tjwei / GANotebooks

wgan, wgan2(improved, gp), infogan, and dcgan implementation in lasagne, keras, pytorch

Geek Repo:Geek Repo

Github PK Tool:Github PK Tool

Face-off dataset

Zingcekhusta opened this issue · comments

I would like to know which dataset you used for the face-off application.
How would I train videos for a face off purpose.
I am working on ubuntu 16.04

OK. See https://github.com/tjwei/GANotebooks/blob/master/CycleGAN-lasagne-fber.ipynb
This is pretty much a copy of CycleGAN-lasagne.ipynb
Except that the width and height of the image can be different.

The original videos can be found at
https://www.facebook.com/1471772763091863/videos/1932197823716019/
https://www.facebook.com/chenyi326/videos/10210708140002188/

The videos are cropped and one of the video was flipped, so that the head sizes are roughly matched and aligned.