Does not run when using the official sample code for Keras3

[z4668640]

Issue Type

Documentation Bug

Source

binary

Keras Version

Keras 3.4.1

Custom Code

No

OS Platform and Distribution

Windows

Python version

3.12.4

GPU model and memory

Nvidia A3000

Current Behavior?

I got an error when using the official Keras3 instance code.
When I took the last step of training I got the following error:
AttributeError: 'list' object has no attribute 'shape'

Standalone code to reproduce the issue or tutorial link

Using the original code, no changes.
https://github.com/keras-team/keras-io/blob/master/guides/custom_train_step_in_torch.py

Relevant log output

---------------------------------------------------------------------------
AttributeError                            Traceback (most recent call last)
Cell In[5], line 22
     15 gan = GAN(discriminator=discriminator, generator=generator, latent_dim=latent_dim)
     16 gan.compile(
     17     d_optimizer=keras.optimizers.Adam(learning_rate=0.0003),
     18     g_optimizer=keras.optimizers.Adam(learning_rate=0.0003),
     19     loss_fn=keras.losses.BinaryCrossentropy(from_logits=True),
     20 )
---> 22 gan.fit(dataloader, epochs=1)

File c:\Users\C\miniconda3\envs\learn100\Lib\site-packages\keras\src\utils\traceback_utils.py:122, in filter_traceback.<locals>.error_handler(*args, **kwargs)
    119     filtered_tb = _process_traceback_frames(e.__traceback__)
    120     # To get the full stack trace, call:
    121     # `keras.config.disable_traceback_filtering()`
--> 122     raise e.with_traceback(filtered_tb) from None
    123 finally:
    124     del filtered_tb

Cell In[4], line 27
     25     real_images = real_images[0]
     26 # Sample random points in the latent space
---> 27 batch_size = real_images.shape[0]
     28 random_latent_vectors = keras.random.normal(
     29     shape=(batch_size, self.latent_dim), seed=self.seed_generator
     30 )
     32 # Decode them to fake images

AttributeError: 'list' object has no attribute 'shape'

[github-actions]

Are you satisfied with the resolution of your issue?
Yes
No