base information about cbloss

[Adorablepet]

Thanks for sharing code.I have modified the code. I want to calculate the multivariate classification. The code is as follows. I can always report errors. I wonder if you have tried it?

pred = logits.log_softmax(dim=1)
cb_loss = F.cross_etropy(input=pred, target=labels, weights=weights)

Thanks.

[LcenArthas]

i have the same questios, have u sove it?

[Adorablepet]

@LcenArthas I have solved.

def forward(self, logits, labels):
      labels = labels.cuda()
      loss = F.cross_entropy(input=logits, target=labels, weight=self.weight)
      return loss