INFO - Iter [8750/12000] lr: 1.500e-02, eta: 0:04:26, time: 0.080, data_time: 0.006, memory: 3224, loss_cls: 0.2064, loss_bbox: 0.2343, loss: 0.4407 2022-10-03 23:37:52,017 - mmdet - INFO - Iter [8800/12000] lr: 1.500e-02, eta: 0:04:22, time: 0.082, data_time: 0.006, memory: 3224, loss_cls: 0.1968, loss_bbox: 0.2174, loss: 0.4142 2022-10-03 23:37:56,011 - mmdet - INFO - Iter [8850/12000] lr: 1.500e-02, eta: 0:04:18, time: 0.080, data_time: 0.006, memory: 3224, loss_cls: 0.1885, loss_bbox: 0.2162, loss: 0.4047 2022-10-03 23:38:00,134 - mmdet - INFO - Iter [8900/12000] lr: 1.500e-02, eta: 0:04:13, time: 0.082, data_time: 0.006, memory: 3224, loss_cls: 0.2002, loss_bbox: 0.2231, loss: 0.4233 2022-10-03 23:38:04,124 - mmdet - INFO - Iter [8950/12000] lr: 1.500e-02, eta: 0:04:09, time: 0.080, data_time: 0.005, memory: 3224, loss_cls: 0.2095, loss_bbox: 0.2255, loss: 0.4350 2022-10-03 23:38:08,120 - mmdet - INFO - Exp name: retinanet_mstrain_12k_voc0712.py 2022-10-03 23:38:08,120 - mmdet - INFO - Iter [9000/12000] lr: 1.500e-02, eta: 0:04:05, time: 0.080, data_time: 0.006, memory: 3224, loss_cls: 0.2179, loss_bbox: 0.2354, loss: 0.4533 2022-10-03 23:38:12,120 - mmdet - INFO - Iter [9050/12000] lr: 1.500e-03, eta: 0:04:01, time: 0.080, data_time: 0.006, memory: 3224, loss_cls: 0.1897, loss_bbox: 0.2153, loss: 0.4050 2022-10-03 23:38:16,101 - mmdet - INFO - Iter [9100/12000] lr: 1.500e-03, eta: 0:03:57, time: 0.080, data_time: 0.006, memory: 3224, loss_cls: 0.1712, loss_bbox: 0.2062, loss: 0.3774 2022-10-03 23:38:20,219 - mmdet - INFO - Iter [9150/12000] lr: 1.500e-03, eta: 0:03:53, time: 0.082, data_time: 0.006, memory: 3224, loss_cls: 0.1705, loss_bbox: 0.2064, loss: 0.3768 2022-10-03 23:38:24,213 - mmdet - INFO - Iter [9200/12000] lr: 1.500e-03, eta: 0:03:49, time: 0.080, data_time: 0.006, memory: 3224, loss_cls: 0.1665, loss_bbox: 0.1998, loss: 0.3663 2022-10-03 23:38:28,257 - mmdet - INFO - Iter [9250/12000] lr: 1.500e-03, eta: 0:03:45, time: 0.081, data_time: 0.006, memory: 3224, loss_cls: 0.1659, loss_bbox: 0.2035, loss: 0.3695 2022-10-03 23:38:32,538 - mmdet - INFO - Iter [9300/12000] lr: 1.500e-03, eta: 0:03:41, time: 0.086, data_time: 0.006, memory: 3224, loss_cls: 0.1672, loss_bbox: 0.1965, loss: 0.3637 2022-10-03 23:38:36,700 - mmdet - INFO - Iter [9350/12000] lr: 1.500e-03, eta: 0:03:37, time: 0.083, data_time: 0.006, memory: 3224, loss_cls: 0.1513, loss_bbox: 0.1907, loss: 0.3420 2022-10-03 23:38:40,755 - mmdet - INFO - Iter [9400/12000] lr: 1.500e-03, eta: 0:03:32, time: 0.081, data_time: 0.006, memory: 3224, loss_cls: 0.1528, loss_bbox: 0.1907, loss: 0.3435 2022-10-03 23:38:44,827 - mmdet - INFO - Iter [9450/12000] lr: 1.500e-03, eta: 0:03:28, time: 0.081, data_time: 0.006, memory: 3224, loss_cls: 0.1436, loss_bbox: 0.1825, loss: 