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

Data-efficient GANs with Adaptive Discriminator Augmentation to keras 3.0 (Tensorflow backend only) #2035

Draft
wants to merge 10 commits into
base: master
Choose a base branch
from
Draft

Data-efficient GANs with Adaptive Discriminator Augmentation to keras 3.0 (Tensorflow backend only) #2035

wants to merge 10 commits into from

Conversation

chunduriv
Copy link
Collaborator

This PR changes the Data-efficient GANs with Adaptive Discriminator Augmentation to keras 3.0 (Tensorflow backend only)

Please review the attached gist.

Humbulani1234 and others added 3 commits January 24, 2025 20:54
@Humbulani1234
Adapting the script structured_data_classification_from_scratch.py to…
fb0ed4d 
… be Backend-Agnostic (keras-team#2031)

* adapting the script structured_data_classification_from_scratch.py to be backend-agnostic

* generating .md and .ipynb files for structured_data_classification_from_scratch.py
@iamarunbrahma
fix broken links in jupyter notebooks (keras-team#2033)
b0ee77f
@sachinprasadhs
Update examples_master.py (keras-team#2034)
ba30e94 
Mark https://keras.io/examples/structured_data/classification_with_grn_and_vsn/ as Keras 3
fchollet
fchollet reviewed Jan 25, 2025
View reviewed changes
Copy link
Contributor

@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 wonder whether it would be possible to make it backend agnostic by implementing def compute_loss instead of def train_step. Maybe not. I don't recall ever doing it with a GAN. It works quite well with VAEs and diffusion models though.

@chunduriv
Copy link
Collaborator Author

chunduriv commented Jan 28, 2025 •
edited
Loading

I think, in general it should be possible to implement a GAN using compute_loss, but in this case, we are additionally using some more sophisticated techniques. For instance, there's the line self.augmenter.update(real_logits), which we would have to put in compute_loss (because this is where we will have real_logits). This should work with tensorflow and torch backends, but not with Jax, since Jax does not allow traced code to have side effects.

laxmareddyp and others added 3 commits January 28, 2025 15:03
@laxmareddyp
Basnet keras-3 migration compatibility with keras-hub (keras-team#2038)
6681f9e
@tilakrayal
Fixed the errors in gradient_centralization.py (keras-team#2042)
cab40db 
* Update gradient_centralization.py

* updated
@yasserhcn
fixed a small mistake in the transformer translation example (keras-t…
7a85372 
…eam#2030)

* fixed a small mistake in the transformer translation example

* Update typo in ipynb file

* Update typo in ipynb file
@fchollet
Copy link
Contributor

Ok, sounds good -- in this case, please add the generated files.

@divyashreepathihalli
Copy link
Contributor

@chunduriv were you able to generate the files?

@chunduriv chunduriv marked this pull request as draft February 6, 2025 00:43
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Reviewers

@fchollet fchollet fchollet left review comments

@MarkDaoust MarkDaoust Awaiting requested review from MarkDaoust MarkDaoust is a code owner

@pcoet pcoet Awaiting requested review from pcoet pcoet is a code owner

At least 1 approving review is required to merge this pull request.

Assignees

@sachinprasadhs sachinprasadhs

Labels
None yet
Projects
None yet
Milestone
No milestone
Development

Successfully merging this pull request may close these issues.
10 participants
@chunduriv @fchollet @divyashreepathihalli @sachinprasadhs @Humbulani1234 @iamarunbrahma @laxmareddyp @tilakrayal @yasserhcn @rajasekharporeddy