WGANGP model - how does _build_adversarial work

[gibki123]

I am wondering how _build_adversarial method works. I see that This method is called only once during WGANGP init. I keep asking myself how line :
self.set_trainable(self.generator, False)
can work every iteration if this method is called only once
And also how RandomWeightedAverage images can be counted every iteration?

Can somebody explain this to me? This is probably some functionality of Keras but I cant see this