8000 stop_gradient in SpectralNormalization wrapper by dryglicki · Pull Request #20353 · keras-team/keras · GitHub
[go: up one dir, main page]
More Web Proxy on the site http://driver.im/
Skip to content

stop_gradient in SpectralNormalization wrapper #20353

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
Oct 14, 2024

Conversation

dryglicki
Copy link
Contributor

Address comment here: #20309

According to @hertschuh, the stop_gradient call was removed since it wasn't available in the keras.ops package. This resulted in unstable behavior for the entire Spectral Normalization wrapper. stop_gradient is now present, and the fix (tested on a much larger problem) appears to have stabilized the behavior.

Copy link
8000
google-cla bot commented Oct 14, 2024

Thanks for your pull request! It looks like this may be your first contribution to a Google open source project. Before we can look at your pull request, you'll need to sign a Contributor License Agreement (CLA).

View this failed invocation of the CLA check for more information.

For the most up to date status, view the checks section at the bottom of the pull request.

@codecov-commenter
Copy link
codecov-commenter commented Oct 14, 2024

Codecov Report

All modified and coverable lines are covered by tests ✅

Project coverage is 78.87%. Comparing base (ea70d1f) to head (8423d3c).

Additional details and impacted files
@@           Coverage Diff           @@
##           master   #20353   +/-   ##
=======================================
  Coverage   78.87%   78.87%           
=======================================
  Files         512      512           
  Lines       49264    49266    +2     
  Branches     7953     7953           
=======================================
+ Hits        38859    38861    +2     
  Misses       8546     8546           
  Partials     1859     1859           
Flag Coverage Δ
keras 78.74% <100.00%> (+<0.01%) ⬆️
keras-jax 62.40% <100.00%> (+<0.01%) ⬆️
keras-numpy 57.42% <100.00%> (+<0.01%) ⬆️
keras-tensorflow 63.64% <100.00%> (+<0.01%) ⬆️
keras-torch 62.37% <100.00%> (+<0.01%) ⬆️

Flags with carried forward coverage won't be shown. Click here to find out more.

☔ View full report in Codecov by Sentry.
📢 Have feedback on the report? Share it here.

@google-ml-butler google-ml-butler bot added kokoro:force-run ready to pull Ready to be merged into the codebase labels Oct 14, 2024
@fchollet fchollet merged commit 3de677e into keras-team:master Oct 14, 2024
7 checks passed
@google-ml-butler google-ml-butler bot removed ready to pull Ready to be merged into the codebase kokoro:force-run labels Oct 14, 2024
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
Projects
None yet
Development

Successfully merging this pull request may close these issues.

4 participants
0