Some tricks when training your GAN

 

Abstract

TTUR

the paper in the [1]

Reference

  1. Heusel M, Ramsauer H, Unterthiner T, et al. Gans trained by a two time-scale update rule converge to a local nash equilibrium[J]. Advances in neural information processing systems, 2017, 30.
更新于

chenkaixu

闭关修炼中。