Home
Projects
Resources
Alternatives
Blog
Sign In
DLHacks Mocogan
Save
A pytorch implemention of MoCoGAN
Overview
Reviews
Resources
Project README
MoCoGAN: Decomposing Motion and Content for Video Generation
Powered by
DL HACKS
Description
A pytorch implmention of MoCoGAN
authors: Sergey Tulyakov, Ming-Yu Liu, Xiaodong Yang, Jan Kautz
arxiv:
https://arxiv.org/abs/1707.04993
project page:
https://github.com/sergeytulyakov/mocogan
Implemention
you need to place datasets([run, walk, skip, ......])
here
under 'raw_data' dir.
python resize.py
: resize your raw data as 96x96 and place them under resized_data dir.
python train.py
: train MoCoGAN.
Results
Requirements
python 3.5
pytorch 0.2
numpy
skvideo
ffmgeg (for preprocessing and saving videos)
References
L.Gorelick,M.Blank,E.Shechtman,M.Irani,andR.Basri. Actions as space-time shapes. PAMI, 29(12):2247–2253, 2007.
http://www.wisdom.weizmann.ac.il/%7Evision/SpaceTimeActions.html
(datasets)
https://github.com/pytorch/examples/tree/master/dcgan
Open Source Agenda is not affiliated with "DLHacks Mocogan" Project. README Source:
DLHacks/mocogan
Stars
103
Open Issues
3
Last Commit
6 years ago
Repository
DLHacks/mocogan
Tags
Image Processing
Machine Learning
Pytorch Implmention
Open Source Agenda Badge
Submit Review
Review Your Favorite Project
Submit Resource
Articles, Courses, Videos
Submit Article
Submit a post to our blog
From the blog
Dec 11, 2022
How to Choose Which Programming Language to Learn First?
From the blog
Dec 11, 2022
How to Choose Which Programming Language to Learn First?
Home
Projects
Resources
Alternatives
Blog
Sign In
Sign In to OSA
I agree with
Terms of Service
and
Privacy Policy
Sign In with Github