error in running code in caisa-b

[aleeyang]

I use this command python3 gaitgraph_casia_b.py fit --config configs/casia_b.yaml
but it always give me error reply

File "gaitgraph_casia_b.py", line 77, in validation_step
  y_hat = self(x)
File "/home/fuyang/anaconda3/envs/gaitgraph/lib/python3.8/site-packages/torch/nn/modules/module.py", line 1110, in _call_impl
  return forward_call(*input, **kwargs)
File "gaitgraph_casia_b.py", line 64, in forward
  return self.backbone(x)[0]
File "/home/fuyang/anaconda3/envs/gaitgraph/lib/python3.8/site-packages/torch/nn/modules/module.py", line 1110, in _call_impl
  return forward_call(*input, **kwargs)
File "/home/fuyang/project/keypoint/GaitGraph2/GaitGraph2-main/GaitGraph/models/ResGCNv1/nets.py", line 66, in forward
  x_cat.append(branch(x[:, i]))
File "/home/fuyang/anaconda3/envs/gaitgraph/lib/python3.8/site-packages/torch/nn/modules/module.py", line 1110, in _call_impl
  return forward_call(*input, **kwargs)
File "/home/fuyang/project/keypoint/GaitGraph2/GaitGraph2-main/GaitGraph/models/ResGCNv1/nets.py", line 24, in forward
  x = self.bn(x)
File "/home/fuyang/anaconda3/envs/gaitgraph/lib/python3.8/site-packages/torch/nn/modules/module.py", line 1110, in _call_impl
  return forward_call(*input, **kwargs)
File "/home/fuyang/anaconda3/envs/gaitgraph/lib/python3.8/site-packages/torch/nn/modules/batchnorm.py", line 168, in forward
  return F.batch_norm(
File "/home/fuyang/anaconda3/envs/gaitgraph/lib/python3.8/site-packages/torch/nn/functional.py", line 2421, in batch_norm
  return torch.batch_norm(
RuntimeError: running_mean should contain 5 elements not 15

[aleeyang]

I can not run your code on caisa-b and oumvlp dataset neither.Can you give more detail command or some steps of configuration?
thank you very much

[aleeyang]

I changed to default setting of caisa-b code multi_branch: bool = False to multi_branch: bool = True
I get this result from tensorboard,but I do not knoe which result is the finnal one
how can I get the result in your paper from this image? (how can I choose one from these results in different steps?)

[OnlyFlashEobard]

same issue, do you solve it?

I use this command python3 gaitgraph_casia_b.py fit --config configs/casia_b.yaml but it always give me error reply

File "gaitgraph_casia_b.py", line 77, in validation_step
  y_hat = self(x)
File "/home/fuyang/anaconda3/envs/gaitgraph/lib/python3.8/site-packages/torch/nn/modules/module.py", line 1110, in _call_impl
  return forward_call(*input, **kwargs)
File "gaitgraph_casia_b.py", line 64, in forward
  return self.backbone(x)[0]
File "/home/fuyang/anaconda3/envs/gaitgraph/lib/python3.8/site-packages/torch/nn/modules/module.py", line 1110, in _call_impl
  return forward_call(*input, **kwargs)
File "/home/fuyang/project/keypoint/GaitGraph2/GaitGraph2-main/GaitGraph/models/ResGCNv1/nets.py", line 66, in forward
  x_cat.append(branch(x[:, i]))
File "/home/fuyang/anaconda3/envs/gaitgraph/lib/python3.8/site-packages/torch/nn/modules/module.py", line 1110, in _call_impl
  return forward_call(*input, **kwargs)
File "/home/fuyang/project/keypoint/GaitGraph2/GaitGraph2-main/GaitGraph/models/ResGCNv1/nets.py", line 24, in forward
  x = self.bn(x)
File "/home/fuyang/anaconda3/envs/gaitgraph/lib/python3.8/site-packages/torch/nn/modules/module.py", line 1110, in _call_impl
  return forward_call(*input, **kwargs)
File "/home/fuyang/anaconda3/envs/gaitgraph/lib/python3.8/site-packages/torch/nn/modules/batchnorm.py", line 168, in forward
  return F.batch_norm(
File "/home/fuyang/anaconda3/envs/gaitgraph/lib/python3.8/site-packages/torch/nn/functional.py", line 2421, in batch_norm
  return torch.batch_norm(
RuntimeError: running_mean should contain 5 elements not 15

same issue, did you solve it?

[OnlyFlashEobard]

issue solved

[zhang123-sys]

I changed to default setting of caisa-b code multi_branch: bool = False to multi_branch: bool = True I get this result from tensorboard,but I do not knoe which result is the finnal one how can I get the result in your paper from this image? (how can I choose one from these results in different steps?)

Could you please send me the result and let me see which result is the final one?

[D9701]

问题已解决

请问您是怎么解决的呢？可以详细说一下吗？谢谢

[D9701]

How did you solve it? Can you elaborate on that? Thank you

[zhang123-sys]

issue solved

Excuse me, what result do you get?

[AhsanBilal7]

How did you solve it? Can you elaborate on that? Thank you

Changing multi_branch: bool = False to multi_branch: bool = True in the both GaitGraphCASIAB and CASIAPoseModule Object