DCGAN and Improved WGAN

Project referenced from Udacity's face_generation wich is part of their deep-learning course. Further implementations have been done for DCGAN and Improved WGAN with techniques to improve training speed.

Prerequisites

Jupyter notebook
Tensoflow
Matplotlib
Numpy

Getting Started

git clone + repo URL
cd to repo
pip install -r requirement.txt if packages are not yet installed
jupyter notebook + jupyter notebook selected

Results

History

Generate images with DCGAN like architecture
Implemented improved WGAN

Built With

Tensoflow - Software library for numerical computation using data flow graphs
Jupyter notebook - Web-based notebook environment for interactive computing
Matplotlib - Python 2D plotting library
Numpy - package for scientific computing

Contributing

Fork it! Star it?
Create your feature branch: git checkout -b my-new-feature
Commit your changes: git commit -am 'Add some feature'
Push to the branch: git push origin my-new-feature
Submit a pull request :D

Authors

Udacity - Initial work/Notebook boiler plate - Repo
Jorge Ceja - Model implementations - Account

Acknowledgments

Improved Techniques for Training GANs - arXiv
Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networks - arXiv
Improved Training of Wasserstein GANs - arXiv