0.3260 2022-10-03 23:38:48,828 - mmdet - INFO - Iter [9500/12000] lr: 1.500e-03, eta: 0:03:24, time: 0.080, data_time: 0.006, memory: 3224, loss_cls: 0.1446, loss_bbox: 0.1885, loss: 0.3330 2022-10-03 23:38:53,071 - mmdet - INFO - Iter [9550/12000] lr: 1.500e-03, eta: 0:03:20, time: 0.085, data_time: 0.006, memory: 3224, loss_cls: 0.1454, loss_bbox: 0.1821, loss: 0.3275 2022-10-03 23:38:57,363 - mmdet - INFO - Iter [9600/12000] lr: 1.500e-03, eta: 0:03:16, time: 0.086, data_time: 0.006, memory: 3224, loss_cls: 0.1452, loss_bbox: 0.1871, loss: 0.3324 2022-10-03 23:39:01,565 - mmdet - INFO - Iter [9650/12000] lr: 1.500e-03, eta: 0:03:12, time: 0.084, data_time: 0.006, memory: 3224, loss_cls: 0.1359, loss_bbox: 0.1872, loss: 0.3231 2022-10-03 23:39:05,566 - mmdet - INFO - Iter [9700/12000] lr: 1.500e-03, eta: 0:03:08, time: 0.080, data_time: 0.006, memory: 3224, loss_cls: 0.1465, loss_bbox: 0.1884, loss: 0.3349 2022-10-03 23:39:09,749 - mmdet - INFO - Iter [9750/12000] lr: 1.500e-03, eta: 0:03:04, time: 0.084, data_time: 0.006, memory: 3224, loss_cls: 0.1463, loss_bbox: 0.1783, loss: 0.3245 2022-10-03 23:39:13,983 - mmdet - INFO - Iter [9800/12000] lr: 1.500e-03, eta: 0:03:00, time: 0.085, data_time: 0.006, memory: 3224, loss_cls: 0.1454, loss_bbox: 0.1846, loss: 0.3300 2022-10-03 23:39:18,054 - mmdet - INFO - Iter [9850/12000] lr: 1.500e-03, eta: 0:02:56, time: 0.081, data_time: 0.006, memory: 3224, loss_cls: 0.1478, loss_bbox: 0.1887, loss: 0.3366 2022-10-03 23:39:22,168 - mmdet - INFO - Iter [9900/12000] lr: 1.500e-03, eta: 0:02:52, time: 0.082, data_time: 0.006, memory: 3224, loss_cls: 0.1466, loss_bbox: 0.1900, loss: 0.3366 2022-10-03 23:39:26,300 - mmdet - INFO - Iter [9950/12000] lr: 1.500e-03, eta: 0:02:47, time: 0.083, data_time: 0.006, memory: 3224, loss_cls: 0.1438, loss_bbox: 0.1887, loss: 0.3325 2022-10-03 23:39:30,376 - mmdet - INFO - Exp name: retinanet_mstrain_12k_voc0712.py 2022-10-03 23:39:30,377 - mmdet - INFO - Iter [10000/12000] lr: 1.500e-03, eta: 0:02:43, time: 0.081, data_time: 0.005, memory: 3224, loss_cls: 0.1425, loss_bbox: 0.1841, loss: 0.3266 2022-10-03 23:39:34,388 - mmdet - INFO - Iter [10050/12000] lr: 1.500e-03, eta: 0:02:39, time: 0.080, data_time: 0.006, memory: 3224, loss_cls: 0.1405, loss_bbox: 0.1827, loss: 0.3233 2022-10-03 23:39:38,375 - mmdet - INFO - Iter [10100/12000] lr: 1.500e-03, eta: 0:02:35, time: 0.080, data_time: 0.006, memory: 3224, loss_cls: 0.1465, loss_bbox: 0.1857, loss: 0.3322 2022-10-03 23:39:42,580 - mmdet - INFO - Iter [10150/12000] lr: 1.500e-03, eta: 0:02:31, time: 0.084, data_time: 0.006, memory: 3224, loss_cls: 0.1381, loss_bbox: 0.1795, loss: 0.3176 2022-10-03 23:39:46,711 - mmdet - INFO - Iter [10200/12000] lr: 1.500e-03, eta: 0:02:27, time: 0.083, data_time: 0.006, memory: 