A KerasTensor cannot be used as input to a TensorFlow function

Course Q&A TensorFlow: Advanced Techniques Specialization Generative Deep Learning with TensorFlow
1

ValueError: A KerasTensor cannot be used as input to a TensorFlow function. A KerasTensor is a symbolic placeholder for a shape and dtype, used when constructing Keras Functional models or Keras Functions. You can only use it as input to a Keras layer or a Keras operation (from the namespaces keras.layers and keras.operations). You are likely doing something like:

x = Input(...)
...
tf_fn(x)  # Invalid.

What you should do instead is wrap tf_fn in a layer:

class MyLayer(Layer):
    def call(self, x):
        return tf_fn(x)

x = MyLayer()(x)

Define our loss functions

2

What is the problem here?

3

are you trying to run codes locally? in your system?

4

can you please explain your problem briefly, and what’s the main causes you are suffering from ?