Skip to content

doodleryul/S3VAE

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

13 Commits
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

S3VAE

Unofficial implementation of S3VAE with pytorch
This repository is inspired by here

Data

The Moving MNIST dataset contains 10,000 video sequences, each consisting of 20 frames. In each video sequence, two digits move independently around the frame, which has a spatial resolution of 64×64 pixels. The digits frequently intersect with each other and bounce off the edges of the frame.
More details

Results

original moving mnist

gif gif gif gif gif gif gif gif gif gif gif


generated moving mnsit

gif gif gif gif gif gif gif gif gif gif gif

How to use

python click/predict.py generate-moving-mnist -c s3vae_config.yaml

To Do

  • fix mutual information loss
  • edit wandb log name

About

Unofficial implement S3VAE with pytorch

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages