Python Deep Learning - Second Edition

Training the generator

We'll train the generator by making it better at deceiving the discriminator. To do this, we'll need both networks, similar to the way we train the discriminator with fake samples:

1. We start with a random latent vector, , and feed it through both the generator and discriminator, to produce the output, .

2. The loss function is the same as the discriminator loss. However, our goal here is to maximize it, rather than minimize it, since we want to deceive the discriminator.
3. In the backward pass, the discriminator weights, ...