PrDiMP_resnet18在运行第42个epoch时报错

[train: 42, 608 / 1625] FPS: 12.0 (24.0)  ,  Loss/total: 4.10781  ,  Loss/bb_ce: -4.89841  ,  ClfTrain/clf_ce: 2.74648
[train: 42, 609 / 1625] FPS: 11.9 (2.2)  ,  Loss/total: 4.10778  ,  Loss/bb_ce: -4.89871  ,  ClfTrain/clf_ce: 2.74647
[train: 42, 610 / 1625] FPS: 11.9 (25.2)  ,  Loss/total: 4.10810  ,  Loss/bb_ce: -4.89825  ,  ClfTrain/clf_ce: 2.74668
[train: 42, 611 / 1625] FPS: 11.9 (23.8)  ,  Loss/total: 4.10796  ,  Loss/bb_ce: -4.89845  ,  ClfTrain/clf_ce: 2.74659
[train: 42, 612 / 1625] FPS: 11.9 (11.8)  ,  Loss/total: 4.10793  ,  Loss/bb_ce: -4.89852  ,  ClfTrain/clf_ce: 2.74657
[train: 42, 613 / 1625] FPS: 11.9 (24.2)  ,  Loss/total: 4.10796  ,  Loss/bb_ce: -4.89906  ,  ClfTrain/clf_ce: 2.74659
[train: 42, 614 / 1625] FPS: 11.9 (25.6)  ,  Loss/total: 4.10799  ,  Loss/bb_ce: -4.89836  ,  ClfTrain/clf_ce: 2.74661
[train: 42, 615 / 1625] FPS: 12.0 (24.8)  ,  Loss/total: 4.10789  ,  Loss/bb_ce: -4.89866  ,  ClfTrain/clf_ce: 2.74655
[train: 42, 616 / 1625] FPS: 12.0 (25.2)  ,  Loss/total: 4.10779  ,  Loss/bb_ce: -4.89896  ,  ClfTrain/clf_ce: 2.74648
[train: 42, 617 / 1625] FPS: 11.9 (1.9)  ,  Loss/total: 4.10789  ,  Loss/bb_ce: -4.89892  ,  ClfTrain/clf_ce: 2.74654
[train: 42, 618 / 1625] FPS: 11.9 (25.3)  ,  Loss/total: 4.10796  ,  Loss/bb_ce: -4.89785  ,  ClfTrain/clf_ce: 2.74659
[train: 42, 619 / 1625] FPS: 11.9 (25.0)  ,  Loss/total: 4.10790  ,  Loss/bb_ce: -4.89824  ,  ClfTrain/clf_ce: 2.74656
[train: 42, 620 / 1625] FPS: 11.9 (23.6)  ,  Loss/total: 4.10785  ,  Loss/bb_ce: -4.89873  ,  ClfTrain/clf_ce: 2.74652
[train: 42, 621 / 1625] FPS: 11.9 (26.3)  ,  Loss/total: 4.10821  ,  Loss/bb_ce: -4.89872  ,  ClfTrain/clf_ce: 2.74676
[train: 42, 622 / 1625] FPS: 11.9 (25.4)  ,  Loss/total: 4.10825  ,  Loss/bb_ce: -4.89827  ,  ClfTrain/clf_ce: 2.74679
[train: 42, 623 / 1625] FPS: 11.9 (25.0)  ,  Loss/total: 4.10829  ,  Loss/bb_ce: -4.89822  ,  ClfTrain/clf_ce: 2.74682
[train: 42, 624 / 1625] FPS: 11.9 (26.1)  ,  Loss/total: 4.10812  ,  Loss/bb_ce: -4.89818  ,  ClfTrain/clf_ce: 2.74670
[train: 42, 625 / 1625] FPS: 11.7 (0.9)  ,  Loss/total: 4.10822  ,  Loss/bb_ce: -4.89837  ,  ClfTrain/clf_ce: 2.74676
[train: 42, 626 / 1625] FPS: 11.7 (23.6)  ,  Loss/total: 4.10817  ,  Loss/bb_ce: -4.89851  ,  ClfTrain/clf_ce: 2.74673
[train: 42, 627 / 1625] FPS: 11.7 (23.6)  ,  Loss/total: 4.10806  ,  Loss/bb_ce: -4.89896  ,  ClfTrain/clf_ce: 2.74665
[train: 42, 628 / 1625] FPS: 11.7 (23.9)  ,  Loss/total: 4.10794  ,  Loss/bb_ce: -4.89961  ,  ClfTrain/clf_ce: 2.74657
[train: 42, 629 / 1625] FPS: 11.7 (24.5)  ,  Loss/total: 4.10813  ,  Loss/bb_ce: -4.89971  ,  ClfTrain/clf_ce: 2.74669
[train: 42, 630 / 1625] FPS: 11.7 (24.9)  ,  Loss/total: 4.10807  ,  Loss/bb_ce: -4.90027  ,  ClfTrain/clf_ce: 2.74665
[train: 42, 631 / 1625] FPS: 11.8 (25.4)  ,  Loss/total: 4.10797  ,  Loss/bb_ce: -4.89984  ,  ClfTrain/clf_ce: 2.74659
[train: 42, 632 / 1625] FPS: 11.8 (25.2)  ,  Loss/total: 4.10791  ,  Loss/bb_ce: -4.90022  ,  ClfTrain/clf_ce: 2.74655
Training crashed at epoch 42
Traceback for the error!
Traceback (most recent call last):
  File "/media/zhuzhu/23227915-deb6-45d3-8d7d-7070283de100/zhuzhu/SOT/ATOM/pytracking-master/ltr/trainers/base_trainer.py", line 70, in train
    self.train_epoch()
  File "/media/zhuzhu/23227915-deb6-45d3-8d7d-7070283de100/zhuzhu/SOT/ATOM/pytracking-master/ltr/trainers/ltr_trainer.py", line 80, in train_epoch
    self.cycle_dataset(loader)
  File "/media/zhuzhu/23227915-deb6-45d3-8d7d-7070283de100/zhuzhu/SOT/ATOM/pytracking-master/ltr/trainers/ltr_trainer.py", line 55, in cycle_dataset
    data = data.to(self.device)
  File "/media/zhuzhu/23227915-deb6-45d3-8d7d-7070283de100/zhuzhu/SOT/ATOM/pytracking-master/pytracking/libs/tensordict.py", line 24, in apply_attr
    return TensorDict({n: getattr(e, name)(*args, **kwargs) if hasattr(e, name) else e for n, e in self.items()})
  File "/media/zhuzhu/23227915-deb6-45d3-8d7d-7070283de100/zhuzhu/SOT/ATOM/pytracking-master/pytracking/libs/tensordict.py", line 24, in <dictcomp>
    return TensorDict({n: getattr(e, name)(*args, **kwargs) if hasattr(e, name) else e for n, e in self.items()})
RuntimeError: CUDA error: unspecified launch failure
Restarting training from last epoch ...
Training crashed at epoch 42
Traceback for the error!
