[BUG] SVAE problems with TypeError: You are passing KerasTensor

[Peanpepu]

Description

In the example code examples/02_model_collaborative_filtering/standard_vae_deep_dive.ipynb I find an error like this one :
TypeError: You are passing KerasTensor(type_spec=TensorSpec(shape=(), dtype=tf.float32, name=None), name='Placeholder:0', description="created by layer 'tf.cast_2'"), an intermediate Keras symbolic input/output, to a TF API that does not allow registering custom dispatchers, such as tf.cond, tf.function, gradient tapes, or tf.map_fn. Keras Functional model construction only supports TF API calls that do support dispatching, such as tf.math.add or tf.reshape. Other APIs cannot be called directly on symbolic Kerasinputs/outputs. You can work around this limitation by putting the operation in a custom Keras layer call and calling that layer on this symbolic input/output.

I have tried changing the libraries it uses, but I found no solution. The error occurs in the snippet code
model_without_anneal = StandardVAE(n_users=train_data.shape[0], # Number of unique users in the training set
original_dim=train_data.shape[1], # Number of unique items in the training set
intermediate_dim=INTERMEDIATE_DIM,
latent_dim=LATENT_DIM,
n_epochs=EPOCHS,
batch_size=BATCH_SIZE,
k=TOP_K,
verbose=0,
seed=SEED,
save_path=WEIGHTS_PATH,
drop_encoder=0.5,
drop_decoder=0.5,
annealing=False,
beta=1.0
)
with Timer() as t:
model_without_anneal.fit(x_train=train_data,
x_valid=val_data,
x_val_tr=val_data_tr,
x_val_te=val_data_te_ratings, # with the original ratings
mapper=am_val
)

In which platform does it happen?

I am using VScode but I'm sure it is not the problem.

How do we replicate the issue?

Install pip install pandera==0.15.1 and execute the code.

Expected behavior (i.e. solution)

It should train the model without problems.

Willingness to contribute

• Yes, I can contribute for this issue independently.
• Yes, I can contribute for this issue with guidance from Recommenders community.
• No, I cannot contribute at this time.

Other Comments

I am using others versions of libraries because installing those older versions gave me some problems. I'm using:

• System version: 3.10.12 (main, Nov 6 2024, 20:22:13) [GCC 11.4.0]
• Pandas version: 2.2.3
• Tensorflow version: 2.13.0
• Keras version: 2.13.1
  The libraries are used in the original code:
• System version: 3.6.9 (default, Jul 17 2020, 12:50:27) [GCC 8.4.0]
• Pandas version: 1.1.2
• Tensorflow version: 2.2.0-rc1
• Keras version: 2.3.1