2023-04-02 18:47:11,122   INFO  **********************Start logging**********************
2023-04-02 18:47:11,123   INFO  CUDA_VISIBLE_DEVICES=ALL
2023-04-02 18:47:11,123   INFO  total_batch_size: 16
2023-04-02 18:47:11,124   INFO  cfg_file         cfgs/sunrgbd_models/CAGroup3D.yaml
2023-04-02 18:47:11,125   INFO  batch_size       16
2023-04-02 18:47:11,126   INFO  epochs           13
2023-04-02 18:47:11,127   INFO  workers          4
2023-04-02 18:47:11,128   INFO  extra_tag        cagroup3d-win10-sunrgbd-train
2023-04-02 18:47:11,130   INFO  ckpt             ../output/sunrgbd_models/CAGroup3D/cagroup3d-win10-sunrgbd-train-good/ckpt/checkpoint_epoch_12.pth
2023-04-02 18:47:11,132   INFO  pretrained_model ../output/sunrgbd_models/CAGroup3D/cagroup3d-win10-sunrgbd-train-good/ckpt/checkpoint_epoch_12.pth
2023-04-02 18:47:11,133   INFO  launcher         pytorch
2023-04-02 18:47:11,134   INFO  tcp_port         18888
2023-04-02 18:47:11,136   INFO  sync_bn          False
2023-04-02 18:47:11,138   INFO  fix_random_seed  True
2023-04-02 18:47:11,139   INFO  ckpt_save_interval 1
2023-04-02 18:47:11,140   INFO  max_ckpt_save_num 30
2023-04-02 18:47:11,141   INFO  merge_all_iters_to_one_epoch False
2023-04-02 18:47:11,142   INFO  set_cfgs         None
2023-04-02 18:47:11,143   INFO  max_waiting_mins 0
2023-04-02 18:47:11,144   INFO  start_epoch      0
2023-04-02 18:47:11,145   INFO  num_epochs_to_eval 0
2023-04-02 18:47:11,147   INFO  save_to_file     False
2023-04-02 18:47:11,148   INFO  cfg.ROOT_DIR: C:\PINKAMENA\CITYU\CS5182\proj\CAGroup3D
2023-04-02 18:47:11,148   INFO  cfg.LOCAL_RANK: 0
2023-04-02 18:47:11,149   INFO  cfg.CLASS_NAMES: ['bed', 'table', 'sofa', 'chair', 'toilet', 'desk', 'dresser', 'night_stand', 'bookshelf', 'bathtub']
2023-04-02 18:47:11,151   INFO  
cfg.DATA_CONFIG = edict()
2023-04-02 18:47:11,153   INFO  cfg.DATA_CONFIG.DATASET: SunrgbdDataset
2023-04-02 18:47:11,155   INFO  cfg.DATA_CONFIG.DATA_PATH: ../data/sunrgbd_data/sunrgbd
2023-04-02 18:47:11,155   INFO  cfg.DATA_CONFIG.PROCESSED_DATA_TAG: sunrgbd_processed_data_v0_5_0
2023-04-02 18:47:11,158   INFO  cfg.DATA_CONFIG.POINT_CLOUD_RANGE: [-40, -40, -10, 40, 40, 10]
2023-04-02 18:47:11,159   INFO  
cfg.DATA_CONFIG.DATA_SPLIT = edict()
2023-04-02 18:47:11,161   INFO  cfg.DATA_CONFIG.DATA_SPLIT.train: train
2023-04-02 18:47:11,161   INFO  cfg.DATA_CONFIG.DATA_SPLIT.test: val
2023-04-02 18:47:11,163   INFO  
cfg.DATA_CONFIG.REPEAT = edict()
2023-04-02 18:47:11,164   INFO  cfg.DATA_CONFIG.REPEAT.train: 4
2023-04-02 18:47:11,165   INFO  cfg.DATA_CONFIG.REPEAT.test: 1
2023-04-02 18:47:11,166   INFO  
cfg.DATA_CONFIG.INFO_PATH = edict()
2023-04-02 18:47:11,167   INFO  cfg.DATA_CONFIG.INFO_PATH.train: ['sunrgbd_infos_train.pkl']
2023-04-02 18:47:11,169   INFO  cfg.DATA_CONFIG.INFO_PATH.test: ['sunrgbd_infos_val.pkl']
2023-04-02 18:47:11,170   INFO  cfg.DATA_CONFIG.GET_ITEM_LIST: ['points']
2023-04-02 18:47:11,171   INFO  cfg.DATA_CONFIG.FILTER_EMPTY_BOXES_FOR_TRAIN: True
2023-04-02 18:47:11,172   INFO  
cfg.DATA_CONFIG.DATA_AUGMENTOR_TRAIN = edict()
2023-04-02 18:47:11,174   INFO  cfg.DATA_CONFIG.DATA_AUGMENTOR_TRAIN.DISABLE_AUG_LIST: ['placeholder']
2023-04-02 18:47:11,175   INFO  cfg.DATA_CONFIG.DATA_AUGMENTOR_TRAIN.AUG_CONFIG_LIST: [{'NAME': 'indoor_point_sample', 'num_points': 100000}, {'NAME': 'random_world_flip', 'ALONG_AXIS_LIST': ['y']}, {'NAME': 'random_world_rotation_mmdet3d', 'WORLD_ROT_ANGLE': [-0.523599, 0.523599]}, {'NAME': 'random_world_scaling', 'WORLD_SCALE_RANGE': [0.85, 1.15]}, {'NAME': 'random_world_translation', 'ALONG_AXIS_LIST': ['x', 'y', 'z'], 'NOISE_TRANSLATE_STD': 0.1}]
2023-04-02 18:47:11,179   INFO  
cfg.DATA_CONFIG.DATA_AUGMENTOR_TEST = edict()
2023-04-02 18:47:11,180   INFO  cfg.DATA_CONFIG.DATA_AUGMENTOR_TEST.DISABLE_AUG_LIST: ['placeholder']
2023-04-02 18:47:11,182   INFO  cfg.DATA_CONFIG.DATA_AUGMENTOR_TEST.AUG_CONFIG_LIST: [{'NAME': 'indoor_point_sample', 'num_points': 100000}]
2023-04-02 18:47:11,184   INFO  
cfg.DATA_CONFIG.DATA_AUGMENTOR = edict()
2023-04-02 18:47:11,189   INFO  cfg.DATA_CONFIG.DATA_AUGMENTOR.DISABLE_AUG_LIST: ['placeholder']
2023-04-02 18:47:11,191   INFO  cfg.DATA_CONFIG.DATA_AUGMENTOR.AUG_CONFIG_LIST: [{'NAME': 'indoor_point_sample', 'num_points': 50000}]
2023-04-02 18:47:11,192   INFO  
cfg.DATA_CONFIG.POINT_FEATURE_ENCODING = edict()
2023-04-02 18:47:11,193   INFO  cfg.DATA_CONFIG.POINT_FEATURE_ENCODING.encoding_type: absolute_coordinates_encoding
2023-04-02 18:47:11,194   INFO  cfg.DATA_CONFIG.POINT_FEATURE_ENCODING.used_feature_list: ['x', 'y', 'z', 'r', 'g', 'b']
2023-04-02 18:47:11,195   INFO  cfg.DATA_CONFIG.POINT_FEATURE_ENCODING.src_feature_list: ['x', 'y', 'z', 'r', 'g', 'b']
2023-04-02 18:47:11,197   INFO  cfg.DATA_CONFIG.DATA_PROCESSOR: [{'NAME': 'mask_points_and_boxes_outside_range', 'REMOVE_OUTSIDE_BOXES': False}]
2023-04-02 18:47:11,201   INFO  cfg.DATA_CONFIG._BASE_CONFIG_: cfgs/dataset_configs/sunrgbd_dataset.yaml
2023-04-02 18:47:11,202   INFO  cfg.VOXEL_SIZE: 0.02
2023-04-02 18:47:11,202   INFO  cfg.N_CLASSES: 10
2023-04-02 18:47:11,203   INFO  cfg.SEMANTIC_THR: 0.15
2023-04-02 18:47:11,203   INFO  
cfg.MODEL = edict()
2023-04-02 18:47:11,205   INFO  cfg.MODEL.NAME: CAGroup3D
2023-04-02 18:47:11,205   INFO  cfg.MODEL.VOXEL_SIZE: 0.02
2023-04-02 18:47:11,206   INFO  cfg.MODEL.SEMANTIC_MIN_THR: 0.05
2023-04-02 18:47:11,207   INFO  cfg.MODEL.SEMANTIC_ITER_VALUE: 0.02
2023-04-02 18:47:11,208   INFO  cfg.MODEL.SEMANTIC_THR: 0.15
2023-04-02 18:47:11,208   INFO  
cfg.MODEL.BACKBONE_3D = edict()
2023-04-02 18:47:11,210   INFO  cfg.MODEL.BACKBONE_3D.NAME: BiResNet
2023-04-02 18:47:11,211   INFO  cfg.MODEL.BACKBONE_3D.IN_CHANNELS: 3
2023-04-02 18:47:11,215   INFO  cfg.MODEL.BACKBONE_3D.OUT_CHANNELS: 64
2023-04-02 18:47:11,215   INFO  
cfg.MODEL.DENSE_HEAD = edict()
2023-04-02 18:47:11,217   INFO  cfg.MODEL.DENSE_HEAD.NAME: CAGroup3DHead
2023-04-02 18:47:11,218   INFO  cfg.MODEL.DENSE_HEAD.IN_CHANNELS: [64, 128, 256, 512]
2023-04-02 18:47:11,218   INFO  cfg.MODEL.DENSE_HEAD.OUT_CHANNELS: 64
2023-04-02 18:47:11,220   INFO  cfg.MODEL.DENSE_HEAD.SEMANTIC_THR: 0.15
2023-04-02 18:47:11,220   INFO  cfg.MODEL.DENSE_HEAD.VOXEL_SIZE: 0.02
2023-04-02 18:47:11,221   INFO  cfg.MODEL.DENSE_HEAD.N_CLASSES: 10
2023-04-02 18:47:11,223   INFO  cfg.MODEL.DENSE_HEAD.N_REG_OUTS: 8
2023-04-02 18:47:11,224   INFO  cfg.MODEL.DENSE_HEAD.CLS_KERNEL: 9
2023-04-02 18:47:11,224   INFO  cfg.MODEL.DENSE_HEAD.WITH_YAW: True
2023-04-02 18:47:11,225   INFO  cfg.MODEL.DENSE_HEAD.USE_SEM_SCORE: False
2023-04-02 18:47:11,227   INFO  cfg.MODEL.DENSE_HEAD.EXPAND_RATIO: 3