Traceback (most recent call last):
  File "/media/zhuzhu/23227915-deb6-45d3-8d7d-7070283de100/zhuzhu/SOT/ATOM/pytracking-master/ltr/trainers/base_trainer.py", line 65, in train
    self.load_checkpoint()
  File "/media/zhuzhu/23227915-deb6-45d3-8d7d-7070283de100/zhuzhu/SOT/ATOM/pytracking-master/ltr/trainers/base_trainer.py", line 190, in load_checkpoint
    net.load_state_dict(checkpoint_dict[key])
  File "/home/zhuzhu/anaconda3/envs/pytracking/lib/python3.7/site-packages/torch/nn/modules/module.py", line 830, in load_state_dict
    self.__class__.__name__, "\n\t".join(error_msgs)))
RuntimeError: Error(s) in loading state_dict for DiMPnet:
	While copying the parameter named "feature_extractor.conv1.weight", whose dimensions in the model are torch.Size([64, 3, 7, 7]) and whose dimensions in the checkpoint are torch.Size([64, 3, 7, 7]).
	While copying the parameter named "feature_extractor.bn1.weight", whose dimensions in the model are torch.Size([64]) and whose dimensions in the checkpoint are torch.Size([64]).
	While copying the parameter named "feature_extractor.bn1.bias", whose dimensions in the model are torch.Size([64]) and whose dimensions in the checkpoint are torch.Size([64]).
	While copying the parameter named "feature_extractor.bn1.running_mean", whose dimensions in the model are torch.Size([64]) and whose dimensions in the checkpoint are torch.Size([64]).
	While copying the parameter named "feature_extractor.bn1.running_var", whose dimensions in the model are torch.Size([64]) and whose dimensions in the checkpoint are torch.Size([64]).
	While copying the parameter named "feature_extractor.bn1.num_batches_tracked", whose dimensions in the model are torch.Size([]) and whose dimensions in the checkpoint are torch.Size([]).
	While copying the parameter named "feature_extractor.layer1.0.conv1.weight", whose dimensions in the model are torch.Size([64, 64, 3, 3]) and whose dimensions in the checkpoint are torch.Size([64, 64, 3, 3]).
	While copying the parameter named "feature_extractor.layer1.0.bn1.weight", whose dimensions in the model are torch.Size([64]) and whose dimensions in the checkpoint are torch.Size([64]).
	While copying the parameter named "feature_extractor.layer1.0.bn1.bias", whose dimensions in the model are torch.Size([64]) and whose dimensions in the checkpoint are torch.Size([64]).
	While copying the parameter named "feature_extractor.layer1.0.bn1.running_mean", whose dimensions in the model are torch.Size([64]) and whose dimensions in the checkpoint are torch.Size([64]).
	While copying the parameter named "feature_extractor.layer1.0.bn1.running_var", whose dimensions in the model are torch.Size([64]) and whose dimensions in the checkpoint are torch.Size([64]).
	While copying the parameter named "feature_extractor.layer1.0.bn1.num_batches_tracked", whose dimensions in the model are torch.Size([]) and whose dimensions in the checkpoint are torch.Size([]).
	While copying the parameter named "feature_extractor.layer1.0.conv2.weight", whose dimensions in the model are torch.Size([64, 64, 3, 3]) and whose dimensions in the checkpoint are torch.Size([64, 64, 3, 3]).
	While copying the parameter named "feature_extractor.layer1.0.bn2.weight", whose dimensions in the model are torch.Size([64]) and whose dimensions in the checkpoint are torch.Size([64]).
	While copying the parameter named "feature_extractor.layer1.0.bn2.bias", whose dimensions in the model are torch.Size([64]) and whose dimensions in the checkpoint are torch.Size([64]).
	While copying the parameter named "feature_extractor.layer1.0.bn2.running_mean", whose dimensions in the model are torch.Size([64]) and whose dimensions in the checkpoint are torch.Size([64]).
	While copying the parameter named "feature_extractor.layer1.0.bn2.running_var", whose dimensions in the model are torch.Size([64]) and whose dimensions in the checkpoint are torch.Size([64]).
	While copying the parameter named "feature_extractor.layer1.0.bn2.num_batches_tracked", whose dimensions in the model are torch.Size([]) and whose dimensions in the checkpoint are torch.Size([]).
	While copying the parameter named "feature_extractor.layer1.1.conv1.weight", whose dimensions in the model are torch.Size([64, 64, 3, 3]) and whose dimensions in the checkpoint are torch.Size([64, 64, 3, 3]).
	While copying the parameter named "feature_extractor.layer1.1.bn1.weight", whose dimensions in the model are torch.Size([64]) and whose dimensions in the checkpoint are torch.Size([64]).
	While copying the parameter named "feature_extractor.layer1.1.bn1.bias", whose dimensions in the model are torch.Size([64]) and whose dimensions in the checkpoint are torch.Size([64]).
	While copying the parameter named "feature_extractor.layer1.1.bn1.running_mean", whose dimensions in the model are torch.Size([64]) and whose dimensions in the checkpoint are torch.Size([64]).
	While copying the parameter named "feature_extractor.layer1.1.bn1.running_var", whose dimensions in the model are torch.Size([64]) and whose dimensions in the checkpoint are torch.Size([64]).
	While copying the parameter named "feature_extractor.layer1.1.bn1.num_batches_tracked", whose dimensions in the model are torch.Size([]) and whose dimensions in the checkpoint are torch.Size([]).
	While copying the parameter named "feature_extractor.layer1.1.conv2.weight", whose dimensions in the model are torch.Size([64, 64, 3, 3]) and whose dimensions in the checkpoint are torch.Size([64, 64, 3, 3]).
	While copying the parameter named "feature_extractor.layer1.1.bn2.weight", whose dimensions in the model are torch.Size([64]) and whose dimensions in the checkpoint are torch.Size([64]).
	While copying the parameter named "feature_extractor.layer1.1.bn2.bias", whose dimensions in the model are torch.Size([64]) and whose dimensions in the checkpoint are torch.Size([64]).
	While copying the parameter named "feature_extractor.layer1.1.bn2.running_mean", whose dimensions in the model are torch.Size([64]) and whose dimensions in the checkpoint are torch.Size([64]).
	While copying the parameter named "feature_extractor.layer1.1.bn2.running_var", whose dimensions in the model are torch.Size([64]) and whose dimensions in the checkpoint are torch.Size([64]).
	While copying the parameter named "feature_extractor.layer1.1.bn2.num_batches_tracked", whose dimensions in the model are torch.Size([]) and whose dimensions in the checkpoint are torch.Size([]).
	While copying the parameter named "feature_extractor.layer2.0.conv1.weight", whose dimensions in the model are torch.Size([128, 64, 3, 3]) and whose dimensions in the checkpoint are torch.Size([128, 64, 3, 3]).
	While copying the parameter named "feature_extractor.layer2.0.bn1.weight", whose dimensions in the model are torch.Size([128]) and whose dimensions in the checkpoint are torch.Size([128]).
