Advanced Deep Learning with Python

Putting it all together

With our newfound knowledge, we can define the minimax objective in full:

In short, the generator tries to minimize the objective, while the discriminator tries to maximize it. Note that, while the discriminator should minimize its loss, the minimax objective is a negative of the discriminator loss, and therefore the discriminator has to maximize it.

The following step-by-step training algorithm was introduced by the authors of the GAN framework.

Repeat this for a number of iterations:

1. Repeat for k steps, where k is a hyperparameter:
   • Sample a mini-batch of m random samples from the latent space,
   • Sample a mini-batch ...