CrossEntropyLoss reduction write error

[AutumnZ-94]

should

loss = (- targets * log_probs).mean(0).sum() in https://github.com/michuanhaohao/reid-strong-baseline/blob/master/layers/triplet_loss.py#L146

be supposed to loss = (- targets * log_probs).sum(1).mean()?

[SuperbTUM]

@AutumnZ-94 Try this. They should be the same

x = torch.randn(32, 64)

y1 = x.mean(0).sum()
y2 = x.sum(1).mean()

assert torch.allclose(y1, y2)