Skip to content

FIX: Invariant input_spec for WeightNormalization #687

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

Merged
merged 1 commit into from
Nov 8, 2019

Conversation

Squadrick
Copy link
Member

Fixes #639

* Make the first dimension `None` to support invariant batch size.

* Add test case to check compatibility of WeightNormalization with
  TimeDistributed.
Copy link
Member

@seanpmorgan seanpmorgan left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

LGTM thanks for the fix @Squadrick !!

@seanpmorgan seanpmorgan merged commit 776b751 into tensorflow:master Nov 8, 2019
@Squadrick Squadrick deleted the wt-norm branch December 23, 2019 20:03
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Projects
None yet
Development

Successfully merging this pull request may close these issues.

Time distributed WeightNormalization result in incompatible shape
4 participants