aeon icon indicating copy to clipboard operation
aeon copied to clipboard

Add Weight Normalization Keras Wrapper

Open aadya940 opened this issue 1 year ago • 2 comments

Related to #1714.

Implements the weight normalization algorithm as a wrapper rather than a layer.

aadya940 avatar Sep 29 '24 16:09 aadya940

@hadifawaz1999

aadya940 avatar Sep 29 '24 16:09 aadya940

Thank you for contributing to aeon

I did not find any labels to add based on the title. Please add the [ENH], [MNT], [BUG], [DOC], [REF], [DEP] and/or [GOV] tags to your pull requests titles. For now you can add the labels manually.

The Checks tab will show the status of our automated tests. You can click on individual test runs in the tab or "Details" in the panel below to see more information if there is a failure.

If our pre-commit code quality check fails, any trivial fixes will automatically be pushed to your PR unless it is a draft.

Don't hesitate to ask questions on the aeon Slack channel if you have any.

PR CI actions

These checkboxes will add labels to enable/disable CI functionality for this PR. This may not take effect immediately, and a new commit may be required to run the new configuration.

  • [ ] Run pre-commit checks for all files
  • [ ] Run mypy typecheck tests
  • [ ] Run all pytest tests and configurations
  • [ ] Run all notebook example tests
  • [ ] Run numba-disabled codecov tests
  • [ ] Stop automatic pre-commit fixes (always disabled for drafts)
  • [ ] Push an empty commit to re-run CI checks

aeon-actions-bot[bot] avatar Sep 29 '24 16:09 aeon-actions-bot[bot]

This was the deprecated layer right? If there's any reused code I would link to the old package and acknowledge that even if it's gone. If it's all original, then no problem.

The implementation is original, hence no need to link to the old package.

aadya940 avatar Oct 16 '24 14:10 aadya940

Fine by me then. Will give it a bit more for @hadifawaz1999 to have a check over and put it in if theres nothing.

MatthewMiddlehurst avatar Oct 18 '24 15:10 MatthewMiddlehurst

Great Addition !! Do you think we can use it for the dilated cnn in deep clustering ?

@hadifawaz1999 Yes it should, since the only difference is a couple of zeros in the kernel. Added it in the test.

aadya940 avatar Oct 20 '24 10:10 aadya940