Quantization Debugger Colab Crash

[pavel-macenauer-nxp]

Describe the current behavior
When running https://colab.research.google.com/github/tensorflow/tensorflow/blob/master/tensorflow/lite/g3doc/performance/quantization_debugger.ipynb the notebook crashes on the "Boilerplates and helpers" section.

---------------------------------------------------------------------------
ValueError                                Traceback (most recent call last)
[<ipython-input-16-f5bd5b09859a>](https://localhost:8080/#) in <cell line: 43>()
     41 
     42 
---> 43 model = tf.keras.Sequential([
     44   tf.keras.layers.Input(shape=(224, 224, 3), batch_size=1),
     45   hub.KerasLayer(MODEL_URI)

1 frames
[/usr/local/lib/python3.10/dist-packages/keras/src/models/sequential.py](https://localhost:8080/#) in add(self, layer, rebuild)
     95                 layer = origin_layer
     96         if not isinstance(layer, Layer):
---> 97             raise ValueError(
     98                 "Only instances of `keras.Layer` can be "
     99                 f"added to a Sequential model. Received: {layer} "

ValueError: Only instances of `keras.Layer` can be added to a Sequential model. Received: <tensorflow_hub.keras_layer.KerasLayer object at 0x7b77f8034610> (of type <class 'tensorflow_hub.keras_layer.KerasLayer'>)

Describe the expected behavior
Does not crash.

What web browser you are using
Chrome.

Additional context

import tf_keras as tfk
...
model = tfk.Sequential([
  tfk.layers.Input(shape=(224, 224, 3), batch_size=1),
  hub.KerasLayer(MODEL_URI)
])

The above fixes the issue, it's caused by incompatible keras version.