ganhacks
starter from "How to Train a GAN?" at NIPS2016
...It recommends architectural practices involving batch normalization, LeakyReLU, and convolutional upsampling. Additional techniques include label smoothing, noisy labels, experience replay, and instance noise. Researchers can also explore optimizer selection, discriminator training strategies, and early failure detection. The repository includes references to relevant academic papers and implementations. Its recommendations are historically influential but are not maintained as current best practices.