eriklindernoren / Keras-GAN

Keras implementations of Generative Adversarial Networks.
MIT License
9.19k stars 3.14k forks source link

(WGAN_GP)BatchNormalization in critic #253

Open yanranjiang opened 3 years ago

yanranjiang commented 3 years ago

In the paper "Improved Training of Wasserstein GANs" (https://papers.nips.cc/paper/2017/file/892c3b1c6dccd52936e27cbd0ff683d6-Paper.pdf), authors think the model should not use batch normalization in both the generator and the discriminator. But why in the WGAN-GP code, they use batch normalization? BatchNormalization contains non-trainable parameters. How do they update the parameters in the code?