search

eriklindernoren / PyTorch-GAN

PyTorch implementations of Generative Adversarial Networks.
MIT License
16.22k stars 4.05k forks source link

Is there a certain reason you update the G first? #114

Open yoon28 opened 4 years ago

yoon28 commented 4 years ago

Hi! First, thank you for sharing your code. I appreciate it. And, I have a question about your code. Is there a specific reason why you update the G first rather than the D? I know that it is normal to update the D first at each iteration.

Sean16SYSU commented 4 years ago

It doesn't matter which model updates first, because we use mini-batch not entirely same as the mathematical analysis in GAN.