https://github.com/pfnet-research/chainer-LSGAN

Least Squares Generative Adversarial Network implemented in Chainer
https://github.com/pfnet-research/chainer-LSGAN

chainer chainer-lsgan gan lsgan

Last synced: 3 months ago
JSON representation

Least Squares Generative Adversarial Network implemented in Chainer

• Host: GitHub
• URL: https://github.com/pfnet-research/chainer-LSGAN
• Owner: pfnet-research
• License: mit
• Created: 2017-03-07T07:02:52.000Z (almost 8 years ago)
• Default Branch: master
• Last Pushed: 2017-12-11T01:20:54.000Z (about 7 years ago)
• Last Synced: 2024-08-02T12:21:52.305Z (6 months ago)
• Topics: chainer, chainer-lsgan, gan, lsgan
• Language: Python
• Homepage:
• Size: 324 KB
• Stars: 18
• Watchers: 3
• Forks: 9
• Open Issues: 0
• Metadata Files:
  • Readme: README.md
  • License: LICENSE.md

Awesome Lists containing this project

README

        
# chainer-LSGAN

An implementation of [_Mao et al., "Least Squares Generative Adversarial Networks" 2017_](https://arxiv.org/abs/1611.04076) using the [Chainer framework](http://chainer.org/). 

Disclaimer: PFN provides no warranty or support for this implementation. Use it at your own risk. See [license](LICENSE.md) for details.

Results

-------

CIFAR10 & MNIST for 100 epochs



   



Usage

-------

Tested using `python 3.5.1`. Install the requirements first:

```

pip install -r requirements.txt

```

Trains on the CIFAR10 dataset by default, and will generate an image of a sample batch from the network after each epoch. Run the following:

```

python train.py --device_id 0

```

to train. By default, an output folder will be created in your current working directory. Setting `--device_id` to -1 will run in CPU mode, whereas 0 will run on GPU number 0 etc. To train on MNIST, use the flag `--mnist`.

License

-------

MIT License. Please see the LICENSE file for details.