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

Posted to dev@singa.apache.org by GitBox <gi...@apache.org> on 2020/05/19 16:07:27 UTC

[GitHub] [singa] chrishkchris edited a comment on issue #702: Update the metric module

chrishkchris edited a comment on issue #702:
URL: https://github.com/apache/singa/issues/702#issuecomment-630920491


   When we use this accuracy:
   y_true (each value is a label index) is provided directly by the dataset
   y_pred (each value is a label index) needs to be obtained by applying max function to the network output (i.e. logit) BEFORE the softmaxCrossEntropy


----------------------------------------------------------------
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.

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