2023-04-02 18:47:11,231   INFO  
cfg.MODEL.DENSE_HEAD.ASSIGNER = edict()
2023-04-02 18:47:11,234   INFO  cfg.MODEL.DENSE_HEAD.ASSIGNER.NAME: CAGroup3DAssigner
2023-04-02 18:47:11,234   INFO  cfg.MODEL.DENSE_HEAD.ASSIGNER.LIMIT: 27
2023-04-02 18:47:11,234   INFO  cfg.MODEL.DENSE_HEAD.ASSIGNER.TOPK: 18
2023-04-02 18:47:11,236   INFO  cfg.MODEL.DENSE_HEAD.ASSIGNER.N_SCALES: 4
2023-04-02 18:47:11,238   INFO  
cfg.MODEL.DENSE_HEAD.LOSS_OFFSET = edict()
2023-04-02 18:47:11,240   INFO  cfg.MODEL.DENSE_HEAD.LOSS_OFFSET.NAME: SmoothL1Loss
2023-04-02 18:47:11,241   INFO  cfg.MODEL.DENSE_HEAD.LOSS_OFFSET.BETA: 0.04
2023-04-02 18:47:11,241   INFO  cfg.MODEL.DENSE_HEAD.LOSS_OFFSET.REDUCTION: sum
2023-04-02 18:47:11,243   INFO  cfg.MODEL.DENSE_HEAD.LOSS_OFFSET.LOSS_WEIGHT: 0.2
2023-04-02 18:47:11,244   INFO  
cfg.MODEL.DENSE_HEAD.LOSS_BBOX = edict()
2023-04-02 18:47:11,246   INFO  cfg.MODEL.DENSE_HEAD.LOSS_BBOX.NAME: IoU3DLoss
2023-04-02 18:47:11,247   INFO  cfg.MODEL.DENSE_HEAD.LOSS_BBOX.WITH_YAW: True
2023-04-02 18:47:11,249   INFO  cfg.MODEL.DENSE_HEAD.LOSS_BBOX.LOSS_WEIGHT: 1.0
2023-04-02 18:47:11,250   INFO  
cfg.MODEL.DENSE_HEAD.NMS_CONFIG = edict()
2023-04-02 18:47:11,251   INFO  cfg.MODEL.DENSE_HEAD.NMS_CONFIG.SCORE_THR: 0.01
2023-04-02 18:47:11,253   INFO  cfg.MODEL.DENSE_HEAD.NMS_CONFIG.NMS_PRE: 1000
2023-04-02 18:47:11,254   INFO  cfg.MODEL.DENSE_HEAD.NMS_CONFIG.IOU_THR: 0.5
2023-04-02 18:47:11,254   INFO  
cfg.MODEL.ROI_HEAD = edict()
2023-04-02 18:47:11,256   INFO  cfg.MODEL.ROI_HEAD.NAME: CAGroup3DRoIHead
2023-04-02 18:47:11,257   INFO  cfg.MODEL.ROI_HEAD.NUM_CLASSES: 10
2023-04-02 18:47:11,258   INFO  cfg.MODEL.ROI_HEAD.MIDDLE_FEATURE_SOURCE: [3]
2023-04-02 18:47:11,260   INFO  cfg.MODEL.ROI_HEAD.GRID_SIZE: 7
2023-04-02 18:47:11,262   INFO  cfg.MODEL.ROI_HEAD.VOXEL_SIZE: 0.02
2023-04-02 18:47:11,263   INFO  cfg.MODEL.ROI_HEAD.COORD_KEY: 2
2023-04-02 18:47:11,264   INFO  cfg.MODEL.ROI_HEAD.MLPS: [[64, 128, 128]]
2023-04-02 18:47:11,265   INFO  cfg.MODEL.ROI_HEAD.CODE_SIZE: 7
2023-04-02 18:47:11,267   INFO  cfg.MODEL.ROI_HEAD.ENCODE_SINCOS: True
2023-04-02 18:47:11,269   INFO  cfg.MODEL.ROI_HEAD.ROI_PER_IMAGE: 128
2023-04-02 18:47:11,271   INFO  cfg.MODEL.ROI_HEAD.ROI_FG_RATIO: 0.9
2023-04-02 18:47:11,272   INFO  cfg.MODEL.ROI_HEAD.REG_FG_THRESH: 0.3
2023-04-02 18:47:11,275   INFO  cfg.MODEL.ROI_HEAD.ROI_CONV_KERNEL: 5
2023-04-02 18:47:11,276   INFO  cfg.MODEL.ROI_HEAD.ENLARGE_RATIO: False
2023-04-02 18:47:11,277   INFO  cfg.MODEL.ROI_HEAD.USE_IOU_LOSS: True
2023-04-02 18:47:11,277   INFO  cfg.MODEL.ROI_HEAD.USE_GRID_OFFSET: False
2023-04-02 18:47:11,279   INFO  cfg.MODEL.ROI_HEAD.USE_SIMPLE_POOLING: True
2023-04-02 18:47:11,280   INFO  cfg.MODEL.ROI_HEAD.USE_CENTER_POOLING: True
2023-04-02 18:47:11,282   INFO  
cfg.MODEL.ROI_HEAD.LOSS_WEIGHTS = edict()
2023-04-02 18:47:11,283   INFO  cfg.MODEL.ROI_HEAD.LOSS_WEIGHTS.RCNN_CLS_WEIGHT: 1.0
2023-04-02 18:47:11,284   INFO  cfg.MODEL.ROI_HEAD.LOSS_WEIGHTS.RCNN_REG_WEIGHT: 0.5
2023-04-02 18:47:11,285   INFO  cfg.MODEL.ROI_HEAD.LOSS_WEIGHTS.RCNN_IOU_WEIGHT: 1.0
2023-04-02 18:47:11,286   INFO  cfg.MODEL.ROI_HEAD.LOSS_WEIGHTS.CODE_WEIGHT: [1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0]
2023-04-02 18:47:11,288   INFO  
cfg.MODEL.POST_PROCESSING = edict()
2023-04-02 18:47:11,290   INFO  cfg.MODEL.POST_PROCESSING.RECALL_THRESH_LIST: [0.25, 0.5]
2023-04-02 18:47:11,292   INFO  cfg.MODEL.POST_PROCESSING.EVAL_METRIC: scannet
2023-04-02 18:47:11,293   INFO  
cfg.OPTIMIZATION = edict()
2023-04-02 18:47:11,295   INFO  cfg.OPTIMIZATION.BATCH_SIZE_PER_GPU: 16
2023-04-02 18:47:11,296   INFO  cfg.OPTIMIZATION.NUM_EPOCHS: 1
2023-04-02 18:47:11,296   INFO  cfg.OPTIMIZATION.OPTIMIZER: adamW
2023-04-02 18:47:11,298   INFO  cfg.OPTIMIZATION.LR: 0.001
2023-04-02 18:47:11,298   INFO  cfg.OPTIMIZATION.WEIGHT_DECAY: 0.0001
2023-04-02 18:47:11,299   INFO  cfg.OPTIMIZATION.DECAY_STEP_LIST: [8, 11]
2023-04-02 18:47:11,300   INFO  cfg.OPTIMIZATION.LR_DECAY: 0.1
2023-04-02 18:47:11,301   INFO  cfg.OPTIMIZATION.GRAD_NORM_CLIP: 10
2023-04-02 18:47:11,302   INFO  cfg.OPTIMIZATION.PCT_START: 0.4
2023-04-02 18:47:11,303   INFO  cfg.OPTIMIZATION.DIV_FACTOR: 10
2023-04-02 18:47:11,306   INFO  cfg.OPTIMIZATION.LR_CLIP: 1e-07
2023-04-02 18:47:11,307   INFO  cfg.OPTIMIZATION.LR_WARMUP: False
2023-04-02 18:47:11,309   INFO  cfg.OPTIMIZATION.WARMUP_EPOCH: 1
2023-04-02 18:47:11,310   INFO  cfg.TAG: CAGroup3D
2023-04-02 18:47:11,311   INFO  cfg.EXP_GROUP_PATH: sunrgbd_models
2023-04-02 18:47:11,474   INFO  Loading SUNRGBD dataset
2023-04-02 18:47:11,731   INFO  Total samples for SUNRGBD dataset: 5285
2023-04-02 18:47:14,571   INFO  ==> Loading parameters from checkpoint ../output/sunrgbd_models/CAGroup3D/cagroup3d-win10-sunrgbd-train-good/ckpt/checkpoint_epoch_12.pth to CPU
2023-04-02 18:47:15,954   INFO  ==> Checkpoint trained from version: pcdet+0.5.2+0000000
2023-04-02 18:47:16,119   INFO  ==> Done (loaded 638/638)
2023-04-02 18:47:16,286   INFO  ==> Loading parameters from checkpoint ../output/sunrgbd_models/CAGroup3D/cagroup3d-win10-sunrgbd-train-good/ckpt/checkpoint_epoch_12.pth to CPU
2023-04-02 18:47:17,535   INFO  ==> Loading optimizer parameters from checkpoint ../output/sunrgbd_models/CAGroup3D/cagroup3d-win10-sunrgbd-train-good/ckpt/checkpoint_epoch_12.pth to CPU
2023-04-02 18:47:17,866   INFO  ==> Done
2023-04-02 18:47:18,267   INFO  DistributedDataParallel(
  (module): CAGroup3D(
    (vfe): None
    (backbone_3d): BiResNet(
      (conv1): Sequential(
        (0): MinkowskiConvolution(in=3, out=64, kernel_size=[3, 3, 3], stride=[1, 1, 1], dilation=[1, 1, 1])
        (1): MinkowskiBatchNorm(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
        (2): MinkowskiReLU()
        (3): MinkowskiConvolution(in=64, out=64, kernel_size=[3, 3, 3], stride=[1, 1, 1], dilation=[1, 1, 1])
        (4): MinkowskiBatchNorm(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
        (5): MinkowskiReLU()
      )
      (relu): MinkowskiReLU()
      (layer1): Sequential(
        (0): BasicBlock(
          (conv1): MinkowskiConvolution(in=64, out=64, kernel_size=[3, 3, 3], stride=[2, 2, 2], dilation=[1, 1, 1])
          (norm1): MinkowskiBatchNorm(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
          (conv2): MinkowskiConvolution(in=64, out=64, kernel_size=[3, 3, 3], stride=[1, 1, 1], dilation=[1, 1, 1])
          (norm2): MinkowskiBatchNorm(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
          (relu): MinkowskiReLU()
          (downsample): Sequential(
            (0): MinkowskiConvolution(in=64, out=64, kernel_size=[1, 1, 1], stride=[2, 2, 2], dilation=[1, 1, 1])
