Tensorflow

Mixing keras and tf.keras is bad karma; only the same one should be used and it should be tf.keras.

Tensorflow Keras stuff outside layers

AttributeError:’Tensor’ object has no attribute ‘_keras_history’ – inneka.com

Everything should be done by:

  • Using keras.backend functions,
  • Lambda layers,
  • Designated keras functions with the same behavior.

When you are using tf operation – you are getting tf tensor object which doesn’t have history field. When you use keras functions you will get keras.tensors.