Fried Chicken

@Zzzzz1 Is the test_acc reported in the paper the best_acc during the whole training(i.e. max(test_acc) for all epoches)? I guess @zhyjbig used the acc of last epoch for comparison and...

I also noticed this mistake, and instead of using torch.view(), I used the following: ```python gradient_penalty = ((gradients.norm(2, dim=(1,2,3)) - 1) ** 2).mean() * LAMBDA ``` Since the gradients here...

@pipilurj Hi, I was reading this paper recently and saw your discussion above. I want to ask that if the "84.30(final)" you mentioned is the score at epoch=120? Since in...