when CrossEntropyLoss loss=nan

[JonesonZheng]

when I use

    loss = nn.CrossEntropyLoss()(output, target) 

replace the code in AngleLoss

    logpt = F.log_softmax(output)
    logpt = logpt.gather(1,target)
    logpt = logpt.view(-1)
    pt = Variable(logpt.data.exp())
    loss = -1 * (1-pt)**self.gamma * logpt
    loss = loss.mean()

I got loss=nan

I think theoretically logpt = F.log_softmax(output) here should be logpt = F.log_softmax(output,1) which is just the same as CrossEntropyLoss, but you implement is logpt = F.log_softmax(output,0)
Would you help explain it?

[clcarwin]

You can try to compare the code in focal_loss_pytorch.

[suanrong]

@JonesonZheng

I think you are right. It should be logpt = F.log_softmax(output,1)