Error in Visualize_video.py when using result/SINet/SINet.pth

[Novaal]

Hello @HYOJINPARK ,

when i try to use the result/SINet/SINet.pth with ./etc/Visualize_video.py i get the following Error:

RuntimeError: Error(s) in loading state_dict for SINet:
	size mismatch for encoder.classifier.conv.weight: copying a param of torch.Size([1, 144, 1, 1]) from checkpoint, where the shape is torch.Size([2, 144, 1, 1]) in current model.
	size mismatch for bn_3.weight: copying a param of torch.Size([1]) from checkpoint, where the shape is torch.Size([2]) in current model.
	size mismatch for bn_3.bias: copying a param of torch.Size([1]) from checkpoint, where the shape is torch.Size([2]) in current model.
	size mismatch for bn_3.running_mean: copying a param of torch.Size([1]) from checkpoint, where the shape is torch.Size([2]) in current model.
	size mismatch for bn_3.running_var: copying a param of torch.Size([1]) from checkpoint, where the shape is torch.Size([2]) in current model.
	size mismatch for level2_C.conv.weight: copying a param of torch.Size([1, 48, 1, 1]) from checkpoint, where the shape is torch.Size([2, 48, 1, 1]) in current model.
	size mismatch for level2_C.bn.weight: copying a param of torch.Size([1]) from checkpoint, where the shape is torch.Size([2]) in current model.
	size mismatch for level2_C.bn.bias: copying a param of torch.Size([1]) from checkpoint, where the shape is torch.Size([2]) in current model.
	size mismatch for level2_C.bn.running_mean: copying a param of torch.Size([1]) from checkpoint, where the shape is torch.Size([2]) in current model.
	size mismatch for level2_C.bn.running_var: copying a param of torch.Size([1]) from checkpoint, where the shape is torch.Size([2]) in current model.
	size mismatch for level2_C.act.weight: copying a param of torch.Size([1]) from checkpoint, where the shape is torch.Size([2]) in current model.
	size mismatch for bn_2.weight: copying a param of torch.Size([1]) from checkpoint, where the shape is torch.Size([2]) in current model.
	size mismatch for bn_2.bias: copying a param of torch.Size([1]) from checkpoint, where the shape is torch.Size([2]) in current model.
	size mismatch for bn_2.running_mean: copying a param of torch.Size([1]) from checkpoint, where the shape is torch.Size([2]) in current model.
	size mismatch for bn_2.running_var: copying a param of torch.Size([1]) from checkpoint, where the shape is torch.Size([2]) in current model.
	size mismatch for classifier.1.weight: copying a param of torch.Size([1, 1, 3, 3]) from checkpoint, where the shape is torch.Size([2, 2, 3, 3]) in current model.

With self trained models i don't get this error. How can i fix this?

Your response would be highly appreciated. Thank you!

[cyf518]

same issue

[qiutzh]

@cyf518 Hi, did you solve the problem?

[cyf518]

@qiutzh
i change net = Dnc_SINet(classes=1, p=2, q=8, chnn=1) to net = Dnc_SINet(classes=2, p=2, q=8, chnn=1)

[YAwei666]

@qiutzh
i change net = Dnc_SINet(classes=1, p=2, q=8, chnn=1) to net = Dnc_SINet(classes=2, p=2, q=8, chnn=1)
RuntimeError: weight tensor should be defined either for all or no classes at /pytorch/aten/src/THCUNN/generic/SpatialClassNLLCriterion.cu:27
when I changed this,another problem accurs. do you know how to solve this ?

[aguthrie19]

It looks like at least one of these, maybe both, is incorrect:

• the "chnn" integer in your .json (ex setting/SINet.json or whichever you're using when loading your model)
• or the "resume" checkpoint in your .json (ex result/training_session/checkpoint.pth.tar)

For whatever reason, your code is trying to combine a SINet.pth model with a checkpoint model, but it can't because SINet.pth expects 2 channels and your checkpoint provides configurations for only 1 channel.

Hope this helps! Share a snippet of the code you're running for more help.