Something wrong when computing loss

Question

Something wrong when computing loss

Opened this issue 3 years ago · 3 comments

It goes wrong when computing loss in losses.py point_loss_ = self._point_loss(logits, pos.squeeze(1))
And I check the value of logits and pos

The shape of logits is (64,42), pos (64,1)

Answer 1 · 2021-10-14T14:38:51.000Z

Is there anything wrong with these two matrix?

Answer 2 · 2021-11-01T12:40:14.000Z

Is there anything wrong with these two matrix?

I have the same problem. Have you solved it?

Answer 3 · 2021-12-22T07:11:36.000Z

I also met this problem. Do you have any solution? These two variables can't get the correct result of the CrossEntropyLoss.