Wu Kanghui
Wu Kanghui
Hello , I wonder why the code in train() function writing like this? ```python target = torch.stack([target * 4 + k for k in range(4)], 1).view(-1) ``` instead of using...
Hi there, Thanks for your awesome work! How can I reproduce the results of `PODNet + CSCCT' in Table 1 & 2 in the paper? by the way, when i...
So pleasure to view this project. I have a question about `get_distillationinfo` in `train_better.py` ```python def get_distillinfo(model, dl): save = {} print("dumping info ......") model.eval() with torch.no_grad(): for ii, (images,...