Skip to content

Latest commit

 

History

History
44 lines (28 loc) · 870 Bytes

README.md

File metadata and controls

44 lines (28 loc) · 870 Bytes

GAN and WGAN-GP

GAN and WGAN-gp implemented with pytorch and test on the mnist dataset

Installation

Clone this repo:

  git clone https://github.com/ZDDWLIG/WGAN-GP.git
  cd path/to/GAN-pytorch-master

Use conda to manage the python environment:

  conda create -n GAN python=3.8
  conda activate GAN
  pip install -r requirements.txt

Train

For example, if you want to train WGAN-gp , then run:

  python WGAN-GP.py

MNIST test results

Epoch 0

epoch0

Epoch 40

epoch40

Epoch 160

epoch160

Loss

Loss