Skip to content

Pytorch implementation of SphereGAN(Sphere Generative Adversarial Network Based on Geometric Moment Matching)

License

Notifications You must be signed in to change notification settings

Dotori-HJ/SphereGAN-Pytorch-implementation

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

3 Commits
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

SphereGAN-Pytorch-implementation

Pytorch implementation of SphereGAN(Sung Woo Park and Junseok Kwon)

cf) The Generator and Discriminator structures is not the same in the paper. In this repository, the Generator and Discriminator structures are used DCGAN's structures.

Requirments

Code is written in Python 3.7.3(Pytorch 1.1.0) and requires:

  • Pytorch
  • tqdm

Run the example

MNIST, CIFAR-10

python main.py --dataset mnist
python main.py --dataset cifar10

Results

MNIST

mnist_random

CIFAR-10

cifar10_random

Reference

Sphere Generative Adversarial Network Based on Geometric Moment Matching

Sung Woo Park and Junseok Kwon. "Sphere Generative Adversarial Network Based on Geometric Moment Matching." Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 2019.

About

Pytorch implementation of SphereGAN(Sphere Generative Adversarial Network Based on Geometric Moment Matching)

Topics

Resources

License

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages