255BITS/HyperGAN

A versatile GAN(generative adversarial network) implementation focused on scalability and ease-of-use. Configuration in HyperGAN uses JSON files. You can create a new config by running hypergan train. A hypergan configuration contains multiple encoders, multiple discriminators, multiple loss functions, and a single generator. A generator is responsible for projecting an encoding (sometimes called z space) to an output (normally an image).