3224, loss_cls: 0.1452, loss_bbox: 0.1838, loss: 0.3290 2022-10-03 23:39:50,718 - mmdet - INFO - Iter [10250/12000] lr: 1.500e-03, eta: 0:02:23, time: 0.080, data_time: 0.006, memory: 3224, loss_cls: 0.1435, loss_bbox: 0.1849, loss: 0.3284 2022-10-03 23:39:54,727 - mmdet - INFO - Iter [10300/12000] lr: 1.500e-03, eta: 0:02:19, time: 0.080, data_time: 0.006, memory: 3224, loss_cls: 0.1427, loss_bbox: 0.1860, loss: 0.3287 2022-10-03 23:39:58,749 - mmdet - INFO - Iter [10350/12000] lr: 1.500e-03, eta: 0:02:15, time: 0.080, data_time: 0.006, memory: 3224, loss_cls: 0.1485, loss_bbox: 0.1881, loss: 0.3366 2022-10-03 23:40:02,757 - mmdet - INFO - Iter [10400/12000] lr: 1.500e-03, eta: 0:02:11, time: 0.080, data_time: 0.006, memory: 3224, loss_cls: 0.1377, loss_bbox: 0.1817, loss: 0.3194 2022-10-03 23:40:06,778 - mmdet - INFO - Iter [10450/12000] lr: 1.500e-03, eta: 0:02:06, time: 0.080, data_time: 0.006, memory: 3224, loss_cls: 0.1335, loss_bbox: 0.1789, loss: 0.3124 2022-10-03 23:40:10,973 - mmdet - INFO - Iter [10500/12000] lr: 1.500e-03, eta: 0:02:02, time: 0.084, data_time: 0.006, memory: 3224, loss_cls: 0.1336, loss_bbox: 0.1866, loss: 0.3202 2022-10-03 23:40:15,026 - mmdet - INFO - Iter [10550/12000] lr: 1.500e-03, eta: 0:01:58, time: 0.081, data_time: 0.006, memory: 3224, loss_cls: 0.1347, loss_bbox: 0.1769, loss: 0.3116 2022-10-03 23:40:19,063 - mmdet - INFO - Iter [10600/12000] lr: 1.500e-03, eta: 0:01:54, time: 0.081, data_time: 0.006, memory: 3224, loss_cls: 0.1328, loss_bbox: 0.1807, loss: 0.3135 2022-10-03 23:40:23,236 - mmdet - INFO - Iter [10650/12000] lr: 1.500e-03, eta: 0:01:50, time: 0.083, data_time: 0.006, memory: 3224, loss_cls: 0.1388, loss_bbox: 0.1812, loss: 0.3200 2022-10-03 23:40:27,364 - mmdet - INFO - Iter [10700/12000] lr: 1.500e-03, eta: 0:01:46, time: 0.082, data_time: 0.006, memory: 3224, loss_cls: 0.1409, loss_bbox: 0.1863, loss: 0.3272 2022-10-03 23:40:31,421 - mmdet - INFO - Iter [10750/12000] lr: 1.500e-03, eta: 0:01:42, time: 0.081, data_time: 0.006, memory: 3224, loss_cls: 0.1357, loss_bbox: 0.1779, loss: 0.3136 2022-10-03 23:40:35,447 - mmdet - INFO - Iter [10800/12000] lr: 1.500e-03, eta: 0:01:38, time: 0.080, data_time: 0.005, memory: 3224, loss_cls: 0.1373, loss_bbox: 0.1832, loss: 0.3205 2022-10-03 23:40:39,435 - mmdet - INFO - Iter [10850/12000] lr: 1.500e-03, eta: 0:01:34, time: 0.080, data_time: 0.006, memory: 3224, loss_cls: 0.1369, loss_bbox: 0.1763, loss: 0.3132 2022-10-03 23:40:43,619 - mmdet - INFO - Iter [10900/12000] lr: 1.500e-03, eta: 0:01:30, time: 0.084, data_time: 0.006, memory: 3224, loss_cls: 0.1321, loss_bbox: 0.1768, loss: 0.3089 2022-10-03 23:40:47,784 - mmdet - INFO - Iter [10950/12000] lr: 1.500e-03, eta: 0:01:25, time: 0.083, data_time: 0.006, memory: 3224, loss_cls: 0.1333, loss_bbox: 