Add WeightNorm wrapper layer #21276
Closed
Add WeightNorm wrapper layer #21276
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
Fix spelling.. Fix eager run without data_init
seanpmorgan
force-pushed
the
14070-weight-norm
branch
from
63e495e
to
5b75424
Compare
|
+1 Can this be reviewed/merged? |
vikaskyadav
approved these changes
Oct 22, 2018
|
Nagging Assignee @case540: It has been 105 days with no activity and this issue has an assignee. Please update the label and/or status accordingly. |
|
+1 I'm already using this, it would be nice to see it in an official release. Thanks for all the work from contributors and reviewers. |
|
This will be moved to a PR for tensorflow/addons. Closing for now to stop the nagging, but I'll reference this issue within a couple of weeks. |
|
a weight normalization wrapper is available in https://github.com/tensorflow/addons/blob/master/tensorflow_addons/layers/wrappers.py |
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Outdated suggestions cannot be applied.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.
Adds a wrapper for Weight Normalization as requested in #14070 & #10125 .
Contains optional data dependent initialization for eager execution, and works on both keras.layers and tf.layers
I struggled to figure out where to place this Wrapper, as no other layers in contrib appear to subclass anything from tf.Keras, but going forward I believe this is the direction TF is headed. Please advise if it should go somewhere else (maybe a wrappers module in contrib?)
Collab Example:
https://colab.research.google.com/drive/1nBQSAA78oUBmi9fhnHJ_zWhHq2NXjwIc#scrollTo=au25bSP75hdr
Wrapped graph:
