Closed edgarriba closed 7 years ago
We found out that in some cases assigning the same ratio to GAN loss and reconstruction loss fails to generate decent results. We guessed this occurred since training with GAN loss is much harder than training with reconstruction loss, especially in the early phase, and this curriculum strategy worked for those cases.
Carpedm20's code was independently implemented before we made this repo public, and his and ours have no authorship relation.
so then I guess that the formulas from the paper need a slight modification. Besides, starting_rate
and default_rate
have both the same value. Is it correct?
Thanks for pointing it out. We will consider making that change in our v2 paper.
starting_rate
and default_rate
are equal only in angle_pairing.py
.
great!
in lines 251-252 you apply curriculum learning to compute the total gan loss. What's the motivation for that? Cannot find it in the paper.
Besides, is there any authorship relation between this repo and https://github.com/carpedm20/DiscoGAN-pytorch ?