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.

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

When Recurrence meets Transformers to keras 3.0 #1984

Merged
merged 4 commits into from
Nov 15, 2024

Conversation

chunduriv
Copy link
Collaborator

@chunduriv chunduriv commented Oct 29, 2024

This PR changes the When Recurrence meets Transformers to keras 3.0, as requested in keras-team/keras-cv#2211

Please review the attached gist

Copy link
Member

@fchollet fchollet left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Thanks for the PR! I'm not seeing any usage of TF in the example, so does it run on JAX and torch?

The patching operation is done using a keras.layers.Conv2D instance instead of a
traditional tf.image.extract_patches to allow for vectorization.

Please update this -- no reference to TF needed.

@chunduriv
Copy link
Collaborator Author

@fchollet, thanks for the review.

so does it run on JAX and torch?

It now supports all backends.

Please update this -- no reference to TF needed.

Done.

@chunduriv chunduriv changed the title When Recurrence meets Transformers to keras 3.0 (Tensorflow backend only) When Recurrence meets Transformers to keras 3.0 Nov 5, 2024
Copy link
Member

@fchollet fchollet left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Looks great -- please add the generated ipynb and md files!

examples/vision/temporal_latent_bottleneck.py Outdated Show resolved Hide resolved
@@ -925,6 +981,12 @@ index = random.randint(0, config["batch_size"])
orig_image = images[index]
overlay_image = upsampled_heat_map[index, ..., 0]

if keras.backend.backend() == "torch":
Copy link
Member

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Please note, if you use ops.convert_to_numpy() you don't need any torch specific code. This is not a blocker so we can merge regardless.

Copy link
Member

@fchollet fchollet left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

LGTM, thanks!

@fchollet fchollet merged commit 67f981b into keras-team:master Nov 15, 2024
3 checks passed
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

Successfully merging this pull request may close these issues.

3 participants