https://github.com/drewszurko/tensorflow-WGAN-GP

TensorFlow 2.0 implementation of Improved Training of Wasserstein GANs
https://github.com/drewszurko/tensorflow-WGAN-GP

tensorflow tensorflow-datasets tensorflow-wgan-gp tensorflow2 wasserstein-gan wgan-gp

Last synced: about 2 months ago
JSON representation

TensorFlow 2.0 implementation of Improved Training of Wasserstein GANs

• Host: GitHub
• URL: https://github.com/drewszurko/tensorflow-WGAN-GP
• Owner: drewszurko
• License: mit
• Created: 2019-05-28T02:43:49.000Z (over 5 years ago)
• Default Branch: master
• Last Pushed: 2019-05-28T23:45:05.000Z (over 5 years ago)
• Last Synced: 2024-04-08T02:56:12.432Z (6 months ago)
• Topics: tensorflow, tensorflow-datasets, tensorflow-wgan-gp, tensorflow2, wasserstein-gan, wgan-gp
• Language: Python
• Homepage: https://arxiv.org/abs/1704.00028
• Size: 11.7 KB
• Stars: 25
• Watchers: 3
• Forks: 8
• Open Issues: 0
• Metadata Files:
  • Readme: README.md
  • License: LICENSE

Awesome Lists containing this project

• Awesome-Tensorflow2 - drewszurko/tensorflow-WGAN-GP

README

        
# TensorFlow 2.0 WGAN-GP 

TensorFlow 2.0 implementation of Improved Training of Wasserstein GANs [[1]](https://arxiv.org/abs/1704.00028). 

New/existing TensorFlow features found in this repository include eager execution, AutoGraph, Keras high-level API, and TensorFlow Datasets.

## Requirements

* [Python 3](https://www.python.org/)

* [Abseil](https://abseil.io/)

* [NumPy](http://www.numpy.org/)

* [TensorFlow >= 2.0](https://www.tensorflow.org/versions/r2.0/api_docs/python/tf)

* [TensorFlow Datasets](https://www.tensorflow.org/datasets/)

* [tqdm](https://tqdm.github.io/)

## Datasets

* [CIFAR-10](https://www.cs.toronto.edu/~kriz/cifar.html)

* [CelebA](http://mmlab.ie.cuhk.edu.hk/projects/CelebA.html)

* [TF Flowers](http://download.tensorflow.org/example_images/flower_photos.tgz)

* [Oxford Flowers 102](https://www.robots.ox.ac.uk/~vgg/data/flowers/102/)

* [Oxford-IIIT pet](http://www.robots.ox.ac.uk/~vgg/data/pets/)

## Usage

**Install requirements**

```

$ pip install -r requirements.txt

```

**Train model**

```

$ python main.py -dataset celeb_a -batch_size 64 -image_size 64

```

## References

[1] [Improved Training of Wasserstein GANs](https://arxiv.org/abs/1704.00028)