Skip to content

lhang33/Unsupervised-Cross-Domain-Image-Generation-Network

 
 

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

15 Commits
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

Unsupervised Cross Domain Image Generation

Unsupervised Cross Domain Image Generation.

To train this network, firstly! download my Unsuperviesed-Cross-Domain-Image-Generation-Network repository.

and then, put dataset what you want(SVHN_MNIST or CelebA_Anime) in dataset folder.

after then, you can train UCDIG Network.


I first trained my network by using MNIST and SVHN Dataset.

output is here.

img


And then, I tried training my network using CelebA and Anime Dataset.

output is under here.

the first and second images are outputs of 60epochs.

img4

the third and fourth, fifth images are outputs of 120epochs

img1

img2

img3


The Loss Graph is under here.

img5

About

Unsupervised Cross Domain Image Generation Network.

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages

  • Jupyter Notebook 100.0%