	While copying the parameter named "feature_extractor.layer2.0.bn1.bias", whose dimensions in the model are torch.Size([128]) and whose dimensions in the checkpoint are torch.Size([128]).
	While copying the parameter named "feature_extractor.layer2.0.bn1.running_mean", whose dimensions in the model are torch.Size([128]) and whose dimensions in the checkpoint are torch.Size([128]).
	While copying the parameter named "feature_extractor.layer2.0.bn1.running_var", whose dimensions in the model are torch.Size([128]) and whose dimensions in the checkpoint are torch.Size([128]).
	While copying the parameter named "feature_extractor.layer2.0.bn1.num_batches_tracked", whose dimensions in the model are torch.Size([]) and whose dimensions in the checkpoint are torch.Size([]).
	While copying the parameter named "feature_extractor.layer2.0.conv2.weight", whose dimensions in the model are torch.Size([128, 128, 3, 3]) and whose dimensions in the checkpoint are torch.Size([128, 128, 3, 3]).
	While copying the parameter named "feature_extractor.layer2.0.bn2.weight", whose dimensions in the model are torch.Size([128]) and whose dimensions in the checkpoint are torch.Size([128]).
	While copying the parameter named "feature_extractor.layer2.0.bn2.bias", whose dimensions in the model are torch.Size([128]) and whose dimensions in the checkpoint are torch.Size([128]).
	While copying the parameter named "feature_extractor.layer2.0.bn2.running_mean", whose dimensions in the model are torch.Size([128]) and whose dimensions in the checkpoint are torch.Size([128]).
	While copying the parameter named "feature_extractor.layer2.0.bn2.running_var", whose dimensions in the model are torch.Size([128]) and whose dimensions in the checkpoint are torch.Size([128]).
	While copying the parameter named "feature_extractor.layer2.0.bn2.num_batches_tracked", whose dimensions in the model are torch.Size([]) and whose dimensions in the checkpoint are torch.Size([]).
	While copying the parameter named "feature_extractor.layer2.0.downsample.0.weight", whose dimensions in the model are torch.Size([128, 64, 1, 1]) and whose dimensions in the checkpoint are torch.Size([128, 64, 1, 1]).
	While copying the parameter named "feature_extractor.layer2.0.downsample.1.weight", whose dimensions in the model are torch.Size([128]) and whose dimensions in the checkpoint are torch.Size([128]).
	While copying the parameter named "feature_extractor.layer2.0.downsample.1.bias", whose dimensions in the model are torch.Size([128]) and whose dimensions in the checkpoint are torch.Size([128]).
	While copying the parameter named "feature_extractor.layer2.0.downsample.1.running_mean", whose dimensions in the model are torch.Size([128]) and whose dimensions in the checkpoint are torch.Size([128]).
	While copying the parameter named "feature_extractor.layer2.0.downsample.1.running_var", whose dimensions in the model are torch.Size([128]) and whose dimensions in the checkpoint are torch.Size([128]).
	While copying the parameter named "feature_extractor.layer2.0.downsample.1.num_batches_tracked", whose dimensions in the model are torch.Size([]) and whose dimensions in the checkpoint are torch.Size([]).
	While copying the parameter named "feature_extractor.layer2.1.conv1.weight", whose dimensions in the model are torch.Size([128, 128, 3, 3]) and whose dimensions in the checkpoint are torch.Size([128, 128, 3, 3]).
	While copying the parameter named "feature_extractor.layer2.1.bn1.weight", whose dimensions in the model are torch.Size([128]) and whose dimensions in the checkpoint are torch.Size([128]).
	While copying the parameter named "feature_extractor.layer2.1.bn1.bias", whose dimensions in the model are torch.Size([128]) and whose dimensions in the checkpoint are torch.Size([128]).
	While copying the parameter named "feature_extractor.layer2.1.bn1.running_mean", whose dimensions in the model are torch.Size([128]) and whose dimensions in the checkpoint are torch.Size([128]).
	While copying the parameter named "feature_extractor.layer2.1.bn1.running_var", whose dimensions in the model are torch.Size([128]) and whose dimensions in the checkpoint are torch.Size([128]).
	While copying the parameter named "feature_extractor.layer2.1.bn1.num_batches_tracked", whose dimensions in the model are torch.Size([]) and whose dimensions in the checkpoint are torch.Size([]).
	While copying the parameter named "feature_extractor.layer2.1.conv2.weight", whose dimensions in the model are torch.Size([128, 128, 3, 3]) and whose dimensions in the checkpoint are torch.Size([128, 128, 3, 3]).
	While copying the parameter named "feature_extractor.layer2.1.bn2.weight", whose dimensions in the model are torch.Size([128]) and whose dimensions in the checkpoint are torch.Size([128]).
	While copying the parameter named "feature_extractor.layer2.1.bn2.bias", whose dimensions in the model are torch.Size([128]) and whose dimensions in the checkpoint are torch.Size([128]).
	While copying the parameter named "feature_extractor.layer2.1.bn2.running_mean", whose dimensions in the model are torch.Size([128]) and whose dimensions in the checkpoint are torch.Size([128]).
	While copying the parameter named "feature_extractor.layer2.1.bn2.running_var", whose dimensions in the model are torch.Size([128]) and whose dimensions in the checkpoint are torch.Size([128]).
	While copying the parameter named "feature_extractor.layer2.1.bn2.num_batches_tracked", whose dimensions in the model are torch.Size([]) and whose dimensions in the checkpoint are torch.Size([]).
	While copying the parameter named "feature_extractor.layer3.0.conv1.weight", whose dimensions in the model are torch.Size([256, 128, 3, 3]) and whose dimensions in the checkpoint are torch.Size([256, 128, 3, 3]).
	While copying the parameter named "feature_extractor.layer3.0.bn1.weight", whose dimensions in the model are torch.Size([256]) and whose dimensions in the checkpoint are torch.Size([256]).
	While copying the parameter named "feature_extractor.layer3.0.bn1.bias", whose dimensions in the model are torch.Size([256]) and whose dimensions in the checkpoint are torch.Size([256]).
	While copying the parameter named "feature_extractor.layer3.0.bn1.running_mean", whose dimensions in the model are torch.Size([256]) and whose dimensions in the checkpoint are torch.Size([256]).
	While copying the parameter named "feature_extractor.layer3.0.bn1.running_var", whose dimensions in the model are torch.Size([256]) and whose dimensions in the checkpoint are torch.Size([256]).
	While copying the parameter named "feature_extractor.layer3.0.bn1.num_batches_tracked", whose dimensions in the model are torch.Size([]) and whose dimensions in the checkpoint are torch.Size([]).
	While copying the parameter named "feature_extractor.layer3.0.conv2.weight", whose dimensions in the model are torch.Size([256, 256, 3, 3]) and whose dimensions in the checkpoint are torch.Size([256, 256, 3, 3]).
	While copying the parameter named "feature_extractor.layer3.0.bn2.weight", whose dimensions in the model are torch.Size([256]) and whose dimensions in the checkpoint are torch.Size([256]).
