Skip to content

NYcleaner/TripleGAN-Tensorflow

 
 

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

39 Commits
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

TripleGAN-Tensorflow

Simple Tensorflow implementation of Triple Generative Adversarial Nets(Triple-GAN)

If you want to see the original author's code, please refer to this link

Issue

  • I am now modifying the weight normalization (If you know how to implement with tensorflow, let me know)

Usage

> python main.py --n 4000 --epoch 1000 --batch_size 20 --unlabel_batch_size 250 --z_dim 100
  • See main.py for other arguments.

Idea

Network Architecture

network

Algorithm

algorithm

Result

Classification result

c_result

Convergence speed on SVHN

s_result

My result (Cifar10, 4000 labelled image)

Loss

loss

Classification accuracy

accuracy

Generated Image (Other images are in assests)

Automobile

automobile

Related works

Reference

Author

Junho Kim

About

Simple Tensorflow implementation of Triple Generative Adversarial Nets (NIPS 2017)

Resources

License

Stars

Watchers

Forks

Releases

No releases published

Packages

 
 
 

Contributors

Languages

  • Python 100.0%