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 O’Reilly online learning.

O’Reilly members experience live online training, plus books, videos, and digital content from 200+ publishers.