ValueError: Only instances of keras.Layer can be added to a Sequential model. Received: <tensorflow_hub.keras_layer.KerasLayer object at 0x7a9a39daf130> (of type <class 'tensorflow_hub.keras_layer.KerasLayer'>)

[moatednorth]

Sequential api can't handle hub.KerasLayer

`

Create a Keras Layer using the USE pretrained layer from Kaggle

sentence_encoder_layer = hub.KerasLayer("https://www.kaggle.com/models/google/universal-sentence-encoder/TensorFlow2/universal-sentence-encoder/2",
input_shape=[],
dtype=tf.string,
trainable=False,
name="USE")

Create model using the Sequential API

model_6 = tf.keras.Sequential([
sentence_encoder_layer,
layers.Dense(64, activation="relu"),
layers.Dense(1, activation="sigmoid", name="ouput_layer")
], name="model_6_USE")
`

[arrshsh]

Same issue, please do let me know if you find some solution around this issue

[masrik-dev]

Could you let me know if you found the solution?

[Anand-Velpuri]

I believe the following code snippet provides a solution or a starting point to address the problem. It outlines how to properly build a Keras model that incorporates a TensorFlow Hub layer.

def hub_layer_fn(x):
    return hub.KerasLayer(MODEL_URL, trainable=False)(x)

import tensorflow as tf
import tensorflow_hub as hub

# Create a function which builds a Keras model
def create_model(input_shape=INPUT_SHAPE, output_shape=OUTPUT_SHAPE, model_url=MODEL_URL):
    print("Building model with:", model_url)

    # Setup the model layers
    model = tf.keras.Sequential([
        tf.keras.layers.Lambda(hub_layer_fn, name="hub_lambda"),  # Wrap the hub.KerasLayer in Lambda
        tf.keras.layers.Dense(units=output_shape, activation="softmax")  # Output layer with softmax activation
    ])

    # Compile the model
    model.compile(
        loss=tf.keras.losses.CategoricalCrossentropy(),
        optimizer=tf.keras.optimizers.Adam(),
        metrics=["accuracy"]
    )

    # Build the model
    model.build((None, *input_shape))  # Ensure input shape is unpacked correctly

    return model

This function create_model takes input_shape, output_shape, and model_url as parameters and constructs a tf.keras.Sequential model. It uses a tf.keras.layers.Lambda layer to wrap the TensorFlow Hub layer (represented by hub_layer_fn, which you would need to define based on how you are loading the Hub module). This approach can sometimes resolve compatibility or layering issues.

Please ensure you have INPUT_SHAPE, OUTPUT_SHAPE, MODEL_URL, and hub_layer_fn defined according to your specific use case.

Another Example:

resnet_url = "https://www.kaggle.com/models/google/resnet-v2/TensorFlow2/50-feature-vector/2"

efficientnet_url = "https://www.kaggle.com/models/tensorflow/efficientnet/TensorFlow2/b0-feature-vector/1"

# Import dependencies
import tensorflow as tf
import tensorflow_hub as hub
from tensorflow.keras import layers

def create_model(model_url, num_classes=10):
  """
  Takes a TensorFlow Hub URL and creates a Keras Sequential model with it.

  Args:
    model_url (str): A TensorFlow Hub feature extraction URL.
    num_classes (int): Number of output neurons in the output layer,
    should be equal to number of target classes, default 10.
  
  Returns:
    An uncompiled keras Sequential model with model_url as feature extarctor
    layer and Dense output layer with num_classes output neurons.
  """
  # Download the pretrained model and save it as a keras layer
  feature_extractor_layer = hub.KerasLayer(model_url,
                                           trainable=False, # Freeze the already learned patterns
                                           name="feature_extraction_layer",
                                           input_shape=IMAGE_SHAPE+(3,)
                                           )
  
  # Create our own model
  model = tf.keras.Sequential([
      layers.Lambda(feature_extractor_layer, name="hub_lambda"),
      layers.Dense(num_classes, activation="softmax", name="output_layer")
  ])

  model.build((None, *(IMAGE_SHAPE+(3,))))

  return model

# Create Resnet model
resnet_model = create_model(resnet_url,
                            num_classes=train_data_10_percent.num_classes
                            )

resnet_model.summary()

For more info check out my Dog Vision Project Notebook: https://github.com/Anand-Velpuri/Dog-Vision/blob/main/dog-vision.ipynb

Let me know if this helps resolve the issue!

Best regards,
@Anand-Velpuri

[naman22a]

use tf-keras
pip install tf-keras
import tf_keras as keras
replace tf.keras with keras

[mechaitanyashintre]

Hi guys, I am also getting same issue, what is the final fix for the same, please help!

[masrik-dev]

I used tf_keras.

Custom wrapper layer so Sequential accepts it: Use the code from stackoverflow to solve the problem of Sequential accepting the layers from resnet_url or others. Link: https://stackoverflow.com/questions/78530756/error-only-instances-of-keras-layer-can-be-added-to-a-sequential-model

If you face any problem in future, which you will. you can check here: https://github.com/masrik-dev/Deep-Learning-with-TensorFlow-and-Python

[mechaitanyashintre]

Thanks for the help, it worked!