Python Deep Learning - Second Edition

Conditional GANs

Conditional GANs (CGANs) are an extension of the GAN framework where both the generator and discriminator receive some additional conditioning input information,. This could be the class of the current image or some other property.

For example, if we train a GAN to generate new MNIST images, we could add an additional input layer with values of one-hot-encoded image labels:

Conditional GAN

CGANs have the one disadvantage that are not strictly unsupervised and we need some kind of labels for them to work. However, they have some ...