Giters

Kaixhin / Autoencoders

Torch implementations of various types of autoencoders

Geek Repo:Geek Repo

Github PK Tool:Github PK Tool

Using Gradient reversal for AAE

ssakhavi opened this issue · comments

commented

Hi

For the AAE,

I noticed that instead of using a gradient reversal layer, you back propagated the loss when the fake samples are real.

Is this correct?

commented

Good question! I originally took the adversarial training bit from soumith/dcgan.torch, so I'd hope that it was fine. And actually it corresponds to a little change in the objective which is explained in the original GAN paper (search for "fixed point"). Whether or not this is the best solution is a matter of active research for some people.

If you do note anything strange with the maths then do let me know as I hope that this is a useful resource for people, both theoretically and practically :)