After searching i found out that potential cause of the issue in tensorflow_hub/keras_layer.py

this is issue is occuring only in keras version > 3.X.X

solution :

Use Keras 2.

version_fn = getattr(tf.keras, "version", None)
if version_fn and version_fn().startswith("3."):
import tf_keras as keras
else:
keras = tf.keras

👉🏻 #63849 (comment)

from tensorflow.

Try to use Keras 2. version 👍🏻

import tensorflow as tf
from tensorflow import keras
print(tf.version)
2.16.1

import keras
print(keras.version)
3.2.0

import tf_keras
print(tf_keras.version)
2.16.0

from tensorflow.

@Pavun-KumarCH Thank you for your responses here.
You can continue using Keras 2 or later with a workaround. That is to wrap the TensorFlow Hub layer returned by tf.keras.layers.experimental.load in a keras.Layer object before adding it to your model.

Please let us know if we can move this issue to closed status as it is resolved from your side?

Thank you!

from tensorflow.

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

from tensorflow.