Align BN trainable behaviour with TF 2.0 #13892
Closed
Conversation
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
# Conflicts: # tests/keras/layers/normalization_test.py
yy-lam
approved these changes
Apr 23, 2020
|
This only impacts people who are not using What about the people using |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
Summary
TensorFlow 2.0 has changed the behavior of Batch Normalization to be in inference mode when the
trainableparameter is set to False. Reference from the documentation:2 years ago, I have submitted a PR (#9965) that changed Keras' BN behaviour to what TF uses tofday but it was not merged. I submit it for reconsideration, hoping we can align the two behaviors.
I'm happy to make changes to the PR to see it getting merged to master.
Related Issues
#9214
#10014
#10045
#11803