John1231983

@vrao9: do you find the good solution to solve the issue? I found that reduce number layer of D can solve it. I did not test your suggested solution: reduce...

"accuracy of prediction by the discriminator for fake image is less than 50%: " how do you do it in pytorch? Thanks

@vrao9 : Thanks. Which line to do "accuracy of prediction by the discriminator for fake image is less than 50%: "?

@VainF it solved. However, I got new issue with DP mode training. It worked without DP. This is code and error ``` if train_mode == 'DP': # Data Parallel model...

@VainF I got same error with sparsity step This is my code ``` pruner = get_pruner(model, example_inputs=example_inputs) optimizer.zero_grad() out = model(data) loss = F.cross_entropy(out, target) loss.backward() if pruner is not...

OK. I found the issue. It is related to the issue of DP training https://github.com/VainF/Torch-Pruning/issues/217#issuecomment-1637076031

Any new? Do you achieve the result same paper report?

Hi all, Could we use Dice loss for 4 classes. For example, brain image: CSF, WM, GM and Background. I am looking for the way to use Dice loss of...

Great reference. I just quickly looked at it. It may use automatically way to compute backward for Dice. I think it is great to point of tensorflow in comparison with...

Thanks for your suggestion. However, I am new in tensorflow and I would like to ask you one more question. It may not related to the thread. However, it related...