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.

Sign up for GitHub

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

Jump to bottom

Bug in losses_utils.reduce_batch_time #143

Closed
gpengzhi opened this issue Apr 30, 2019 · 0 comments · Fixed by #144
Closed

Bug in losses_utils.reduce_batch_time #143

gpengzhi opened this issue Apr 30, 2019 · 0 comments · Fixed by #144

Comments

@gpengzhi
Copy link
Collaborator

https://github.com/asyml/texar/blob/master/texar/losses/losses_utils.py#L156

sequence_length should be cast to the type of sequence for the tensorflow tensor division.
@gpengzhi gpengzhi mentioned this issue Apr 30, 2019
Merged
ZhitingHu added a commit that referenced this issue Apr 30, 2019
@ZhitingHu
Merge pull request #144 from gpengzhi/master
8c42c7f 
Fixes `reduce_batch_time`: cast `sequence_length` base on the dtype of `sequence`
Fixes #143
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Assignees
No one assigned
Labels
None yet
Projects
None yet
Milestone
No milestone
Development

Successfully merging a pull request may close this issue.

cast sequence_length base on the type of sequence
1 participant
@gpengzhi