            (1): MinkowskiBatchNorm(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
          )
        )
        (1): BasicBlock(
          (conv1): MinkowskiConvolution(in=64, out=64, kernel_size=[3, 3, 3], stride=[1, 1, 1], dilation=[1, 1, 1])
          (norm1): MinkowskiBatchNorm(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
          (conv2): MinkowskiConvolution(in=64, out=64, kernel_size=[3, 3, 3], stride=[1, 1, 1], dilation=[1, 1, 1])
          (norm2): MinkowskiBatchNorm(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
          (relu): MinkowskiReLU()
        )
      )
      (layer2): Sequential(
        (0): BasicBlock(
          (conv1): MinkowskiConvolution(in=64, out=128, kernel_size=[3, 3, 3], stride=[2, 2, 2], dilation=[1, 1, 1])
          (norm1): MinkowskiBatchNorm(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
          (conv2): MinkowskiConvolution(in=128, out=128, kernel_size=[3, 3, 3], stride=[1, 1, 1], dilation=[1, 1, 1])
          (norm2): MinkowskiBatchNorm(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
          (relu): MinkowskiReLU()
          (downsample): Sequential(
            (0): MinkowskiConvolution(in=64, out=128, kernel_size=[1, 1, 1], stride=[2, 2, 2], dilation=[1, 1, 1])
            (1): MinkowskiBatchNorm(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
          )
        )
        (1): BasicBlock(
          (conv1): MinkowskiConvolution(in=128, out=128, kernel_size=[3, 3, 3], stride=[1, 1, 1], dilation=[1, 1, 1])
          (norm1): MinkowskiBatchNorm(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
          (conv2): MinkowskiConvolution(in=128, out=128, kernel_size=[3, 3, 3], stride=[1, 1, 1], dilation=[1, 1, 1])
          (norm2): MinkowskiBatchNorm(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
          (relu): MinkowskiReLU()
        )
      )
      (layer3): Sequential(
        (0): BasicBlock(
          (conv1): MinkowskiConvolution(in=128, out=256, kernel_size=[3, 3, 3], stride=[2, 2, 2], dilation=[1, 1, 1])
          (norm1): MinkowskiBatchNorm(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
          (conv2): MinkowskiConvolution(in=256, out=256, kernel_size=[3, 3, 3], stride=[1, 1, 1], dilation=[1, 1, 1])
          (norm2): MinkowskiBatchNorm(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
          (relu): MinkowskiReLU()
          (downsample): Sequential(
            (0): MinkowskiConvolution(in=128, out=256, kernel_size=[1, 1, 1], stride=[2, 2, 2], dilation=[1, 1, 1])
            (1): MinkowskiBatchNorm(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
          )
        )
        (1): BasicBlock(
          (conv1): MinkowskiConvolution(in=256, out=256, kernel_size=[3, 3, 3], stride=[1, 1, 1], dilation=[1, 1, 1])
          (norm1): MinkowskiBatchNorm(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
          (conv2): MinkowskiConvolution(in=256, out=256, kernel_size=[3, 3, 3], stride=[1, 1, 1], dilation=[1, 1, 1])
          (norm2): MinkowskiBatchNorm(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
          (relu): MinkowskiReLU()
        )
      )
      (layer4): Sequential(
        (0): BasicBlock(
          (conv1): MinkowskiConvolution(in=256, out=512, kernel_size=[3, 3, 3], stride=[2, 2, 2], dilation=[1, 1, 1])
          (norm1): MinkowskiBatchNorm(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
          (conv2): MinkowskiConvolution(in=512, out=512, kernel_size=[3, 3, 3], stride=[1, 1, 1], dilation=[1, 1, 1])
          (norm2): MinkowskiBatchNorm(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
          (relu): MinkowskiReLU()
          (downsample): Sequential(
            (0): MinkowskiConvolution(in=256, out=512, kernel_size=[1, 1, 1], stride=[2, 2, 2], dilation=[1, 1, 1])
            (1): MinkowskiBatchNorm(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
          )
        )
        (1): BasicBlock(
          (conv1): MinkowskiConvolution(in=512, out=512, kernel_size=[3, 3, 3], stride=[1, 1, 1], dilation=[1, 1, 1])
          (norm1): MinkowskiBatchNorm(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
          (conv2): MinkowskiConvolution(in=512, out=512, kernel_size=[3, 3, 3], stride=[1, 1, 1], dilation=[1, 1, 1])
          (norm2): MinkowskiBatchNorm(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
          (relu): MinkowskiReLU()
        )
      )
      (compression3): Sequential(
        (0): MinkowskiConvolution(in=256, out=128, kernel_size=[1, 1, 1], stride=[1, 1, 1], dilation=[1, 1, 1])
        (1): MinkowskiBatchNorm(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
      )
      (compression4): Sequential(
        (0): MinkowskiConvolution(in=512, out=128, kernel_size=[1, 1, 1], stride=[1, 1, 1], dilation=[1, 1, 1])
        (1): MinkowskiBatchNorm(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
      )
      (down3): Sequential(
        (0): MinkowskiConvolution(in=128, out=256, kernel_size=[3, 3, 3], stride=[2, 2, 2], dilation=[1, 1, 1])
        (1): MinkowskiBatchNorm(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
      )
      (down4): Sequential(
        (0): MinkowskiConvolution(in=128, out=256, kernel_size=[3, 3, 3], stride=[2, 2, 2], dilation=[1, 1, 1])
        (1): MinkowskiBatchNorm(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
        (2): MinkowskiReLU()
        (3): MinkowskiConvolution(in=256, out=512, kernel_size=[3, 3, 3], stride=[2, 2, 2], dilation=[1, 1, 1])
        (4): MinkowskiBatchNorm(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
      )
      (layer3_): Sequential(
        (0): BasicBlock(
          (conv1): MinkowskiConvolution(in=128, out=128, kernel_size=[3, 3, 3], stride=[1, 1, 1], dilation=[1, 1, 1])
          (norm1): MinkowskiBatchNorm(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
          (conv2): MinkowskiConvolution(in=128, out=128, kernel_size=[3, 3, 3], stride=[1, 1, 1], dilation=[1, 1, 1])
          (norm2): MinkowskiBatchNorm(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
          (relu): MinkowskiReLU()
        )
        (1): BasicBlock(
          (conv1): MinkowskiConvolution(in=128, out=128, kernel_size=[3, 3, 3], stride=[1, 1, 1], dilation=[1, 1, 1])
          (norm1): MinkowskiBatchNorm(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
          (conv2): MinkowskiConvolution(in=128, out=128, kernel_size=[3, 3, 3], stride=[1, 1, 1], dilation=[1, 1, 1])
          (norm2): MinkowskiBatchNorm(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
