Skip to content
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.

Sign up for GitHub

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

Jump to bottom

Feature request: fold/unfold ops #20046

Open
shkarupa-alex opened this issue Jul 26, 2024 · 3 comments
Open

Feature request: fold/unfold ops #20046

shkarupa-alex opened this issue Jul 26, 2024 · 3 comments
Assignees
@mehtamansi29
Labels
type:feature The user is asking for a new feature.

Comments

@shkarupa-alex
Copy link
Contributor

Fold/Unforld it torch and their analogs space_to_depth/depth_to_space in TF sometimes used in models (e.g. https://paperswithcode.com/paper/selfreformer-self-refined-network-with )

It would be great to have that ops in keras.
@mehtamansi29 mehtamansi29 added type:feature The user is asking for a new feature. keras-team-review-pending Pending review by a Keras team member. labels Jul 26, 2024
@fchollet
Copy link
Collaborator

Thanks for the suggestions. Do these ops have any equivalent in JAX or in NumPy?

@hertschuh
Copy link
Collaborator

@shkarupa-alex , do you know any implementation of these operations?

@hertschuh hertschuh removed the keras-team-review-pending Pending review by a Keras team member. label Aug 2, 2024
@shkarupa-alex
Copy link
Contributor Author

I couldn't find any equivalent in NumPy. Here is a discussion related to JAX jax-ml/jax#5968

@shkarupa-alex shkarupa-alex mentioned this issue Aug 14, 2024
Open
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Assignees

@mehtamansi29 mehtamansi29

Labels
type:feature The user is asking for a new feature.
Projects
None yet
Milestone
No milestone
Development

No branches or pull requests
4 participants
@fchollet @hertschuh @shkarupa-alex @mehtamansi29