• Stars
    star
    411
  • Rank 101,377 (Top 3 %)
  • Language
    Python
  • License
    MIT License
  • Created almost 7 years ago
  • Updated 12 months ago

Reviews

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

Repository Details

PyTorch Implementation of CycleGAN and SSGAN for Domain Transfer (Minimal)

MNIST-to-SVHN and SVHN-to-MNIST

PyTorch Implementation of CycleGAN and Semi-Supervised GAN for Domain Transfer.

alt text

Prerequites


Usage

Clone the repository

$ git clone https://github.com/yunjey/mnist-svhn-transfer.git
$ cd mnist-svhn-transfer/

Download the dataset

$ chmod +x download.sh
$ ./download.sh

Train the model

1) CycleGAN
$ python main.py --use_labels=False --use_reconst_loss=True
2) SGAN
$ python main.py --use_labels=True --use_reconst_loss=False

Results

1) CycleGAN (should be re-uploaded)

From SVHN to MNIST From MNIST to SVHN
alt text alt text
alt text alt text

2) SGAN

From SVHN to MNIST From MNIST to SVHN
alt text alt text
alt text alt text