0.1819, loss: 0.3152 2022-10-03 23:40:51,741 - mmdet - INFO - Exp name: retinanet_mstrain_12k_voc0712.py 2022-10-03 23:40:51,742 - mmdet - INFO - Iter [11000/12000] lr: 1.500e-03, eta: 0:01:21, time: 0.079, data_time: 0.006, memory: 3224, loss_cls: 0.1382, loss_bbox: 0.1829, loss: 0.3211 2022-10-03 23:40:55,915 - mmdet - INFO - Iter [11050/12000] lr: 1.500e-04, eta: 0:01:17, time: 0.084, data_time: 0.006, memory: 3224, loss_cls: 0.1316, loss_bbox: 0.1733, loss: 0.3049 2022-10-03 23:40:59,957 - mmdet - INFO - Iter [11100/12000] lr: 1.500e-04, eta: 0:01:13, time: 0.081, data_time: 0.005, memory: 3224, loss_cls: 0.1339, loss_bbox: 0.1824, loss: 0.3163 2022-10-03 23:41:03,948 - mmdet - INFO - Iter [11150/12000] lr: 1.500e-04, eta: 0:01:09, time: 0.080, data_time: 0.005, memory: 3224, loss_cls: 0.1324, loss_bbox: 0.1758, loss: 0.3082 2022-10-03 23:41:07,959 - mmdet - INFO - Iter [11200/12000] lr: 1.500e-04, eta: 0:01:05, time: 0.080, data_time: 0.006, memory: 3224, loss_cls: 0.1334, loss_bbox: 0.1796, loss: 0.3130 2022-10-03 23:41:11,955 - mmdet - INFO - Iter [11250/12000] lr: 1.500e-04, eta: 0:01:01, time: 0.080, data_time: 0.006, memory: 3224, loss_cls: 0.1316, loss_bbox: 0.1796, loss: 0.3112 2022-10-03 23:41:15,974 - mmdet - INFO - Iter [11300/12000] lr: 1.500e-04, eta: 0:00:57, time: 0.080, data_time: 0.006, memory: 3224, loss_cls: 0.1321, loss_bbox: 0.1769, loss: 0.3091 2022-10-03 23:41:20,077 - mmdet - INFO - Iter [11350/12000] lr: 1.500e-04, eta: 0:00:53, time: 0.082, data_time: 0.006, memory: 3224, loss_cls: 0.1374, loss_bbox: 0.1751, loss: 0.3125 2022-10-03 23:41:24,078 - mmdet - INFO - Iter [11400/12000] lr: 1.500e-04, eta: 0:00:49, time: 0.080, data_time: 0.006, memory: 3224, loss_cls: 0.1315, loss_bbox: 0.1763, loss: 0.3078 2022-10-03 23:41:28,124 - mmdet - INFO - Iter [11450/12000] lr: 1.500e-04, eta: 0:00:45, time: 0.081, data_time: 0.006, memory: 3224, loss_cls: 0.1331, loss_bbox: 0.1792, loss: 0.3123 2022-10-03 23:41:32,144 - mmdet - INFO - Iter [11500/12000] lr: 1.500e-04, eta: 0:00:40, time: 0.080, data_time: 0.006, memory: 3224, loss_cls: 0.1207, loss_bbox: 0.1679, loss: 0.2886 2022-10-03 23:41:36,142 - mmdet - INFO - Iter [11550/12000] lr: 1.500e-04, eta: 0:00:36, time: 0.080, data_time: 0.006, memory: 3224, loss_cls: 0.1375, loss_bbox: 0.1823, loss: 0.3198 2022-10-03 23:41:40,174 - mmdet - INFO - Iter [11600/12000] lr: 1.500e-04, eta: 0:00:32, time: 0.081, data_time: 0.006, memory: 3224, loss_cls: 0.1275, loss_bbox: 0.1758, loss: 0.3033 2022-10-03 23:41:44,256 - mmdet - INFO - Iter [11650/12000] lr: 1.500e-04, eta: 0:00:28, time: 0.082, data_time: 0.006, memory: 3224, loss_cls: 0.1376, loss_bbox: 0.1794, loss: 0.3171 2022-10-03 23:41:48,314 - mmdet - INFO - Iter [11700/12000] lr: 1.500e-04, eta: 0:00:24, time: 