You are viewing a plain text version of this content. The canonical link for it is here.

Posted to commits@tvm.apache.org by GitBox <gi...@apache.org> on 2021/09/27 22:45:01 UTC

[GitHub] [tvm] SWu commented on issue #9109: Incorrect implementation of cross_entropy_with_logits

SWu commented on issue #9109:
URL: https://github.com/apache/tvm/issues/9109#issuecomment-928387900


   FWIW, it appears that the current `cross_entropy_with_logits` is actually what pytorch calls `NLLLoss` (negative log-likelihood loss), so a workaround to actually get `cross_entropy_with_logits` is to `cross_entropy_with_logits(log_softmax(y_pred), y_target)`.


-- 
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.

To unsubscribe, e-mail: commits-unsubscribe@tvm.apache.org

For queries about this service, please contact Infrastructure at:
users@infra.apache.org