Why multiply d_loss_real by num_gen - Githubissues

andrewgordonwilson / bayesgan

Tensorflow code for the Bayesian GAN (https://arxiv.org/abs/1705.09558) (NIPS 2017)

Other

1.02k stars 176 forks source link

Why multiply d_loss_real by num_gen #14

Open Xiaohui9607 opened 4 years ago

Xiaohui9607 commented 4 years ago

https://github.com/andrewgordonwilson/bayesgan/blob/ca06613201e0882a21e53f18e71ecbff5eda7923/bgan.py#L277