How does call() work for a custom Keras layer?

Question

I am trying to build my own Keras layer by inheriting tf.keras.layers.Layer and I don't really understand what the call() method is doing. I have set my call() method to:

def call(self,inputs): 
    print('call')
    return inputs

When I run the.network, I would expect 'call' to be printed many times (with a training set of 100 examples and 10 epochs I would expect this to be printed 1000 times). However, 'call' is printed once when the model is built, then 3 times during the first epoch and then never again. Is my.network not using this layer in the subsequent epochs? Why is it only being called 3 times in the first epoch despite there being 100 training examples?

Answer 1

Call method automatically decorated by @tf.function. It means that keras builds dataflow graph on the first call and runs this graph on the next calls.

Calling python functions happening only on the first call. See details here - https://www.tensorflow.org/guide/function#debugging .

Answer 2

I am trying to build my own Keras layer by inheriting tf.keras.layers.Layer and I don't really understand what the call() method is doing. I have set my call() method to:

def call(self,inputs): 
    print('call')
    return inputs

When I run the network, I would expect 'call' to be printed many times (with a training set of 100 examples and 10 epochs I would expect this to be printed 1000 times). However, 'call' is printed once when the model is built, then 3 times during the first epoch and then never again. Is my network not using this layer in the subsequent epochs? Why is it only being called 3 times in the first epoch despite there being 100 training examples?