Move Image classification with ConvMixer to keras-core

[divyashreepathihalli]

• fixed imports
• removed tfa dependency

[codecov]

Codecov Report

Patch and project coverage have no change.

Comparison is base (9bf92c8) 83.83% compared to head (d528e22) 83.83%.

Additional details and impacted files

@@           Coverage Diff           @@
##             main     keras-team/keras-core#941   +/-   ##
=======================================
  Coverage   83.83%   83.83%           
=======================================
  Files         319      319           
  Lines       28879    28879           
  Branches     5529     5529           
=======================================
  Hits        24211    24211           
  Misses       3148     3148           
  Partials     1520     1520           

Flag	Coverage Δ
keras_core	83.72% <ø> (ø)
keras_core-jax	67.11% <ø> (ø)
keras_core-numpy	60.56% <ø> (ø)
keras_core-tensorflow	67.08% <ø> (ø)
keras_core-torch	69.08% <ø> (ø)

Flags with carried forward coverage won't be shown. Click here to find out more.

☔ View full report in Codecov by Sentry.
📢 Have feedback on the report? Share it here.

[fchollet]

Thanks for the PR! Does the example work with all backends? If so we should move it out of the tensorflow directory.

[divyashreepathihalli]

Thanks for the PR! Does the example work with all backends? If so we should move it out of the tensorflow directory.

I had to change data augmentation from a sequential model to a function for it to work with all the backends. I have filed an issue with a repro here - keras-team/keras#18396

[fchollet]

Keras Core is becoming Keras 3, and we're switching development to the main repository! Please reopen this PR in the keras-team/keras repository. Unfortunately we aren't able to automatically transfer PRs (but we have transferred all issues).