Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Fix softmax_cross_entropy issue #24970

Conversation

yongtang
Copy link
Member

This fix is from #24397/#24736 and all credit goes to @felix-schneider (👍 )

This fix fixes #24397. This fix fixes #24736.

/cc @felix-schneider

This fix is from 24397/24736 and all credit goes to @felix-schneider

This fix fixes 24397. This fix fixes 24736.

Signed-off-by: Yong Tang <yong.tang.github@outlook.com>
@Harshini-Gadige Harshini-Gadige self-assigned this Jan 16, 2019
@Harshini-Gadige Harshini-Gadige added awaiting review Pull request awaiting review size:XS CL Change Size: Extra Small labels Jan 16, 2019
@Harshini-Gadige Harshini-Gadige added this to Assigned Reviewer in PR Queue via automation Jan 16, 2019
PR Queue automation moved this from Assigned Reviewer to Approved by Reviewer Jan 16, 2019
@Harshini-Gadige Harshini-Gadige removed the awaiting review Pull request awaiting review label Jan 16, 2019
@martinwicke martinwicke added the ready to pull PR ready for merge process label Jan 16, 2019
@tensorflow-copybara tensorflow-copybara merged commit e74388e into tensorflow:master Jan 18, 2019
PR Queue automation moved this from Approved by Reviewer to Merged Jan 18, 2019
tensorflow-copybara pushed a commit that referenced this pull request Jan 18, 2019
@yongtang yongtang deleted the 24397-24736-softmax_cross_entropy branch January 18, 2019 14:26
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
cla: yes ready to pull PR ready for merge process size:XS CL Change Size: Extra Small
Projects
PR Queue
  
Merged
Development

Successfully merging this pull request may close these issues.

tf.losses.softmax_cross_entropy does not handle sequence loss when using label smoothing
5 participants