Hi @zzj0402 ,

The code executes fine on Colab as per gist. This moght be related to Kaggle environment which might have incompatible TF and tensorflow_hub version. You may check the Tensorflow and tensorflow_hub in kaggle environment and try to install those works in locally. Neverthless it's not problem with Tensorflow or Keras.

Thanks!

i got the same issue also with Kaggle's environment, with @SuryanarayanaY conclusion i got the solution by just
pip install tensorflow
again and found out that the keras library reinstalls to latest version

!pip install tensorflow

fixes the problem in Kaggle.

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

i had the same issue, tried all the things explained here but still having the same issue. i am not using kaggle i am coding on jupyter notebook. please help

@Kun7l I am also having same issue. I am using jupyter notebook as well with PyCharm. I have tried many things but cannot fix this error. I believe it might be a package incompatibility error. However, I am using most up to date versions.

im also having this using conda, tried conda install again tensorflow and it no compatible with tensorflow_hub that i installed before, please help

Has someone resolved this for jupyter notebook / conda enviroment? I am also having a similar problem (although with tensorflow probability)

I got the same error when running the official notebook, https://www.tensorflow.org/tutorials/interpretability/integrated_gradients, the environment I am using is tensorflow==2.16 and tensorflow-hub==0.16.
But if I roll back to tensorflow 2.14 and tensorflow-hub 0.15, there is no such error.

I've tried to use some previous versions of tensorflow, but on MacOS there was another bug that was't allowing me to use GPU acceleration. So I've solved the problem using the Model Subclassing API, here the example from my code:

class MyModel(keras.Model):
  def __init__(self):
    super(MyModel, self).__init__()
    self.embedding_layer = embed
    self.dense_layer1 = layers.Dense(256, activation='relu')
    self.dense_layer2 = layers.Dense(128, activation='relu')
    self.dense_layer3 = layers.Dense(64, activation='relu')
    self.output_layer = layers.Dense(13, activation='softmax')

  def call(self, inputs):
    x = self.embedding_layer(inputs)
    x = self.dense_layer1(x)
    x = self.dense_layer2(x)
    x = self.dense_layer3(x)
    return self.output_layer(x)

do anyone know how to resolve this error, i have been trying and reinstalling the tensorflow to its latest but still its gets the error

i cant even install older version of tensorflow the oldest i can install in 2.16

Consegui añadir el modelo con una lambda

import tensorflow_hub as hub

Cargar el modelo base preentrenado

base_model = hub.KerasLayer("https://www.kaggle.com/models/google/mobilenet-v3/TensorFlow2/large-075-224-classification/1",
trainable=True, arguments=dict(batch_norm_momentum=0.997))

Construir el modelo

model = tf.keras.Sequential([
# Capa de entrada
tf.keras.layers.InputLayer(input_shape=(224, 224, 3)),

# Envolver la capa del modelo base en una capa Lambda
tf.keras.layers.Lambda(lambda x: base_model(x)),

tf.keras.layers.Dropout(0.2),

# Capa densa final para clasificación
tf.keras.layers.Dense(3, activation='softmax')

])

Compilar el modelo

model.compile(
optimizer=tf.keras.optimizers.Adam(learning_rate=0.0001),
loss='sparse_categorical_crossentropy',
metrics=['accuracy']
)

Callbacks

early_stopping = tf.keras.callbacks.EarlyStopping(patience=10, restore_best_weights=True)
reduce_lr = tf.keras.callbacks.ReduceLROnPlateau(factor=0.2, patience=5, min_lr=1e-6)

model.summary()

For colab users: by downgrading your Tensorflow and TensorHub
!pip install tensforflow == 2.8.0 and tensorflow_hub == 0.12.0

For Jupyter Notebook users:
I have installed these version of Tensorflow and tersorflow_hub:
TensorFlow version: 2.14.0
TensorFlow Hub version: 0.15.0

and changes input_shape from [None,224, 224, 3] to [224, 224, 3] (removed batch value)
and these changes resolved the issue for me.

!pip install tensorflow

fixes the problem in Kaggle.

The error pops up again. Seems like version issue.

fixed with:

!pip install tensorflow==2.15.0 tensorflow-hub keras==2.15.0

This is definitely a Tensorflow issue where the package management fails to check backward capability.

Hi @SuryanarayanaY , you forgot to run build_model(embed) on your gist, when run, it will raise exactly the same error.

you have to wrap the hub layer in a Lambda layer like below:

import tensorflow as tf
import tensorflow_hub as hub

 # Wrap the hub layer in a Lambda layer

hub_layer_wrapper = tf.keras.layers.Lambda(lambda x: hub_layer(x))

model = tf.keras.Sequential([
    hub_layer_wrapper,  # Use the wrapped layer
    tf.keras.layers.Dense(16, activation='relu'),
    tf.keras.layers.Dense(1, activation='sigmoid')
])

model.summary()

I fix my code by using lambda layer
I hope it is useful for you

i cant even install older version of tensorflow the oldest i can install in 2.16

Same, I can only install the version starting from 2.16.1

(.venv) PS D:\fastapi> pip install --no-cache-dir tensorflow==2.15.0
ERROR: Could not find a version that satisfies the requirement tensorflow==2.15.0 (from versions: 2.16.0rc0, 2.16.1, 2.16.2, 2.17.0rc0, 2.17.0rc1, 2.17.0)
ERROR: No matching distribution found for tensorflow==2.15.0

Tensorflow 2.17 contains Keras3.0 which might be the reason for the error. Could you please try to install tf-keras i.e., keras2.0 and try to test the code and the if the issue is present, please raise the issue in the keras-team/keras repo as it is more related to Keras.

!pip install tf-keras
import tf_keras as keras

Thank you!

This issue is stale because it has been open for 7 days with no activity. It will be closed if no further activity occurs. Thank you.

This issue was closed because it has been inactive for 7 days since being marked as stale. Please reopen if you'd like to work on this further.

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

fixed with:

!pip install tensorflow==2.15.0 tensorflow-hub keras==2.15.0

This is definitely a Tensorflow issue where the package management fails to check backward capability.

Thanks, this worked for me