Loss_ToolBox-PyTorch

Loss_ToolBox-PyTorch copied to clipboard

In running the Tversky loss following error Occurred. "Legacy autograd function with non-static forward method is deprecated. " RuntimeError: Legacy autograd function with non-static forward method is deprecated. Please use...

Abbas009

issue on BinaryFocalLoss

1

I have two questions: 1) Why you are applying sigmoid at the beginning of fow$rward call? 2) Is label smoothing is correct? Should we apply to target rather than output?...

quancore

博主您好，我刚刚开始接触这个， 请问focal loss中的Binary和ori这两个focal loss有什么不同呢？ 谢谢！

Halleyawoo

Hey can the focal loss be used for a multi label problem? Thanks

DecentMakeover

balance_index: (int) balance class index, should be specific when alpha is float

4

Hi @Hsuxu , I'm a little bit confused about balance_index. What happens to the loss when alpha is of type float? Millions of thanks in advance.

DeeDiveT