search

NVlabs / SCOPS

SCOPS: Self-Supervised Co-Part Segmentation (CVPR'19)
https://varunjampani.github.io/scops/
Other
217 stars 35 forks source link

Error loading model #16

Open dorsadadjoo opened 3 years ago

dorsadadjoo commented 3 years ago

I ran eval_cub.sh with model=DeepLab50_2branch

and got the following error:

    model.load_state_dict(torch.load(args.restore_from))
  File "/local-scratch/anaconda/envs/scops_env/lib/python3.6/site-packages/torch/nn/modules/module.py", line 721, in load_state_dict
    self.__class__.__name__, "\n\t".join(error_msgs)))
RuntimeError: Error(s) in loading state_dict for ResNet:
    Unexpected key(s) in state_dict: "bn1.num_batches_tracked", "layer1.0.bn1.num_batches_tracked", "layer1.0.bn2.num_batches_tracked", "layer1.0.bn3.num_batches_tracked", "layer1.0.downsample.1.num_batches_tracked", "layer1.1.bn1.num_batches_tracked", "layer1.1.bn2.num_batches_tracked", "layer1.1.bn3.num_batches_tracked", "layer1.2.bn1.num_batches_tracked", "layer1.2.bn2.num_batches_tracked", "layer1.2.bn3.num_batches_tracked", "layer2.0.bn1.num_batches_tracked", "layer2.0.bn2.num_batches_tracked", "layer2.0.bn3.num_batches_tracked", "layer2.0.downsample.1.num_batches_tracked", "layer2.1.bn1.num_batches_tracked", "layer2.1.bn2.num_batches_tracked", "layer2.1.bn3.num_batches_tracked", "layer2.2.bn1.num_batches_tracked", "layer2.2.bn2.num_batches_tracked", "layer2.2.bn3.num_batches_tracked", "layer2.3.bn1.num_batches_tracked", "layer2.3.bn2.num_batches_tracked", "layer2.3.bn3.num_batches_tracked", "layer3.0.bn1.num_batches_tracked", "layer3.0.bn2.num_batches_tracked", "layer3.0.bn3.num_batches_tracked", "layer3.0.downsample.1.num_batches_tracked", "layer3.1.bn1.num_batches_tracked", "layer3.1.bn2.num_batches_tracked", "layer3.1.bn3.num_batches_tracked", "layer3.2.bn1.num_batches_tracked", "layer3.2.bn2.num_batches_tracked", "layer3.2.bn3.num_batches_tracked", "layer3.3.bn1.num_batches_tracked", "layer3.3.bn2.num_batches_tracked", "layer3.3.bn3.num_batches_tracked", "layer3.4.bn1.num_batches_tracked", "layer3.4.bn2.num_batches_tracked", "layer3.4.bn3.num_batches_tracked", "layer3.5.bn1.num_batches_tracked", "layer3.5.bn2.num_batches_tracked", "layer3.5.bn3.num_batches_tracked", "layer4.0.bn1.num_batches_tracked", "layer4.0.bn2.num_batches_tracked", "layer4.0.bn3.num_batches_tracked", "layer4.0.downsample.1.num_batches_tracked", "layer4.1.bn1.num_batches_tracked", "layer4.1.bn2.num_batches_tracked", "layer4.1.bn3.num_batches_tracked", "layer4.2.bn1.num_batches_tracked", "layer4.2.bn2.num_batches_tracked", "layer4.2.bn3.num_batches_tracked".

Also, I tried other models. Seems like there is a mismatch between the model and the provided snapshot.

dorsadadjoo commented 3 years ago

To solve the previous issue, I added the strict=False attribute to load_state_dict() (File "evaluate_cub.py", line 135) :

model.load_state_dict(torch.load(args.restore_from), strict=False)

I also changed my torch version to 1.4.0.

Then, I got a file extension error while running sh eval_cub.sh and the reason was that the saving path in Image.fromarray was hardcoded (File "evaluate_cub.py", line 244) filename path was local and hardcoded. To solve that, the img_folder (line 190) and img_nm (line 192) should change depending on your local path.

jaymefosa commented 3 years ago

Thanks this worked for me