Image classification with ConvMixer - Converted to Keras Core by: @divyashreepathihalli #387
Conversation
divyashreepathihalli
commented
Jun 21, 2023
divyashreepathihalli
commented
- fixed imports
- removed tfa dependency
- changed augmentations - swapped RandomCrop to RandomBrightness to avoid batch shape issue with RandomCrop(does not accept None shape)
This seems like a bug. Can you file a bug ticket with a reproduction script (something that works with tf.keras but doesn't work with Keras Core)? |
| import keras_core as keras | ||
|
|
||
| import matplotlib.pyplot as plt | ||
| import tensorflow as tf |
There was a problem hiding this comment.
Looks like you are only using tf.data. So, can you -
- import it as
from tensorflow import data as tf_data. - Verify that this example works with JAX backend as well.
- Keep the example at
examples/keras_io/visionif its backward agnostic?
There was a problem hiding this comment.
I updated the imports
regarding working with JAX, the colab results in errors when used with JAX backend. Because this conversion is part of stage 1 - (tf.keras backwards compatibility check) I have not tried to get it to work with jax.
filed an issue with repro here - #428 |
sachinprasadhs
added
the
stat:awaiting keras-eng
|
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 transferred PRs (but we have transferred all issues). |