          (relu): MinkowskiReLU()
        )
      )
      (layer4_): Sequential(
        (0): BasicBlock(
          (conv1): MinkowskiConvolution(in=128, out=128, kernel_size=[3, 3, 3], stride=[1, 1, 1], dilation=[1, 1, 1])
          (norm1): MinkowskiBatchNorm(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
          (conv2): MinkowskiConvolution(in=128, out=128, kernel_size=[3, 3, 3], stride=[1, 1, 1], dilation=[1, 1, 1])
          (norm2): MinkowskiBatchNorm(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
          (relu): MinkowskiReLU()
        )
        (1): BasicBlock(
          (conv1): MinkowskiConvolution(in=128, out=128, kernel_size=[3, 3, 3], stride=[1, 1, 1], dilation=[1, 1, 1])
          (norm1): MinkowskiBatchNorm(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
          (conv2): MinkowskiConvolution(in=128, out=128, kernel_size=[3, 3, 3], stride=[1, 1, 1], dilation=[1, 1, 1])
          (norm2): MinkowskiBatchNorm(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
          (relu): MinkowskiReLU()
        )
      )
      (layer5_): Sequential(
        (0): Bottleneck(
          (conv1): MinkowskiConvolution(in=128, out=128, kernel_size=[1, 1, 1], stride=[1, 1, 1], dilation=[1, 1, 1])
          (norm1): MinkowskiBatchNorm(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
          (conv2): MinkowskiConvolution(in=128, out=128, kernel_size=[3, 3, 3], stride=[1, 1, 1], dilation=[1, 1, 1])
          (norm2): MinkowskiBatchNorm(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
          (conv3): MinkowskiConvolution(in=128, out=256, kernel_size=[1, 1, 1], stride=[1, 1, 1], dilation=[1, 1, 1])
          (norm3): MinkowskiBatchNorm(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
          (relu): MinkowskiReLU()
          (downsample): Sequential(
            (0): MinkowskiConvolution(in=128, out=256, kernel_size=[1, 1, 1], stride=[1, 1, 1], dilation=[1, 1, 1])
            (1): MinkowskiBatchNorm(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
          )
        )
      )
      (layer5): Sequential(
        (0): Bottleneck(
          (conv1): MinkowskiConvolution(in=512, out=512, kernel_size=[1, 1, 1], stride=[1, 1, 1], dilation=[1, 1, 1])
          (norm1): MinkowskiBatchNorm(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
          (conv2): MinkowskiConvolution(in=512, out=512, kernel_size=[3, 3, 3], stride=[2, 2, 2], dilation=[1, 1, 1])
          (norm2): MinkowskiBatchNorm(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
          (conv3): MinkowskiConvolution(in=512, out=1024, kernel_size=[1, 1, 1], stride=[1, 1, 1], dilation=[1, 1, 1])
          (norm3): MinkowskiBatchNorm(1024, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
          (relu): MinkowskiReLU()
          (downsample): Sequential(
            (0): MinkowskiConvolution(in=512, out=1024, kernel_size=[1, 1, 1], stride=[2, 2, 2], dilation=[1, 1, 1])
            (1): MinkowskiBatchNorm(1024, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
          )
        )
      )
      (spp): DAPPM(
        (scale1): Sequential(
          (0): MinkowskiAvgPooling(kernel_size=[5, 5, 5], stride=[2, 2, 2], dilation=[1, 1, 1])
          (1): MinkowskiBatchNorm(1024, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
          (2): MinkowskiReLU()
          (3): MinkowskiConvolution(in=1024, out=128, kernel_size=[1, 1, 1], stride=[1, 1, 1], dilation=[1, 1, 1])
        )
        (scale2): Sequential(
          (0): MinkowskiAvgPooling(kernel_size=[9, 9, 9], stride=[4, 4, 4], dilation=[1, 1, 1])
          (1): MinkowskiBatchNorm(1024, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
          (2): MinkowskiReLU()
          (3): MinkowskiConvolution(in=1024, out=128, kernel_size=[1, 1, 1], stride=[1, 1, 1], dilation=[1, 1, 1])
        )
        (scale3): Sequential(
          (0): MinkowskiAvgPooling(kernel_size=[17, 17, 17], stride=[8, 8, 8], dilation=[1, 1, 1])
          (1): MinkowskiBatchNorm(1024, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
          (2): MinkowskiReLU()
          (3): MinkowskiConvolution(in=1024, out=128, kernel_size=[1, 1, 1], stride=[1, 1, 1], dilation=[1, 1, 1])
        )
        (scale4): Sequential(
          (0): MinkowskiAvgPooling(kernel_size=[33, 33, 33], stride=[16, 16, 16], dilation=[1, 1, 1])
          (1): MinkowskiBatchNorm(1024, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
          (2): MinkowskiReLU()
          (3): MinkowskiConvolution(in=1024, out=128, kernel_size=[1, 1, 1], stride=[1, 1, 1], dilation=[1, 1, 1])
        )
        (scale0): Sequential(
          (0): MinkowskiBatchNorm(1024, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
          (1): MinkowskiReLU()
          (2): MinkowskiConvolution(in=1024, out=128, kernel_size=[1, 1, 1], stride=[1, 1, 1], dilation=[1, 1, 1])
        )
        (process1): Sequential(
          (0): MinkowskiBatchNorm(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
          (1): MinkowskiReLU()
          (2): MinkowskiConvolution(in=128, out=128, kernel_size=[3, 3, 3], stride=[1, 1, 1], dilation=[1, 1, 1])
        )
        (process2): Sequential(
          (0): MinkowskiBatchNorm(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
          (1): MinkowskiReLU()
          (2): MinkowskiConvolution(in=128, out=128, kernel_size=[3, 3, 3], stride=[1, 1, 1], dilation=[1, 1, 1])
        )
        (process3): Sequential(
          (0): MinkowskiBatchNorm(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
          (1): MinkowskiReLU()
          (2): MinkowskiConvolution(in=128, out=128, kernel_size=[3, 3, 3], stride=[1, 1, 1], dilation=[1, 1, 1])
        )
        (process4): Sequential(
          (0): MinkowskiBatchNorm(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
          (1): MinkowskiReLU()
          (2): MinkowskiConvolution(in=128, out=128, kernel_size=[3, 3, 3], stride=[1, 1, 1], dilation=[1, 1, 1])
        )
        (compression): Sequential(
          (0): MinkowskiBatchNorm(640, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
          (1): MinkowskiReLU()
          (2): MinkowskiConvolution(in=640, out=256, kernel_size=[1, 1, 1], stride=[1, 1, 1], dilation=[1, 1, 1])
        )
        (shortcut): Sequential(
          (0): MinkowskiBatchNorm(1024, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
          (1): MinkowskiReLU()
          (2): MinkowskiConvolution(in=1024, out=256, kernel_size=[1, 1, 1], stride=[1, 1, 1], dilation=[1, 1, 1])
        )
      )
      (out): Sequential(
        (0): MinkowskiConvolutionTranspose(in=256, out=256, kernel_size=[2, 2, 2], stride=[2, 2, 2], dilation=[1, 1, 1])
        (1): MinkowskiBatchNorm(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
        (2): MinkowskiReLU()
        (3): MinkowskiConvolution(in=256, out=64, kernel_size=[1, 1, 1], stride=[1, 1, 1], dilation=[1, 1, 1])
        (4): MinkowskiBatchNorm(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
        (5): MinkowskiReLU()
      )
    )
    (map_to_bev_module): None
    (pfe): None
    (backbone_2d): None
    (dense_head): CAGroup3DHead(
      (loss_centerness): CrossEntropy()
      (loss_bbox): IoU3DLoss()
      (loss_cls): FocalLoss()
      (loss_sem): FocalLoss()
      (loss_offset): SmoothL1Loss()
      (offset_block): Sequential(
        (0): MinkowskiConvolution(in=64, out=64, kernel_size=[1, 1, 1], stride=[1, 1, 1], dilation=[1, 1, 1])
        (1): MinkowskiBatchNorm(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
        (2): MinkowskiELU()
        (3): MinkowskiConvolution(in=64, out=64, kernel_size=[1, 1, 1], stride=[1, 1, 1], dilation=[1, 1, 1])
        (4): MinkowskiBatchNorm(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
        (5): MinkowskiELU()
        (6): MinkowskiConvolution(in=64, out=9, kernel_size=[1, 1, 1], stride=[1, 1, 1], dilation=[1, 1, 1])
      )
      (feature_offset): Sequential(
        (0): MinkowskiConvolution(in=64, out=192, kernel_size=[3, 3, 3], stride=[1, 1, 1], dilation=[1, 1, 1])
        (1): MinkowskiBatchNorm(192, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
        (2): MinkowskiELU()
      )
      (semantic_conv): MinkowskiConvolution(in=64, out=10, kernel_size=[1, 1, 1], stride=[1, 1, 1], dilation=[1, 1, 1])
      (centerness_conv): MinkowskiConvolution(in=64, out=1, kernel_size=[1, 1, 1], stride=[1, 1, 1], dilation=[1, 1, 1])
      (reg_conv): MinkowskiConvolution(in=64, out=8, kernel_size=[1, 1, 1], stride=[1, 1, 1], dilation=[1, 1, 1])
      (cls_conv): MinkowskiConvolution(in=64, out=10, kernel_size=[1, 1, 1], stride=[1, 1, 1], dilation=[1, 1, 1])
      (scales): ModuleList(
        (0): Scale()
        (1): Scale()
        (2): Scale()
        (3): Scale()
        (4): Scale()
        (5): Scale()
        (6): Scale()
        (7): Scale()
        (8): Scale()
        (9): Scale()
      )
      (cls_individual_out): ModuleList(
        (0): Sequential(
          (0): MinkowskiConvolution(in=64, out=64, kernel_size=[9, 9, 9], stride=[1, 1, 1], dilation=[1, 1, 1])
          (1): MinkowskiBatchNorm(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
          (2): MinkowskiELU()
        )
        (1): Sequential(
          (0): MinkowskiConvolution(in=64, out=64, kernel_size=[9, 9, 9], stride=[1, 1, 1], dilation=[1, 1, 1])
          (1): MinkowskiBatchNorm(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
          (2): MinkowskiELU()
        )
        (2): Sequential(
          (0): MinkowskiConvolution(in=64, out=64, kernel_size=[9, 9, 9], stride=[1, 1, 1], dilation=[1, 1, 1])
          (1): MinkowskiBatchNorm(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
          (2): MinkowskiELU()
        )
        (3): Sequential(
          (0): MinkowskiConvolution(in=64, out=64, kernel_size=[9, 9, 9], stride=[1, 1, 1], dilation=[1, 1, 1])
          (1): MinkowskiBatchNorm(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
          (2): MinkowskiELU()
        )
        (4): Sequential(
          (0): MinkowskiConvolution(in=64, out=64, kernel_size=[9, 9, 9], stride=[1, 1, 1], dilation=[1, 1, 1])
          (1): MinkowskiBatchNorm(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
          (2): MinkowskiELU()
        )
        (5): Sequential(
          (0): MinkowskiConvolution(in=64, out=64, kernel_size=[9, 9, 9], stride=[1, 1, 1], dilation=[1, 1, 1])
          (1): MinkowskiBatchNorm(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
          (2): MinkowskiELU()
        )
        (6): Sequential(
          (0): MinkowskiConvolution(in=64, out=64, kernel_size=[9, 9, 9], stride=[1, 1, 1], dilation=[1, 1, 1])
          (1): MinkowskiBatchNorm(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
          (2): MinkowskiELU()
        )
        (7): Sequential(
          (0): MinkowskiConvolution(in=64, out=64, kernel_size=[9, 9, 9], stride=[1, 1, 1], dilation=[1, 1, 1])
          (1): MinkowskiBatchNorm(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
          (2): MinkowskiELU()
        )
        (8): Sequential(
          (0): MinkowskiConvolution(in=64, out=64, kernel_size=[9, 9, 9], stride=[1, 1, 1], dilation=[1, 1, 1])
          (1): MinkowskiBatchNorm(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
          (2): MinkowskiELU()
        )
        (9): Sequential(
          (0): MinkowskiConvolution(in=64, out=64, kernel_size=[9, 9, 9], stride=[1, 1, 1], dilation=[1, 1, 1])
          (1): MinkowskiBatchNorm(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
          (2): MinkowskiELU()
        )
      )
      (cls_individual_up): ModuleList(
        (0): ModuleList(
          (0): MinkowskiGenerativeConvolutionTranspose(in=64, out=64, kernel_size=[3, 3, 3], stride=[3, 3, 3], dilation=[1, 1, 1])
          (1): Sequential(
            (0): MinkowskiBatchNorm(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
            (1): MinkowskiELU()
          )
        )
        (1): ModuleList(
          (0): MinkowskiGenerativeConvolutionTranspose(in=64, out=64, kernel_size=[3, 3, 3], stride=[3, 3, 3], dilation=[1, 1, 1])
          (1): Sequential(
            (0): MinkowskiBatchNorm(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
            (1): MinkowskiELU()
          )
        )
        (2): ModuleList(
          (0): MinkowskiGenerativeConvolutionTranspose(in=64, out=64, kernel_size=[3, 3, 3], stride=[3, 3, 3], dilation=[1, 1, 1])
          (1): Sequential(
            (0): MinkowskiBatchNorm(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
            (1): MinkowskiELU()
          )
        )
        (3): ModuleList(
          (0): MinkowskiGenerativeConvolutionTranspose(in=64, out=64, kernel_size=[3, 3, 3], stride=[3, 3, 3], dilation=[1, 1, 1])
          (1): Sequential(
            (0): MinkowskiBatchNorm(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
            (1): MinkowskiELU()
          )
        )
        (4): ModuleList(
          (0): MinkowskiGenerativeConvolutionTranspose(in=64, out=64, kernel_size=[3, 3, 3], stride=[3, 3, 3], dilation=[1, 1, 1])
          (1): Sequential(
