李宏毅GAN學(xué)習(xí)筆記(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

傾向推薦第二種網(wǎng)絡(luò)架構(gòu)
參考文獻:StackGAN

參考文獻:Patch GAN

參考例子:Github

?著作權(quán)歸作者所有,轉(zhuǎn)載或內(nèi)容合作請聯(lián)系作者
【社區(qū)內(nèi)容提示】社區(qū)部分內(nèi)容疑似由AI輔助生成,瀏覽時請結(jié)合常識與多方信息審慎甄別。
平臺聲明:文章內(nèi)容(如有圖片或視頻亦包括在內(nèi))由作者上傳并發(fā)布,文章內(nèi)容僅代表作者本人觀點,簡書系信息發(fā)布平臺,僅提供信息存儲服務(wù)。

相關(guān)閱讀更多精彩內(nèi)容

友情鏈接更多精彩內(nèi)容