How to implement self attention Generator and Discriminator in Conditional Generative Adversarial Nets

Question

We have a CGAN built with a generator and a discriminator built using neural networks. How can we change the code to implement the same logic using self attention generator and discriminators?

Our code.

Answer 1

I think you can get some help from here self-attention using keras. Though I myself cannot solve your problem. As a beginner I would also like to know the answer.