Training the GAN

Setting up a training flow for a generative adversarial network is not straight forward, as it demands a lot of technical considerations. We define three networks for training as follows:

  • The generator network g with parameters
  • The discriminator network d with parameters
  • The combined generator discriminator network denoted by g_d with weights and

The generator g creates fake images that the d discriminator would evaluate and ...

Get Intelligent Projects Using Python now with the O’Reilly learning platform.

O’Reilly members experience books, live events, courses curated by job role, and more from O’Reilly and nearly 200 top publishers.