李宏毅GAN学习笔记（2）

GAN Lecture 2

Conditional Generation by GAN

Algorithm

In each traing iteration:

  • Sample m positive examples \{(c^1, x^1), (c^2, x^2), \dots, (c^m, x^m)\} from database
  • Sample m noise samples \{z^1, z^2, \dots, z^m\} from a distribution
  • Obtaining generated data \{\tilde{x}^1, \tilde{x}^2, \dots, \tilde{x}^m\}, \tilde{x}^i=G(c^i, z^i)
  • Sample m objects \{\hat{x}^1, \hat{x}^2, \dots, \hat{x}^m\} from database
  • Update discriminator parameters \theta_d to maximize
    • \tilde{V}=\frac{1}{m}\sum_{i=1}^mlogD(c^i, x^i)+\frac{1}{m}\sum_{i=1}^mlog(1-D(c^i, \tilde{x}^i))+\frac{1}{m}_{i=1}^mlog(1-D(c^i, \hat{x}^i))
    • \theta_d \leftarrow \theta_d+\eta\bigtriangledown\tilde{V}(\theta_d)

Learning D

  • Sample m noise samples \{z^1,z^2,\dots,z^m\} from a distribution
  • Sample m conditions \{c^1,c^2,\dots,c^m\} from a database
  • Update generator parameters \theta_g to maximize
    • \tilde{V}=\frac{1}{m}\sum_{i=1}^mlog(D(G(c^i, z^i))), \theta_g \leftarrow\eta\bigtriangledown\tilde{V}(\theta_g)

Learning G

倾向推荐第二种网络架构
参考文献：StackGAN

参考文献：Patch GAN

参考例子：Github

©著作权归作者所有,转载或内容合作请联系作者
平台声明：文章内容（如有图片或视频亦包括在内）由作者上传并发布，文章内容仅代表作者本人观点，简书系信息发布平台，仅提供信息存储服务。

推荐阅读更多精彩内容