DequanZhu/GANs-collections-tf2.0_keras-eager_mode DequanZhu/GANs-collections-tf2.0_keras-eager_mode

  • Stars
    star
    134
  • Rank 269,431 (Top 6 %)
  • Language
    Python
  • Created over 5 years ago
  • Updated about 1 year ago
Twitter logo Share LinkedIn logo Share Facebook logo Share
DequanZhu/GANs-collections-tf2.0_keras-eager_mode
github

DequanZhu

Reviews

There are no reviews yet. Be the first to send feedback to the community and the maintainers!

Repository Details

This repository implements all kinds of GAN-models based on tensorflow2.0 keras API including GAN, CGAN, WGAN, WGAN_GP, VAE, CVAE, LSGAN, infoGAN, EBGAN, BEGAN, ACGAN

Description

This repository implements all kinds of GAN-models based on tensorflow2.0 keras API and in eager mode. The code was only validated on windows platform and just cpu mode.

How to use

Install tensorflow2.0-aplha version. Anaconda virtual enviroment is recommended. To support GPU mode,please refer to this(I haven't validated on GPU beacuse have no GPU to use).

TODO

  • To implement ACGAN, EBGAN, BEGAN, etc.
  • Support GPU run.

More Repositories

1

FaceNet-and-FaceLoss-collections-tensorflow2.0

Facenet implemented by tensorflow2.0-keras api and in eager-mode support CenterLoss, LSoftmaxLoss, L2SoftmaxLoss, AMSoftmaxLoss, ASoftmaxLoss, ArcFaceSoftmaxLoss
Python
118
star