-
Notifications
You must be signed in to change notification settings - Fork 116
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
Image classification with ConvMixer - Converted to Keras Core by: @divyashreepathihalli #387
Conversation
divyashreepathihalli
commented
Jun 21, 2023
- 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.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
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/vision
if its backward agnostic?
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
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 |
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). |