	While copying the parameter named "feature_extractor.layer3.0.bn2.bias", whose dimensions in the model are torch.Size([256]) and whose dimensions in the checkpoint are torch.Size([256]).
	While copying the parameter named "feature_extractor.layer3.0.bn2.running_mean", whose dimensions in the model are torch.Size([256]) and whose dimensions in the checkpoint are torch.Size([256]).
	While copying the parameter named "feature_extractor.layer3.0.bn2.running_var", whose dimensions in the model are torch.Size([256]) and whose dimensions in the checkpoint are torch.Size([256]).
	While copying the parameter named "feature_extractor.layer3.0.bn2.num_batches_tracked", whose dimensions in the model are torch.Size([]) and whose dimensions in the checkpoint are torch.Size([]).
	While copying the parameter named "feature_extractor.layer3.0.downsample.0.weight", whose dimensions in the model are torch.Size([256, 128, 1, 1]) and whose dimensions in the checkpoint are torch.Size([256, 128, 1, 1]).
	While copying the parameter named "feature_extractor.layer3.0.downsample.1.weight", whose dimensions in the model are torch.Size([256]) and whose dimensions in the checkpoint are torch.Size([256]).
	While copying the parameter named "feature_extractor.layer3.0.downsample.1.bias", whose dimensions in the model are torch.Size([256]) and whose dimensions in the checkpoint are torch.Size([256]).
	While copying the parameter named "feature_extractor.layer3.0.downsample.1.running_mean", whose dimensions in the model are torch.Size([256]) and whose dimensions in the checkpoint are torch.Size([256]).
	While copying the parameter named "feature_extractor.layer3.0.downsample.1.running_var", whose dimensions in the model are torch.Size([256]) and whose dimensions in the checkpoint are torch.Size([256]).
	While copying the parameter named "feature_extractor.layer3.0.downsample.1.num_batches_tracked", whose dimensions in the model are torch.Size([]) and whose dimensions in the checkpoint are torch.Size([]).
	While copying the parameter named "feature_extractor.layer3.1.conv1.weight", whose dimensions in the model are torch.Size([256, 256, 3, 3]) and whose dimensions in the checkpoint are torch.Size([256, 256, 3, 3]).
	While copying the parameter named "feature_extractor.layer3.1.bn1.weight", whose dimensions in the model are torch.Size([256]) and whose dimensions in the checkpoint are torch.Size([256]).
	While copying the parameter named "feature_extractor.layer3.1.bn1.bias", whose dimensions in the model are torch.Size([256]) and whose dimensions in the checkpoint are torch.Size([256]).
	While copying the parameter named "feature_extractor.layer3.1.bn1.running_mean", whose dimensions in the model are torch.Size([256]) and whose dimensions in the checkpoint are torch.Size([256]).
	While copying the parameter named "feature_extractor.layer3.1.bn1.running_var", whose dimensions in the model are torch.Size([256]) and whose dimensions in the checkpoint are torch.Size([256]).
	While copying the parameter named "feature_extractor.layer3.1.bn1.num_batches_tracked", whose dimensions in the model are torch.Size([]) and whose dimensions in the checkpoint are torch.Size([]).
	While copying the parameter named "feature_extractor.layer3.1.conv2.weight", whose dimensions in the model are torch.Size([256, 256, 3, 3]) and whose dimensions in the checkpoint are torch.Size([256, 256, 3, 3]).
	While copying the parameter named "feature_extractor.layer3.1.bn2.weight", whose dimensions in the model are torch.Size([256]) and whose dimensions in the checkpoint are torch.Size([256]).
	While copying the parameter named "feature_extractor.layer3.1.bn2.bias", whose dimensions in the model are torch.Size([256]) and whose dimensions in the checkpoint are torch.Size([256]).
	While copying the parameter named "feature_extractor.layer3.1.bn2.running_mean", whose dimensions in the model are torch.Size([256]) and whose dimensions in the checkpoint are torch.Size([256]).
	While copying the parameter named "feature_extractor.layer3.1.bn2.running_var", whose dimensions in the model are torch.Size([256]) and whose dimensions in the checkpoint are torch.Size([256]).
	While copying the parameter named "feature_extractor.layer3.1.bn2.num_batches_tracked", whose dimensions in the model are torch.Size([]) and whose dimensions in the checkpoint are torch.Size([]).
	While copying the parameter named "feature_extractor.layer4.0.conv1.weight", whose dimensions in the model are torch.Size([512, 256, 3, 3]) and whose dimensions in the checkpoint are torch.Size([512, 256, 3, 3]).
	While copying the parameter named "feature_extractor.layer4.0.bn1.weight", whose dimensions in the model are torch.Size([512]) and whose dimensions in the checkpoint are torch.Size([512]).
	While copying the parameter named "feature_extractor.layer4.0.bn1.bias", whose dimensions in the model are torch.Size([512]) and whose dimensions in the checkpoint are torch.Size([512]).
	While copying the parameter named "feature_extractor.layer4.0.bn1.running_mean", whose dimensions in the model are torch.Size([512]) and whose dimensions in the checkpoint are torch.Size([512]).
	While copying the parameter named "feature_extractor.layer4.0.bn1.running_var", whose dimensions in the model are torch.Size([512]) and whose dimensions in the checkpoint are torch.Size([512]).
	While copying the parameter named "feature_extractor.layer4.0.bn1.num_batches_tracked", whose dimensions in the model are torch.Size([]) and whose dimensions in the checkpoint are torch.Size([]).
	While copying the parameter named "feature_extractor.layer4.0.conv2.weight", whose dimensions in the model are torch.Size([512, 512, 3, 3]) and whose dimensions in the checkpoint are torch.Size([512, 512, 3, 3]).
	While copying the parameter named "feature_extractor.layer4.0.bn2.weight", whose dimensions in the model are torch.Size([512]) and whose dimensions in the checkpoint are torch.Size([512]).
	While copying the parameter named "feature_extractor.layer4.0.bn2.bias", whose dimensions in the model are torch.Size([512]) and whose dimensions in the checkpoint are torch.Size([512]).
	While copying the parameter named "feature_extractor.layer4.0.bn2.running_mean", whose dimensions in the model are torch.Size([512]) and whose dimensions in the checkpoint are torch.Size([512]).
	While copying the parameter named "feature_extractor.layer4.0.bn2.running_var", whose dimensions in the model are torch.Size([512]) and whose dimensions in the checkpoint are torch.Size([512]).
	While copying the parameter named "feature_extractor.layer4.0.bn2.num_batches_tracked", whose dimensions in the model are torch.Size([]) and whose dimensions in the checkpoint are torch.Size([]).
	While copying the parameter named "feature_extractor.layer4.0.downsample.0.weight", whose dimensions in the model are torch.Size([512, 256, 1, 1]) and whose dimensions in the checkpoint are torch.Size([512, 256, 1, 1]).
	While copying the parameter named "feature_extractor.layer4.0.downsample.1.weight", whose dimensions in the model are torch.Size([512]) and whose dimensions in the checkpoint are torch.Size([512]).
