diff --git a/doc/design/gan_api.md b/doc/design/gan_api.md index 2fb30432cb4f068f9f443a037be4ad80dc9f14e7..f9bf5939f4aaa716e28230a7b716911f99e2beb0 100644 --- a/doc/design/gan_api.md +++ b/doc/design/gan_api.md @@ -29,13 +29,13 @@ In our GAN design, we wrap it as a user-friendly easily customized python API to


-The overall running logic of GAN. The black solid arrows indicate the forward pass; the green dashed arrows indicate the backward pass of generator training; the red dashed arrows indicate the backward pass of the discriminator training. The BP pass of the green (red) arrow should only update the parameters in the green (red) boxes. The diamonds indicate the data providers. d\_loss and g\_loss mared in red and green are the two targets we would like to run. +Figure 1. The overall running logic of GAN. The black solid arrows indicate the forward pass; the green dashed arrows indicate the backward pass of generator training; the red dashed arrows indicate the backward pass of the discriminator training. The BP pass of the green (red) arrow should only update the parameters in the green (red) boxes. The diamonds indicate the data providers. d\_loss and g\_loss marked in red and green are the two targets we would like to run.


-Photo borrowed from the original DC-GAN paper. +Figure 2. Photo borrowed from the original DC-GAN paper.

## The Conditional-GAN might be a class.