Tarun K
Tarun K
Yes, the model converges with SGD, but same model does not if I replace SGD with adam.
Agree that BN shouldn't be relevant to optimization method, but I have read somewhere that Adam requires global statistics at every iteration, so the implementation of BNsync given here could...
Can you make sure that the versions of the PyTorch are the same as recommended? I did not face any such issues at my end.
We use exactly the same method used by CAIN but plot only the highest activation feature. https://www.dropbox.com/s/b62wnroqdd5lhfc/AAAI-ChoiM.4773.pdf?dl=0
During training, we compute a separate attention score for each channel dimension in each layer. To visualize, we pick a layer and compute the attention weights for all the channels,...
@issakh Can you make sure that the versions of the PyTorch are the same as recommended? I did not face any such issues at my end.
May I know what Adobe dataset are you using?
Looks like a memory issue. Try batch loading the frames.
Can you make sure that the versions of the PyTorch are the same as recommended? I did not face any such issues at my end.
Sure. That will be really helpful. Please raise a PR and I can review soon.