search

sergeytulyakov / mocogan

MoCoGAN: Decomposing Motion and Content for Video Generation
573 stars 113 forks source link

Discriminators structures are not same as in paper? #9

Closed chmxu closed 6 years ago

chmxu commented 6 years ago

Hi, I've read the MocoGAN paper and in the supplementary materials and it said that stride and padding of 3D Conv in Dis_v are "equal for all the dimensions in each layer", which is obviously different from your code. So which one is the actual one you used in your paper?

sergeytulyakov commented 6 years ago

Hi,

I assume you mean video discriminators, thanks for pointing this out. I'll update the supplement. The code is this repository was used to generate all the results in the paper.