Skip to content

A simple variational autoencoder to learn handwritten alphabets

Notifications You must be signed in to change notification settings

vinsis/fonts-vae-pytorch

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

3 Commits
 
 
 
 
 
 
 
 
 
 

Repository files navigation

fonts-vae-pytorch

Data source: https://www.kaggle.com/gregvial/comnist

Images generated with latent variables of size 1:

Images are blurred (as expected).

Images generated with latent variables of size 25:

Much better images with a bigger latent size.

About

A simple variational autoencoder to learn handwritten alphabets

Topics

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages