Compatibility with Keras 2.2.3 and Tensorflow 1.11.0#13
Open
krasserm wants to merge 2 commits intoopenai:masterfrom
Open
Compatibility with Keras 2.2.3 and Tensorflow 1.11.0#13krasserm wants to merge 2 commits intoopenai:masterfrom
krasserm wants to merge 2 commits intoopenai:masterfrom
Conversation
krasserm
force-pushed
the
keras-upgrade
branch
2 times, most recently
from
d95423e to
1c462bd
Compare
Author
|
@TimSalimans instead of changing the original implementation for Keras 1 I created a new |
krasserm
force-pushed
the
keras-upgrade
branch
from
1c462bd to
fd42f2c
Compare
Author
|
@TimSalimans you can see the actual changes from Keras 1 to Keras 2 in the second commit. |
This file contains hidden or 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
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
1 participant
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
This PR contains the required changes to get
SGDWithWeightnormandAdamWithWeightnormrunning with Keras 2.2.3 and Tensorflow 1.11.0. I testedcifar10_cnn.pywith both updated optimizers and training shows reasonable convergence. For testing theconstraintbranch in the optimizer code I temporarily added akernel_constraintto the firstDenselayer incifar10_cnn.py(not part of the PR though) with reasonable results. I'm happy to include the test code in the PR if needed.Update: It seems that this project is not active any more. I'll therefore continue maintaining the Keras 2.x version here. For more information about weight normalization implementation options for Keras see this blog post.