	While copying the parameter named "feature_extractor.layer4.0.downsample.1.bias", whose dimensions in the model are torch.Size([512]) and whose dimensions in the checkpoint are torch.Size([512]).
	While copying the parameter named "feature_extractor.layer4.0.downsample.1.running_mean", whose dimensions in the model are torch.Size([512]) and whose dimensions in the checkpoint are torch.Size([512]).
	While copying the parameter named "feature_extractor.layer4.0.downsample.1.running_var", whose dimensions in the model are torch.Size([512]) and whose dimensions in the checkpoint are torch.Size([512]).
	While copying the parameter named "feature_extractor.layer4.0.downsample.1.num_batches_tracked", whose dimensions in the model are torch.Size([]) and whose dimensions in the checkpoint are torch.Size([]).
	While copying the parameter named "feature_extractor.layer4.1.conv1.weight", whose dimensions in the model are torch.Size([512, 512, 3, 3]) and whose dimensions in the checkpoint are torch.Size([512, 512, 3, 3]).
	While copying the parameter named "feature_extractor.layer4.1.bn1.weight", whose dimensions in the model are torch.Size([512]) and whose dimensions in the checkpoint are torch.Size([512]).
	While copying the parameter named "feature_extractor.layer4.1.bn1.bias", whose dimensions in the model are torch.Size([512]) and whose dimensions in the checkpoint are torch.Size([512]).
	While copying the parameter named "feature_extractor.layer4.1.bn1.running_mean", whose dimensions in the model are torch.Size([512]) and whose dimensions in the checkpoint are torch.Size([512]).
	While copying the parameter named "feature_extractor.layer4.1.bn1.running_var", whose dimensions in the model are torch.Size([512]) and whose dimensions in the checkpoint are torch.Size([512]).
	While copying the parameter named "feature_extractor.layer4.1.bn1.num_batches_tracked", whose dimensions in the model are torch.Size([]) and whose dimensions in the checkpoint are torch.Size([]).
	While copying the parameter named "feature_extractor.layer4.1.conv2.weight", whose dimensions in the model are torch.Size([512, 512, 3, 3]) and whose dimensions in the checkpoint are torch.Size([512, 512, 3, 3]).
	While copying the parameter named "feature_extractor.layer4.1.bn2.weight", whose dimensions in the model are torch.Size([512]) and whose dimensions in the checkpoint are torch.Size([512]).
	While copying the parameter named "feature_extractor.layer4.1.bn2.bias", whose dimensions in the model are torch.Size([512]) and whose dimensions in the checkpoint are torch.Size([512]).
	While copying the parameter named "feature_extractor.layer4.1.bn2.running_mean", whose dimensions in the model are torch.Size([512]) and whose dimensions in the checkpoint are torch.Size([512]).
	While copying the parameter named "feature_extractor.layer4.1.bn2.running_var", whose dimensions in the model are torch.Size([512]) and whose dimensions in the checkpoint are torch.Size([512]).
	While copying the parameter named "feature_extractor.layer4.1.bn2.num_batches_tracked", whose dimensions in the model are torch.Size([]) and whose dimensions in the checkpoint are torch.Size([]).
	While copying the parameter named "feature_extractor.fc.weight", whose dimensions in the model are torch.Size([1000, 512]) and whose dimensions in the checkpoint are torch.Size([1000, 512]).
	While copying the parameter named "feature_extractor.fc.bias", whose dimensions in the model are torch.Size([1000]) and whose dimensions in the checkpoint are torch.Size([1000]).
	While copying the parameter named "classifier.filter_initializer.filter_conv.weight", whose dimensions in the model are torch.Size([256, 256, 3, 3]) and whose dimensions in the checkpoint are torch.Size([256, 256, 3, 3]).
	While copying the parameter named "classifier.filter_initializer.filter_conv.bias", whose dimensions in the model are torch.Size([256]) and whose dimensions in the checkpoint are torch.Size([256]).
	While copying the parameter named "classifier.filter_optimizer.log_step_length", whose dimensions in the model are torch.Size([1]) and whose dimensions in the checkpoint are torch.Size([1]).
	While copying the parameter named "classifier.filter_optimizer.filter_reg", whose dimensions in the model are torch.Size([1]) and whose dimensions in the checkpoint are torch.Size([1]).
	While copying the parameter named "classifier.feature_extractor.0.conv1.weight", whose dimensions in the model are torch.Size([256, 256, 3, 3]) and whose dimensions in the checkpoint are torch.Size([256, 256, 3, 3]).
	While copying the parameter named "classifier.feature_extractor.0.bn1.weight", whose dimensions in the model are torch.Size([256]) and whose dimensions in the checkpoint are torch.Size([256]).
	While copying the parameter named "classifier.feature_extractor.0.bn1.bias", whose dimensions in the model are torch.Size([256]) and whose dimensions in the checkpoint are torch.Size([256]).
	While copying the parameter named "classifier.feature_extractor.0.bn1.running_mean", whose dimensions in the model are torch.Size([256]) and whose dimensions in the checkpoint are torch.Size([256]).
	While copying the parameter named "classifier.feature_extractor.0.bn1.running_var", whose dimensions in the model are torch.Size([256]) and whose dimensions in the checkpoint are torch.Size([256]).
	While copying the parameter named "classifier.feature_extractor.0.bn1.num_batches_tracked", whose dimensions in the model are torch.Size([]) and whose dimensions in the checkpoint are torch.Size([]).
	While copying the parameter named "classifier.feature_extractor.0.conv2.weight", whose dimensions in the model are torch.Size([256, 256, 3, 3]) and whose dimensions in the checkpoint are torch.Size([256, 256, 3, 3]).
	While copying the parameter named "classifier.feature_extractor.0.bn2.weight", whose dimensions in the model are torch.Size([256]) and whose dimensions in the checkpoint are torch.Size([256]).
	While copying the parameter named "classifier.feature_extractor.0.bn2.bias", whose dimensions in the model are torch.Size([256]) and whose dimensions in the checkpoint are torch.Size([256]).
	While copying the parameter named "classifier.feature_extractor.0.bn2.running_mean", whose dimensions in the model are torch.Size([256]) and whose dimensions in the checkpoint are torch.Size([256]).
	While copying the parameter named "classifier.feature_extractor.0.bn2.running_var", whose dimensions in the model are torch.Size([256]) and whose dimensions in the checkpoint are torch.Size([256]).
	While copying the parameter named "classifier.feature_extractor.0.bn2.num_batches_tracked", whose dimensions in the model are torch.Size([]) and whose dimensions in the checkpoint are torch.Size([]).
	While copying the parameter named "classifier.feature_extractor.1.weight", whose dimensions in the model are torch.Size([256, 256, 3, 3]) and whose dimensions in the checkpoint are torch.Size([256, 256, 3, 3]).
	While copying the parameter named "bb_regressor.conv3_1r.0.weight", whose dimensions in the model are torch.Size([128, 128, 3, 3]) and whose dimensions in the checkpoint are torch.Size([128, 128, 3, 3]).