            (0): MinkowskiBatchNorm(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
            (1): MinkowskiELU()
          )
        )
        (5): ModuleList(
          (0): MinkowskiGenerativeConvolutionTranspose(in=64, out=64, kernel_size=[3, 3, 3], stride=[3, 3, 3], dilation=[1, 1, 1])
          (1): Sequential(
            (0): MinkowskiBatchNorm(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
            (1): MinkowskiELU()
          )
        )
        (6): ModuleList(
          (0): MinkowskiGenerativeConvolutionTranspose(in=64, out=64, kernel_size=[3, 3, 3], stride=[3, 3, 3], dilation=[1, 1, 1])
          (1): Sequential(
            (0): MinkowskiBatchNorm(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
            (1): MinkowskiELU()
          )
        )
        (7): ModuleList(
          (0): MinkowskiGenerativeConvolutionTranspose(in=64, out=64, kernel_size=[3, 3, 3], stride=[3, 3, 3], dilation=[1, 1, 1])
          (1): Sequential(
            (0): MinkowskiBatchNorm(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
            (1): MinkowskiELU()
          )
        )
        (8): ModuleList(
          (0): MinkowskiGenerativeConvolutionTranspose(in=64, out=64, kernel_size=[3, 3, 3], stride=[3, 3, 3], dilation=[1, 1, 1])
          (1): Sequential(
            (0): MinkowskiBatchNorm(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
            (1): MinkowskiELU()
          )
        )
        (9): ModuleList(
          (0): MinkowskiGenerativeConvolutionTranspose(in=64, out=64, kernel_size=[3, 3, 3], stride=[3, 3, 3], dilation=[1, 1, 1])
          (1): Sequential(
            (0): MinkowskiBatchNorm(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
            (1): MinkowskiELU()
          )
        )
      )
      (cls_individual_fuse): ModuleList(
        (0): Sequential(
          (0): MinkowskiConvolution(in=128, out=64, kernel_size=[1, 1, 1], stride=[1, 1, 1], dilation=[1, 1, 1])
          (1): MinkowskiBatchNorm(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
          (2): MinkowskiELU()
        )
        (1): Sequential(
          (0): MinkowskiConvolution(in=128, out=64, kernel_size=[1, 1, 1], stride=[1, 1, 1], dilation=[1, 1, 1])
          (1): MinkowskiBatchNorm(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
          (2): MinkowskiELU()
        )
        (2): Sequential(
          (0): MinkowskiConvolution(in=128, out=64, kernel_size=[1, 1, 1], stride=[1, 1, 1], dilation=[1, 1, 1])
          (1): MinkowskiBatchNorm(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
          (2): MinkowskiELU()
        )
        (3): Sequential(
          (0): MinkowskiConvolution(in=128, out=64, kernel_size=[1, 1, 1], stride=[1, 1, 1], dilation=[1, 1, 1])
          (1): MinkowskiBatchNorm(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
          (2): MinkowskiELU()
        )
        (4): Sequential(
          (0): MinkowskiConvolution(in=128, out=64, kernel_size=[1, 1, 1], stride=[1, 1, 1], dilation=[1, 1, 1])
          (1): MinkowskiBatchNorm(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
          (2): MinkowskiELU()
        )
        (5): Sequential(
          (0): MinkowskiConvolution(in=128, out=64, kernel_size=[1, 1, 1], stride=[1, 1, 1], dilation=[1, 1, 1])
          (1): MinkowskiBatchNorm(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
          (2): MinkowskiELU()
        )
        (6): Sequential(
          (0): MinkowskiConvolution(in=128, out=64, kernel_size=[1, 1, 1], stride=[1, 1, 1], dilation=[1, 1, 1])
          (1): MinkowskiBatchNorm(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
          (2): MinkowskiELU()
        )
        (7): Sequential(
          (0): MinkowskiConvolution(in=128, out=64, kernel_size=[1, 1, 1], stride=[1, 1, 1], dilation=[1, 1, 1])
          (1): MinkowskiBatchNorm(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
          (2): MinkowskiELU()
        )
        (8): Sequential(
          (0): MinkowskiConvolution(in=128, out=64, kernel_size=[1, 1, 1], stride=[1, 1, 1], dilation=[1, 1, 1])
          (1): MinkowskiBatchNorm(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
          (2): MinkowskiELU()
        )
        (9): Sequential(
          (0): MinkowskiConvolution(in=128, out=64, kernel_size=[1, 1, 1], stride=[1, 1, 1], dilation=[1, 1, 1])
          (1): MinkowskiBatchNorm(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
          (2): MinkowskiELU()
        )
      )
      (cls_individual_expand_out): ModuleList(
        (0): Sequential(
          (0): MinkowskiConvolution(in=64, out=64, kernel_size=[5, 5, 5], stride=[1, 1, 1], dilation=[1, 1, 1])
          (1): MinkowskiBatchNorm(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
          (2): MinkowskiELU()
        )
        (1): Sequential(
          (0): MinkowskiConvolution(in=64, out=64, kernel_size=[5, 5, 5], stride=[1, 1, 1], dilation=[1, 1, 1])
          (1): MinkowskiBatchNorm(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
          (2): MinkowskiELU()
        )
        (2): Sequential(
          (0): MinkowskiConvolution(in=64, out=64, kernel_size=[5, 5, 5], stride=[1, 1, 1], dilation=[1, 1, 1])
          (1): MinkowskiBatchNorm(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
          (2): MinkowskiELU()
        )
        (3): Sequential(
          (0): MinkowskiConvolution(in=64, out=64, kernel_size=[5, 5, 5], stride=[1, 1, 1], dilation=[1, 1, 1])
          (1): MinkowskiBatchNorm(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
          (2): MinkowskiELU()
        )
        (4): Sequential(
          (0): MinkowskiConvolution(in=64, out=64, kernel_size=[5, 5, 5], stride=[1, 1, 1], dilation=[1, 1, 1])
          (1): MinkowskiBatchNorm(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
          (2): MinkowskiELU()
        )
        (5): Sequential(
          (0): MinkowskiConvolution(in=64, out=64, kernel_size=[5, 5, 5], stride=[1, 1, 1], dilation=[1, 1, 1])
          (1): MinkowskiBatchNorm(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
          (2): MinkowskiELU()
        )
        (6): Sequential(
          (0): MinkowskiConvolution(in=64, out=64, kernel_size=[5, 5, 5], stride=[1, 1, 1], dilation=[1, 1, 1])
          (1): MinkowskiBatchNorm(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
          (2): MinkowskiELU()
        )
        (7): Sequential(
          (0): MinkowskiConvolution(in=64, out=64, kernel_size=[5, 5, 5], stride=[1, 1, 1], dilation=[1, 1, 1])
          (1): MinkowskiBatchNorm(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