0.081, data_time: 0.006, memory: 3224, loss_cls: 0.1246, loss_bbox: 0.1731, loss: 0.2976 2022-10-03 23:41:52,368 - mmdet - INFO - Iter [11750/12000] lr: 1.500e-04, eta: 0:00:20, time: 0.081, data_time: 0.006, memory: 3224, loss_cls: 0.1330, loss_bbox: 0.1800, loss: 0.3130 2022-10-03 23:41:56,339 - mmdet - INFO - Iter [11800/12000] lr: 1.500e-04, eta: 0:00:16, time: 0.079, data_time: 0.006, memory: 3224, loss_cls: 0.1323, loss_bbox: 0.1737, loss: 0.3060 2022-10-03 23:42:00,341 - mmdet - INFO - Iter [11850/12000] lr: 1.500e-04, eta: 0:00:12, time: 0.080, data_time: 0.006, memory: 3224, loss_cls: 0.1308, loss_bbox: 0.1803, loss: 0.3111 2022-10-03 23:42:04,373 - mmdet - INFO - Iter [11900/12000] lr: 1.500e-04, eta: 0:00:08, time: 0.081, data_time: 0.006, memory: 3224, loss_cls: 0.1270, loss_bbox: 0.1711, loss: 0.2981 2022-10-03 23:42:08,494 - mmdet - INFO - Iter [11950/12000] lr: 1.500e-04, eta: 0:00:04, time: 0.082, data_time: 0.006, memory: 3224, loss_cls: 0.1334, loss_bbox: 0.1811, loss: 0.3145 2022-10-03 23:42:12,730 - mmdet - INFO - Saving checkpoint at 12000 iterations 2022-10-03 23:42:13,292 - mmdet - INFO - Exp name: retinanet_mstrain_12k_voc0712.py 2022-10-03 23:42:13,293 - mmdet - INFO - Iter [12000/12000] lr: 1.500e-04, eta: 0:00:00, time: 0.096, data_time: 0.006, memory: 3224, loss_cls: 0.1328, loss_bbox: 0.1773, loss: 0.3101 2022-10-03 23:42:35,293 - mmdet - INFO - +-------------+------+-------+--------+-------+ | class | gts | dets | recall | ap | +-------------+------+-------+--------+-------+ | aeroplane | 285 | 4350 | 0.982 | 0.858 | | bicycle | 337 | 7182 | 0.982 | 0.852 | | bird | 459 | 6594 | 0.976 | 0.843 | | boat | 263 | 10306 | 0.977 | 0.748 | | bottle | 469 | 15005 | 0.949 | 0.708 | | bus | 213 | 5621 | 0.991 | 0.854 | | car | 1201 | 18728 | 0.989 | 0.884 | | cat | 358 | 3995 | 0.989 | 0.890 | | chair | 756 | 27501 | 0.963 | 0.659 | | cow | 244 | 4390 | 0.996 | 0.835 | | diningtable | 206 | 13269 | 0.956 | 0.696 | | dog | 489 | 5970 | 0.990 | 0.867 | | horse | 348 | 5822 | 0.997 | 0.858 | | motorbike | 325 | 7104 | 0.985 | 0.842 | | person | 4528 | 52884 | 0.988 | 0.854 | | pottedplant | 480 | 13789 | 0.944 | 0.582 | | sheep | 242 | 4454 | 0.988 | 0.819 | | sofa | 239 | 8932 | 0.983 | 0.758 | | train | 282 | 5723 | 0.986 | 0.855 | | tvmonitor | 308 | 7857 | 0.971 | 0.820 | +-------------+------+-------+--------+-------+ | mAP | | | | 0.804 | +-------------+------+-------+--------+-------+ 2022-10-03 23:42:35,884 - mmdet - INFO - Now best checkpoint is saved as best_mAP_iter_12000.pth. 2022-10-03 23:42:35,885 - mmdet - INFO - Best mAP is 0.8042 at 12000 iter. 2022-10-03 23:42:35,885 - mmdet - INFO - Exp name: retinanet_mstrain_12k_voc0712.py 2022-10-03 23:42:35,885 - mmdet - INFO - Iter(val) [619] mAP: 0.8042, AP50: 0.8040