search

LantaoYu / SeqGAN

Implementation of Sequence Generative Adversarial Nets with Policy Gradient
2.08k stars 711 forks source link

About generator in adversarial training #63

Open xieexiaotuzi opened 5 years ago

xieexiaotuzi commented 5 years ago

Hi, I am very interested in your work. About 'g, d and k', I think 'g' means one epoch in the paper. But in code, I think it may be one batch. So, could u help me with it ? Thanks a lot.

MichaelZhouwang commented 5 years ago

I think it is one batch, which is a common practice in GANs.

xieexiaotuzi commented 5 years ago

I think it is one batch, which is a common practice in GANs.

thanks a lot. I will have a try.