          (2): MinkowskiELU()
        )
        (8): Sequential(
          (0): MinkowskiConvolution(in=64, out=64, kernel_size=[5, 5, 5], stride=[1, 1, 1], dilation=[1, 1, 1])
          (1): MinkowskiBatchNorm(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
          (2): MinkowskiELU()
        )
        (9): Sequential(
          (0): MinkowskiConvolution(in=64, out=64, kernel_size=[5, 5, 5], stride=[1, 1, 1], dilation=[1, 1, 1])
          (1): MinkowskiBatchNorm(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
          (2): MinkowskiELU()
        )
      )
    )
    (point_head): None
    (roi_head): CAGroup3DRoIHead(
      (iou_loss_computer): IoU3DLoss()
      (proposal_target_layer): ProposalTargetLayer()
      (reg_loss_func): WeightedSmoothL1Loss()
      (roi_grid_pool_layers): ModuleList(
        (0): SimplePoolingLayer(
          (grid_conv): MinkowskiConvolution(in=64, out=128, kernel_size=[5, 5, 5], stride=[1, 1, 1], dilation=[1, 1, 1])
          (grid_bn): MinkowskiBatchNorm(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
          (grid_relu): MinkowskiELU()
          (pooling_conv): MinkowskiConvolution(in=128, out=128, kernel_size=[7, 7, 7], stride=[1, 1, 1], dilation=[1, 1, 1])
          (pooling_bn): MinkowskiBatchNorm(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
        )
      )
      (reg_fc_layers): Sequential(
        (0): Linear(in_features=128, out_features=256, bias=False)
        (1): BatchNorm1d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
        (2): ReLU()
        (3): Dropout(p=0.3, inplace=False)
        (4): Linear(in_features=256, out_features=256, bias=False)
        (5): BatchNorm1d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
        (6): ReLU()
      )
      (reg_pred_layer): Linear(in_features=256, out_features=8, bias=True)
    )
  )
)
2023-04-02 18:47:18,392   INFO  **********************Start training sunrgbd_models/CAGroup3D(cagroup3d-win10-sunrgbd-train)**********************
2023-04-02 21:02:53,692   INFO  Epoch [13][  50]/[1322] : lr:  1.000e-05, sem_thr: 0.05, loss_centerness: 0.6623631048202515, loss_bbox: 0.35187224864959715, loss_cls: 0.18067386567592622, loss_sem: 0.27758967235684395, loss_vote: 0.11847812041640282, one_stage_loss: 1.5909770154953002, rcnn_loss_reg: 0.3226509618759155, rcnn_loss_iou: 0.37351417541503906, loss_two_stage: 0.6961651408672332, 
2023-04-02 23:14:58,782   INFO  Epoch [13][ 100]/[1322] : lr:  1.000e-05, sem_thr: 0.05, loss_centerness: 0.6630406963825226, loss_bbox: 0.35230674386024474, loss_cls: 0.1816549304127693, loss_sem: 0.22412991568446158, loss_vote: 0.11678819626569747, one_stage_loss: 1.5379204940795899, rcnn_loss_reg: 0.3200619313120842, rcnn_loss_iou: 0.3759835082292557, loss_two_stage: 0.6960454404354095, 
2023-04-03 01:31:22,578   INFO  Epoch [13][ 150]/[1322] : lr:  1.000e-05, sem_thr: 0.05, loss_centerness: 0.6641919124126434, loss_bbox: 0.34244911730289457, loss_cls: 0.17572991371154786, loss_sem: 0.164187930226326, loss_vote: 0.11165566861629486, one_stage_loss: 1.4582145309448242, rcnn_loss_reg: 0.3245995166897774, rcnn_loss_iou: 0.3702506846189499, loss_two_stage: 0.6948502039909363, 
2023-04-03 03:15:28,156   INFO  Epoch [13][ 200]/[1322] : lr:  1.000e-05, sem_thr: 0.05, loss_centerness: 0.661133303642273, loss_bbox: 0.3516665494441986, loss_cls: 0.1864103177189827, loss_sem: 0.19939401865005493, loss_vote: 0.12085840627551078, one_stage_loss: 1.5194626092910766, rcnn_loss_reg: 0.3308644261956215, rcnn_loss_iou: 0.37599210619926454, loss_two_stage: 0.7068565285205841, 
2023-04-03 04:48:30,413   INFO  Epoch [13][ 250]/[1322] : lr:  1.000e-05, sem_thr: 0.05, loss_centerness: 0.6646712601184845, loss_bbox: 0.34947874903678894, loss_cls: 0.18044402152299882, loss_sem: 0.14906390145421028, loss_vote: 0.11759307235479355, one_stage_loss: 1.4612509989738465, rcnn_loss_reg: 0.31861241459846495, rcnn_loss_iou: 0.3731016290187836, loss_two_stage: 0.6917140460014344, 
2023-04-03 06:21:26,423   INFO  Epoch [13][ 300]/[1322] : lr:  1.000e-05, sem_thr: 0.05, loss_centerness: 0.6643083465099334, loss_bbox: 0.3536418664455414, loss_cls: 0.17994892954826355, loss_sem: 0.1544986192882061, loss_vote: 0.11901766777038575, one_stage_loss: 1.4714154267311097, rcnn_loss_reg: 0.32731219202280043, rcnn_loss_iou: 0.376601088643074, loss_two_stage: 0.7039132845401764, 
2023-04-03 07:54:18,231   INFO  Epoch [13][ 350]/[1322] : lr:  1.000e-05, sem_thr: 0.05, loss_centerness: 0.6622652173042297, loss_bbox: 0.34778221607208254, loss_cls: 0.17725018173456192, loss_sem: 0.26385487884283065, loss_vote: 0.11609601065516471, one_stage_loss: 1.5672485136985779, rcnn_loss_reg: 0.3184669044613838, rcnn_loss_iou: 0.36683365106582644, loss_two_stage: 0.6853005504608154, 
2023-04-03 09:30:14,314   INFO  Epoch [13][ 400]/[1322] : lr:  1.000e-05, sem_thr: 0.05, loss_centerness: 0.661707843542099, loss_bbox: 0.35418744444847106, loss_cls: 0.18439087867736817, loss_sem: 0.25267973288893697, loss_vote: 0.11465635925531387, one_stage_loss: 1.5676222562789917, rcnn_loss_reg: 0.32181145310401915, rcnn_loss_iou: 0.37672561407089233, loss_two_stage: 0.6985370683670044, 
2023-04-03 11:03:56,627   INFO  Epoch [13][ 450]/[1322] : lr:  1.000e-05, sem_thr: 0.05, loss_centerness: 0.6624130165576935, loss_bbox: 0.35507028639316557, loss_cls: 0.18141891568899154, loss_sem: 0.1587126612663269, loss_vote: 0.11347746297717094, one_stage_loss: 1.4710923361778259, rcnn_loss_reg: 0.3236926472187042, rcnn_loss_iou: 0.37554241478443146, loss_two_stage: 0.6992350625991821, 
2023-04-03 12:35:12,815   INFO  Epoch [13][ 500]/[1322] : lr:  1.000e-05, sem_thr: 0.05, loss_centerness: 0.6629520893096924, loss_bbox: 0.3519792276620865, loss_cls: 0.17892935872077942, loss_sem: 0.17500929594039916, loss_vote: 0.11417005106806755, one_stage_loss: 1.483040030002594, rcnn_loss_reg: 0.3217777442932129, rcnn_loss_iou: 0.37734968066215513, loss_two_stage: 0.6991274237632752, 
2023-04-03 14:10:09,972   INFO  Epoch [13][ 550]/[1322] : lr:  1.000e-05, sem_thr: 0.05, loss_centerness: 0.6637387633323669, loss_bbox: 0.34735734045505523, loss_cls: 0.18063713282346724, loss_sem: 0.13179368287324905, loss_vote: 0.12056573927402496, one_stage_loss: 1.4440926504135132, rcnn_loss_reg: 0.33059713900089266, rcnn_loss_iou: 0.37435609817504883, loss_two_stage: 0.7049532413482666, 
2023-04-03 15:41:21,969   INFO  Epoch [13][ 600]/[1322] : lr:  1.000e-05, sem_thr: 0.05, loss_centerness: 0.662292810678482, loss_bbox: 0.35720852434635164, loss_cls: 0.17849652022123336, loss_sem: 0.12923728227615355, loss_vote: 0.11629633039236069, one_stage_loss: 1.4435314631462097, rcnn_loss_reg: 0.3326093548536301, rcnn_loss_iou: 0.37626142144203184, loss_two_stage: 0.7088707709312438, 