	While copying the parameter named "bb_regressor.conv3_1r.0.bias", whose dimensions in the model are torch.Size([128]) and whose dimensions in the checkpoint are torch.Size([128]).
	While copying the parameter named "bb_regressor.conv3_1r.1.weight", whose dimensions in the model are torch.Size([128]) and whose dimensions in the checkpoint are torch.Size([128]).
	While copying the parameter named "bb_regressor.conv3_1r.1.bias", whose dimensions in the model are torch.Size([128]) and whose dimensions in the checkpoint are torch.Size([128]).
	While copying the parameter named "bb_regressor.conv3_1r.1.running_mean", whose dimensions in the model are torch.Size([128]) and whose dimensions in the checkpoint are torch.Size([128]).
	While copying the parameter named "bb_regressor.conv3_1r.1.running_var", whose dimensions in the model are torch.Size([128]) and whose dimensions in the checkpoint are torch.Size([128]).
	While copying the parameter named "bb_regressor.conv3_1r.1.num_batches_tracked", whose dimensions in the model are torch.Size([]) and whose dimensions in the checkpoint are torch.Size([]).
	While copying the parameter named "bb_regressor.conv3_1t.0.weight", whose dimensions in the model are torch.Size([256, 128, 3, 3]) and whose dimensions in the checkpoint are torch.Size([256, 128, 3, 3]).
	While copying the parameter named "bb_regressor.conv3_1t.0.bias", whose dimensions in the model are torch.Size([256]) and whose dimensions in the checkpoint are torch.Size([256]).
	While copying the parameter named "bb_regressor.conv3_1t.1.weight", whose dimensions in the model are torch.Size([256]) and whose dimensions in the checkpoint are torch.Size([256]).
	While copying the parameter named "bb_regressor.conv3_1t.1.bias", whose dimensions in the model are torch.Size([256]) and whose dimensions in the checkpoint are torch.Size([256]).
	While copying the parameter named "bb_regressor.conv3_1t.1.running_mean", whose dimensions in the model are torch.Size([256]) and whose dimensions in the checkpoint are torch.Size([256]).
	While copying the parameter named "bb_regressor.conv3_1t.1.running_var", whose dimensions in the model are torch.Size([256]) and whose dimensions in the checkpoint are torch.Size([256]).
	While copying the parameter named "bb_regressor.conv3_1t.1.num_batches_tracked", whose dimensions in the model are torch.Size([]) and whose dimensions in the checkpoint are torch.Size([]).
	While copying the parameter named "bb_regressor.conv3_2t.0.weight", whose dimensions in the model are torch.Size([256, 256, 3, 3]) and whose dimensions in the checkpoint are torch.Size([256, 256, 3, 3]).
	While copying the parameter named "bb_regressor.conv3_2t.0.bias", whose dimensions in the model are torch.Size([256]) and whose dimensions in the checkpoint are torch.Size([256]).
	While copying the parameter named "bb_regressor.conv3_2t.1.weight", whose dimensions in the model are torch.Size([256]) and whose dimensions in the checkpoint are torch.Size([256]).
	While copying the parameter named "bb_regressor.conv3_2t.1.bias", whose dimensions in the model are torch.Size([256]) and whose dimensions in the checkpoint are torch.Size([256]).
	While copying the parameter named "bb_regressor.conv3_2t.1.running_mean", whose dimensions in the model are torch.Size([256]) and whose dimensions in the checkpoint are torch.Size([256]).
	While copying the parameter named "bb_regressor.conv3_2t.1.running_var", whose dimensions in the model are torch.Size([256]) and whose dimensions in the checkpoint are torch.Size([256]).
	While copying the parameter named "bb_regressor.conv3_2t.1.num_batches_tracked", whose dimensions in the model are torch.Size([]) and whose dimensions in the checkpoint are torch.Size([]).
	While copying the parameter named "bb_regressor.fc3_1r.0.weight", whose dimensions in the model are torch.Size([256, 128, 3, 3]) and whose dimensions in the checkpoint are torch.Size([256, 128, 3, 3]).
	While copying the parameter named "bb_regressor.fc3_1r.0.bias", whose dimensions in the model are torch.Size([256]) and whose dimensions in the checkpoint are torch.Size([256]).
	While copying the parameter named "bb_regressor.fc3_1r.1.weight", whose dimensions in the model are torch.Size([256]) and whose dimensions in the checkpoint are torch.Size([256]).
	While copying the parameter named "bb_regressor.fc3_1r.1.bias", whose dimensions in the model are torch.Size([256]) and whose dimensions in the checkpoint are torch.Size([256]).
	While copying the parameter named "bb_regressor.fc3_1r.1.running_mean", whose dimensions in the model are torch.Size([256]) and whose dimensions in the checkpoint are torch.Size([256]).
	While copying the parameter named "bb_regressor.fc3_1r.1.running_var", whose dimensions in the model are torch.Size([256]) and whose dimensions in the checkpoint are torch.Size([256]).
	While copying the parameter named "bb_regressor.fc3_1r.1.num_batches_tracked", whose dimensions in the model are torch.Size([]) and whose dimensions in the checkpoint are torch.Size([]).
	While copying the parameter named "bb_regressor.conv4_1r.0.weight", whose dimensions in the model are torch.Size([256, 256, 3, 3]) and whose dimensions in the checkpoint are torch.Size([256, 256, 3, 3]).
	While copying the parameter named "bb_regressor.conv4_1r.0.bias", whose dimensions in the model are torch.Size([256]) and whose dimensions in the checkpoint are torch.Size([256]).
	While copying the parameter named "bb_regressor.conv4_1r.1.weight", whose dimensions in the model are torch.Size([256]) and whose dimensions in the checkpoint are torch.Size([256]).
	While copying the parameter named "bb_regressor.conv4_1r.1.bias", whose dimensions in the model are torch.Size([256]) and whose dimensions in the checkpoint are torch.Size([256]).
	While copying the parameter named "bb_regressor.conv4_1r.1.running_mean", whose dimensions in the model are torch.Size([256]) and whose dimensions in the checkpoint are torch.Size([256]).
	While copying the parameter named "bb_regressor.conv4_1r.1.running_var", whose dimensions in the model are torch.Size([256]) and whose dimensions in the checkpoint are torch.Size([256]).
	While copying the parameter named "bb_regressor.conv4_1r.1.num_batches_tracked", whose dimensions in the model are torch.Size([]) and whose dimensions in the checkpoint are torch.Size([]).
	While copying the parameter named "bb_regressor.conv4_1t.0.weight", whose dimensions in the model are torch.Size([256, 256, 3, 3]) and whose dimensions in the checkpoint are torch.Size([256, 256, 3, 3]).
	While copying the parameter named "bb_regressor.conv4_1t.0.bias", whose dimensions in the model are torch.Size([256]) and whose dimensions in the checkpoint are torch.Size([256]).
