feat: implemented hardsilu activation function #26847
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
|
Thank you for this PR, here is the CI results: This pull request does not result in any additional test failures. Congratulations! |
![github-actions[bot]](https://avatars.githubusercontent.com/in/15368?s=60&v=4){kind=small}
ivy-leaves
added
Array API
aparajith21
suggested changes
Oct 14, 2023
|
Hi, please don't delete the |
|
Hello, I think this PR is unactive for a little while, so I'll close it for now. If you want to continue working on it in the future please feel free to open it and start working. Thanks and happy contributing 😊 |
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Outdated suggestions cannot be applied.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.
PR Description
I have implemented the hardsilu activation for tensorflow, numpy, torch, paddle, and jax. See the attached image below showing the test results in PyCharm.
Only issue is that the jax test is not passing, but this happens with other existing activations in the repo because I'm getting the KeyError issue. I tried versions lower than 0.4.18 and they all give another error mentioning something about circular import. Note that I'm using a conda environment due to issues with Docker. I asked for help on Discord but it seems no one knows how to address any of these issues yet.
Related Issue
Close #26741
Checklist