2023-04-03 17:11:28,683   INFO  Epoch [13][ 650]/[1322] : lr:  1.000e-05, sem_thr: 0.05, loss_centerness: 0.6618774938583374, loss_bbox: 0.35374693453311923, loss_cls: 0.18276749283075333, loss_sem: 0.144855744689703, loss_vote: 0.11687358900904656, one_stage_loss: 1.460121262073517, rcnn_loss_reg: 0.32241543173789977, rcnn_loss_iou: 0.3724362623691559, loss_two_stage: 0.6948516941070557, 
2023-04-03 18:44:33,632   INFO  Epoch [13][ 700]/[1322] : lr:  1.000e-05, sem_thr: 0.05, loss_centerness: 0.6633472311496734, loss_bbox: 0.35507338523864745, loss_cls: 0.1834974604845047, loss_sem: 0.16129221200942992, loss_vote: 0.11933488368988038, one_stage_loss: 1.482545187473297, rcnn_loss_reg: 0.32722929924726485, rcnn_loss_iou: 0.37687767803668976, loss_two_stage: 0.7041069781780243, 
2023-04-03 20:14:36,146   INFO  Epoch [13][ 750]/[1322] : lr:  1.000e-05, sem_thr: 0.05, loss_centerness: 0.6644761955738068, loss_bbox: 0.35398071110248563, loss_cls: 0.18030155092477798, loss_sem: 0.17029531091451644, loss_vote: 0.11823550701141357, one_stage_loss: 1.4872892904281616, rcnn_loss_reg: 0.33191990315914155, rcnn_loss_iou: 0.37786650359630586, loss_two_stage: 0.7097864115238189, 
2023-04-03 21:43:57,721   INFO  Epoch [13][ 800]/[1322] : lr:  1.000e-05, sem_thr: 0.05, loss_centerness: 0.6641488337516784, loss_bbox: 0.3623661398887634, loss_cls: 0.17759602785110473, loss_sem: 0.13985075324773788, loss_vote: 0.12048821434378625, one_stage_loss: 1.4644499826431274, rcnn_loss_reg: 0.32571767300367355, rcnn_loss_iou: 0.37867982625961305, loss_two_stage: 0.7043974995613098, 
2023-04-03 23:14:42,693   INFO  Epoch [13][ 850]/[1322] : lr:  1.000e-05, sem_thr: 0.05, loss_centerness: 0.6634637904167175, loss_bbox: 0.3510202074050903, loss_cls: 0.1817261689901352, loss_sem: 0.17562781766057015, loss_vote: 0.11219386965036392, one_stage_loss: 1.4840318632125855, rcnn_loss_reg: 0.3145780658721924, rcnn_loss_iou: 0.3710771632194519, loss_two_stage: 0.6856552314758301, 
2023-04-04 00:46:57,991   INFO  Epoch [13][ 900]/[1322] : lr:  1.000e-05, sem_thr: 0.05, loss_centerness: 0.6604310703277588, loss_bbox: 0.35609620809555054, loss_cls: 0.18157291144132615, loss_sem: 0.17424873754382134, loss_vote: 0.1169225138425827, one_stage_loss: 1.4892714548110961, rcnn_loss_reg: 0.3271025702357292, rcnn_loss_iou: 0.37567222356796265, loss_two_stage: 0.7027747964859009, 
2023-04-04 02:46:38,860   INFO  Epoch [13][ 950]/[1322] : lr:  1.000e-05, sem_thr: 0.05, loss_centerness: 0.6638546955585479, loss_bbox: 0.34598992109298704, loss_cls: 0.17896713733673095, loss_sem: 0.14396111875772477, loss_vote: 0.11255239754915237, one_stage_loss: 1.445325255393982, rcnn_loss_reg: 0.3274132317304611, rcnn_loss_iou: 0.37157038986682894, loss_two_stage: 0.69898362159729, 
2023-04-04 05:08:44,516   INFO  Epoch [13][1000]/[1322] : lr:  1.000e-05, sem_thr: 0.05, loss_centerness: 0.6622758531570434, loss_bbox: 0.3549597650766373, loss_cls: 0.17880465477705001, loss_sem: 0.16847254008054732, loss_vote: 0.11574765816330909, one_stage_loss: 1.4802604627609253, rcnn_loss_reg: 0.32289525389671325, rcnn_loss_iou: 0.3747403818368912, loss_two_stage: 0.6976356363296509, 
2023-04-04 07:33:09,320   INFO  Epoch [13][1050]/[1322] : lr:  1.000e-05, sem_thr: 0.05, loss_centerness: 0.6620133376121521, loss_bbox: 0.3527708554267883, loss_cls: 0.17823042571544648, loss_sem: 0.13636301800608636, loss_vote: 0.11551862224936485, one_stage_loss: 1.444896252155304, rcnn_loss_reg: 0.3306643870472908, rcnn_loss_iou: 0.38059409976005554, loss_two_stage: 0.7112584865093231, 
2023-04-04 09:58:58,318   INFO  Epoch [13][1100]/[1322] : lr:  1.000e-05, sem_thr: 0.05, loss_centerness: 0.6630631291866302, loss_bbox: 0.34507942259311675, loss_cls: 0.1765292030572891, loss_sem: 0.17366553276777266, loss_vote: 0.11843317538499833, one_stage_loss: 1.476770441532135, rcnn_loss_reg: 0.32106285572052, rcnn_loss_iou: 0.3712770110368729, loss_two_stage: 0.6923398649692536, 
2023-04-04 11:50:03,203   INFO  Epoch [13][1150]/[1322] : lr:  1.000e-05, sem_thr: 0.05, loss_centerness: 0.6624673461914062, loss_bbox: 0.35551845014095307, loss_cls: 0.18390144944190978, loss_sem: 0.1476328657567501, loss_vote: 0.11500328212976456, one_stage_loss: 1.4645233917236329, rcnn_loss_reg: 0.3294647446274757, rcnn_loss_iou: 0.3782592761516571, loss_two_stage: 0.7077240252494812, 
2023-04-04 13:20:31,850   INFO  Epoch [13][1200]/[1322] : lr:  1.000e-05, sem_thr: 0.05, loss_centerness: 0.663930526971817, loss_bbox: 0.35358040988445283, loss_cls: 0.17962905526161194, loss_sem: 0.1480906042456627, loss_vote: 0.11691673502326011, one_stage_loss: 1.462147331237793, rcnn_loss_reg: 0.31809635043144224, rcnn_loss_iou: 0.3736869865655899, loss_two_stage: 0.6917833364009858, 
2023-04-04 14:50:35,089   INFO  Epoch [13][1250]/[1322] : lr:  1.000e-05, sem_thr: 0.05, loss_centerness: 0.6616610872745514, loss_bbox: 0.3473211169242859, loss_cls: 0.17929236128926276, loss_sem: 0.13846698969602586, loss_vote: 0.10878140345215798, one_stage_loss: 1.435522973537445, rcnn_loss_reg: 0.3105960166454315, rcnn_loss_iou: 0.36950829446315764, loss_two_stage: 0.6801043093204499, 
2023-04-04 16:20:45,500   INFO  Epoch [13][1300]/[1322] : lr:  1.000e-05, sem_thr: 0.05, loss_centerness: 0.6631780481338501, loss_bbox: 0.35142988979816436, loss_cls: 0.18354893177747728, loss_sem: 0.1891991038620472, loss_vote: 0.10815204933285713, one_stage_loss: 1.4955080199241637, rcnn_loss_reg: 0.3235346841812134, rcnn_loss_iou: 0.3715806418657303, loss_two_stage: 0.6951153266429901, 
2023-04-04 16:58:46,259   INFO  **********************End training sunrgbd_models/CAGroup3D(cagroup3d-win10-sunrgbd-train)**********************



2023-04-04 16:58:46,261   INFO  **********************Start evaluation sunrgbd_models/CAGroup3D(cagroup3d-win10-sunrgbd-train)**********************
2023-04-04 16:58:46,262   INFO  Loading SUNRGBD dataset
2023-04-04 16:58:46,521   INFO  Total samples for SUNRGBD dataset: 5050
2023-04-04 16:58:46,528   INFO  ==> Loading parameters from checkpoint C:\PINKAMENA\CITYU\CS5182\proj\CAGroup3D\output\sunrgbd_models\CAGroup3D\cagroup3d-win10-sunrgbd-train\ckpt\checkpoint_epoch_13.pth to CPU
2023-04-04 16:58:47,139   INFO  ==> Checkpoint trained from version: pcdet+0.5.2+18bc5f5+py9059037
2023-04-04 16:58:47,218   INFO  ==> Done (loaded 638/638)
2023-04-04 16:58:47,318   INFO  *************** EPOCH 13 EVALUATION *****************