	While copying the parameter named "bb_regressor.conv4_1t.1.weight", whose dimensions in the model are torch.Size([256]) and whose dimensions in the checkpoint are torch.Size([256]).
	While copying the parameter named "bb_regressor.conv4_1t.1.bias", whose dimensions in the model are torch.Size([256]) and whose dimensions in the checkpoint are torch.Size([256]).
	While copying the parameter named "bb_regressor.conv4_1t.1.running_mean", whose dimensions in the model are torch.Size([256]) and whose dimensions in the checkpoint are torch.Size([256]).
	While copying the parameter named "bb_regressor.conv4_1t.1.running_var", whose dimensions in the model are torch.Size([256]) and whose dimensions in the checkpoint are torch.Size([256]).
	While copying the parameter named "bb_regressor.conv4_1t.1.num_batches_tracked", whose dimensions in the model are torch.Size([]) and whose dimensions in the checkpoint are torch.Size([]).
	While copying the parameter named "bb_regressor.conv4_2t.0.weight", whose dimensions in the model are torch.Size([256, 256, 3, 3]) and whose dimensions in the checkpoint are torch.Size([256, 256, 3, 3]).
	While copying the parameter named "bb_regressor.conv4_2t.0.bias", whose dimensions in the model are torch.Size([256]) and whose dimensions in the checkpoint are torch.Size([256]).
	While copying the parameter named "bb_regressor.conv4_2t.1.weight", whose dimensions in the model are torch.Size([256]) and whose dimensions in the checkpoint are torch.Size([256]).
	While copying the parameter named "bb_regressor.conv4_2t.1.bias", whose dimensions in the model are torch.Size([256]) and whose dimensions in the checkpoint are torch.Size([256]).
	While copying the parameter named "bb_regressor.conv4_2t.1.running_mean", whose dimensions in the model are torch.Size([256]) and whose dimensions in the checkpoint are torch.Size([256]).
	While copying the parameter named "bb_regressor.conv4_2t.1.running_var", whose dimensions in the model are torch.Size([256]) and whose dimensions in the checkpoint are torch.Size([256]).
	While copying the parameter named "bb_regressor.conv4_2t.1.num_batches_tracked", whose dimensions in the model are torch.Size([]) and whose dimensions in the checkpoint are torch.Size([]).
	While copying the parameter named "bb_regressor.fc34_3r.0.weight", whose dimensions in the model are torch.Size([256, 512, 1, 1]) and whose dimensions in the checkpoint are torch.Size([256, 512, 1, 1]).
	While copying the parameter named "bb_regressor.fc34_3r.0.bias", whose dimensions in the model are torch.Size([256]) and whose dimensions in the checkpoint are torch.Size([256]).
	While copying the parameter named "bb_regressor.fc34_3r.1.weight", whose dimensions in the model are torch.Size([256]) and whose dimensions in the checkpoint are torch.Size([256]).
	While copying the parameter named "bb_regressor.fc34_3r.1.bias", whose dimensions in the model are torch.Size([256]) and whose dimensions in the checkpoint are torch.Size([256]).
	While copying the parameter named "bb_regressor.fc34_3r.1.running_mean", whose dimensions in the model are torch.Size([256]) and whose dimensions in the checkpoint are torch.Size([256]).
	While copying the parameter named "bb_regressor.fc34_3r.1.running_var", whose dimensions in the model are torch.Size([256]) and whose dimensions in the checkpoint are torch.Size([256]).
	While copying the parameter named "bb_regressor.fc34_3r.1.num_batches_tracked", whose dimensions in the model are torch.Size([]) and whose dimensions in the checkpoint are torch.Size([]).
	While copying the parameter named "bb_regressor.fc34_4r.0.weight", whose dimensions in the model are torch.Size([256, 512, 1, 1]) and whose dimensions in the checkpoint are torch.Size([256, 512, 1, 1]).
	While copying the parameter named "bb_regressor.fc34_4r.0.bias", whose dimensions in the model are torch.Size([256]) and whose dimensions in the checkpoint are torch.Size([256]).
	While copying the parameter named "bb_regressor.fc34_4r.1.weight", whose dimensions in the model are torch.Size([256]) and whose dimensions in the checkpoint are torch.Size([256]).
	While copying the parameter named "bb_regressor.fc34_4r.1.bias", whose dimensions in the model are torch.Size([256]) and whose dimensions in the checkpoint are torch.Size([256]).
	While copying the parameter named "bb_regressor.fc34_4r.1.running_mean", whose dimensions in the model are torch.Size([256]) and whose dimensions in the checkpoint are torch.Size([256]).
	While copying the parameter named "bb_regressor.fc34_4r.1.running_var", whose dimensions in the model are torch.Size([256]) and whose dimensions in the checkpoint are torch.Size([256]).
	While copying the parameter named "bb_regressor.fc34_4r.1.num_batches_tracked", whose dimensions in the model are torch.Size([]) and whose dimensions in the checkpoint are torch.Size([]).
	While copying the parameter named "bb_regressor.fc3_rt.linear.weight", whose dimensions in the model are torch.Size([256, 6400]) and whose dimensions in the checkpoint are torch.Size([256, 6400]).
	While copying the parameter named "bb_regressor.fc3_rt.linear.bias", whose dimensions in the model are torch.Size([256]) and whose dimensions in the checkpoint are torch.Size([256]).
	While copying the parameter named "bb_regressor.fc3_rt.bn.weight", whose dimensions in the model are torch.Size([256]) and whose dimensions in the checkpoint are torch.Size([256]).
	While copying the parameter named "bb_regressor.fc3_rt.bn.bias", whose dimensions in the model are torch.Size([256]) and whose dimensions in the checkpoint are torch.Size([256]).
	While copying the parameter named "bb_regressor.fc3_rt.bn.running_mean", whose dimensions in the model are torch.Size([256]) and whose dimensions in the checkpoint are torch.Size([256]).
	While copying the parameter named "bb_regressor.fc3_rt.bn.running_var", whose dimensions in the model are torch.Size([256]) and whose dimensions in the checkpoint are torch.Size([256]).
	While copying the parameter named "bb_regressor.fc3_rt.bn.num_batches_tracked", whose dimensions in the model are torch.Size([]) and whose dimensions in the checkpoint are torch.Size([]).
	While copying the parameter named "bb_regressor.fc4_rt.linear.weight", whose dimensions in the model are torch.Size([256, 2304]) and whose dimensions in the checkpoint are torch.Size([256, 2304]).
	While copying the parameter named "bb_regressor.fc4_rt.linear.bias", whose dimensions in the model are torch.Size([256]) and whose dimensions in the checkpoint are torch.Size([256]).
	While copying the parameter named "bb_regressor.fc4_rt.bn.weight", whose dimensions in the model are torch.Size([256]) and whose dimensions in the checkpoint are torch.Size([256]).
	While copying the parameter named "bb_regressor.fc4_rt.bn.bias", whose dimensions in the model are torch.Size([256]) and whose dimensions in the checkpoint are torch.Size([256]).
