Created
October 22, 2016 02:10
-
-
Save awjuliani/c9ecd8b37d33d6855cd4ed9aa16ce89f to your computer and use it in GitHub Desktop.
An implementation of InfoGAN.
Also it looks like the continuous Q loss is a reconstruction error, not conditional entropy? Where are the log-likelihoods as in https://github.com/openai/InfoGAN/blob/master/infogan/algos/infogan_trainer.py#L87
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Love the minimalism of this example.
One question -- it seems here that G is only being optimized to fool D, but not at all wrt maximizing mutual information via Q. Is this the case, or is G getting gradients from somewhere I'm missing?
For reference, in the infoGAN paper it suggests (right under eq (5)) "LI can be maximized w.r.t. Q directly and w.r.t. G via the reparametrization trick" and lines 82 and 97 of https://github.com/openai/InfoGAN/blob/master/infogan/algos/infogan_trainer.py are adding Q losses to the generator loss, which presumably propagates the Q errors through G as well.