	While copying the parameter named "bb_regressor.fc4_rt.bn.running_mean", whose dimensions in the model are torch.Size([256]) and whose dimensions in the checkpoint are torch.Size([256]).
	While copying the parameter named "bb_regressor.fc4_rt.bn.running_var", whose dimensions in the model are torch.Size([256]) and whose dimensions in the checkpoint are torch.Size([256]).
	While copying the parameter named "bb_regressor.fc4_rt.bn.num_batches_tracked", whose dimensions in the model are torch.Size([]) and whose dimensions in the checkpoint are torch.Size([]).
	While copying the parameter named "bb_regressor.iou_predictor.weight", whose dimensions in the model are torch.Size([1, 512]) and whose dimensions in the checkpoint are torch.Size([1, 512]).
	While copying the parameter named "bb_regressor.iou_predictor.bias", whose dimensions in the model are torch.Size([1]) and whose dimensions in the checkpoint are torch.Size([1]).
Restarting training from last epoch ...
Training crashed at epoch 42
Traceback for the error!

DiMPnet(
  (feature_extractor): ResNet(
    (conv1): Conv2d(3, 64, kernel_size=(7, 7), stride=(2, 2), padding=(3, 3), bias=False)
    (bn1): BatchNorm2d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
    (relu): ReLU(inplace=True)
    (maxpool): MaxPool2d(kernel_size=3, stride=2, padding=1, dilation=1, ceil_mode=False)
    (layer1): Sequential(
      (0): BasicBlock(
        (conv1): Conv2d(64, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
        (bn1): BatchNorm2d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
        (relu): ReLU(inplace=True)
        (conv2): Conv2d(64, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
        (bn2): BatchNorm2d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
      )
      (1): BasicBlock(
        (conv1): Conv2d(64, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
        (bn1): BatchNorm2d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
        (relu): ReLU(inplace=True)
        (conv2): Conv2d(64, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
        (bn2): BatchNorm2d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
      )
    )
    (layer2): Sequential(
      (0): BasicBlock(
        (conv1): Conv2d(64, 128, kernel_size=(3, 3), stride=(2, 2), padding=(1, 1), bias=False)
        (bn1): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
        (relu): ReLU(inplace=True)
        (conv2): Conv2d(128, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
        (bn2): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
        (downsample): Sequential(
          (0): Conv2d(64, 128, kernel_size=(1, 1), stride=(2, 2), bias=False)
          (1): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
        )
      )
      (1): BasicBlock(
        (conv1): Conv2d(128, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
        (bn1): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
        (relu): ReLU(inplace=True)
        (conv2): Conv2d(128, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
        (bn2): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
      )
    )
    (layer3): Sequential(
      (0): BasicBlock(
        (conv1): Conv2d(128, 256, kernel_size=(3, 3), stride=(2, 2), padding=(1, 1), bias=False)
        (bn1): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
        (relu): ReLU(inplace=True)
        (conv2): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
        (bn2): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
        (downsample): Sequential(
          (0): Conv2d(128, 256, kernel_size=(1, 1), stride=(2, 2), bias=False)
          (1): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
        )
      )
      (1): BasicBlock(
        (conv1): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
        (bn1): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
        (relu): ReLU(inplace=True)
        (conv2): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
        (bn2): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
      )
    )
    (layer4): Sequential(
      (0): BasicBlock(
        (conv1): Conv2d(256, 512, kernel_size=(3, 3), stride=(2, 2), padding=(1, 1), bias=False)
        (bn1): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
        (relu): ReLU(inplace=True)
        (conv2): Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
        (bn2): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
        (downsample): Sequential(
          (0): Conv2d(256, 512, kernel_size=(1, 1), stride=(2, 2), bias=False)
          (1): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
        )
      )
      (1): BasicBlock(
        (conv1): Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
        (bn1): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
        (relu): ReLU(inplace=True)
        (conv2): Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
        (bn2): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
      )
    )
    (avgpool): AdaptiveAvgPool2d(output_size=(1, 1))
    (fc): Linear(in_features=512, out_features=1000, bias=True)
  )
  (classifier): LinearFilter(
    (filter_initializer): FilterInitializerLinear(
      (filter_conv): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
      (filter_pool): FilterPool(
        (prroi_pool): PrRoIPool2D(kernel_size=(4, 4), spatial_scale=0.0625)
      )
    )
    (filter_optimizer): PrDiMPSteepestDescentNewton()
    (feature_extractor): Sequential(
      (0): BasicBlock(
        (conv1): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
        (bn1): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
        (relu): ReLU(inplace=True)
        (conv2): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
        (bn2): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
      )
      (1): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
      (2): InstanceL2Norm()
    )
  )
  (bb_regressor): AtomIoUNet(
    (conv3_1r): Sequential(
      (0): Conv2d(128, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
      (1): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
      (2): ReLU(inplace=True)
    )
    (conv3_1t): Sequential(
      (0): Conv2d(128, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
      (1): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
      (2): ReLU(inplace=True)
    )
    (conv3_2t): Sequential(
      (0): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
      (1): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
      (2): ReLU(inplace=True)
    )
    (prroi_pool3r): PrRoIPool2D(kernel_size=(3, 3), spatial_scale=0.125)
    (prroi_pool3t): PrRoIPool2D(kernel_size=(5, 5), spatial_scale=0.125)
    (fc3_1r): Sequential(
      (0): Conv2d(128, 256, kernel_size=(3, 3), stride=(1, 1))
      (1): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
      (2): ReLU(inplace=True)
    )
    (conv4_1r): Sequential(
      (0): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
      (1): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
      (2): ReLU(inplace=True)
    )
    (conv4_1t): Sequential(
      (0): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
      (1): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
      (2): ReLU(inplace=True)
    )
    (conv4_2t): Sequential(
      (0): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
      (1): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
      (2): ReLU(inplace=True)
    )
    (prroi_pool4r): PrRoIPool2D(kernel_size=(1, 1), spatial_scale=0.0625)
    (prroi_pool4t): PrRoIPool2D(kernel_size=(3, 3), spatial_scale=0.0625)
    (fc34_3r): Sequential(
      (0): Conv2d(512, 256, kernel_size=(1, 1), stride=(1, 1))
      (1): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
      (2): ReLU(inplace=True)
    )
    (fc34_4r): Sequential(
      (0): Conv2d(512, 256, kernel_size=(1, 1), stride=(1, 1))
      (1): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
      (2): ReLU(inplace=True)
    )
    (fc3_rt): LinearBlock(
      (linear): Linear(in_features=6400, out_features=256, bias=True)
      (bn): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
      (relu): ReLU(inplace=True)
    )
    (fc4_rt): LinearBlock(
      (linear): Linear(in_features=2304, out_features=256, bias=True)
      (bn): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
      (relu): ReLU(inplace=True)
    )
    (iou_predictor): Linear(in_features=512, out_features=1, bias=True)
  )
)

程序开始运行时间：
2020-08-19 17:06:29.877117
程序结束运行时间：
2020-08-21 13:09:13.846450
程序共运行：72163.000000秒