tund / D2GAN

Dual Discriminator Generative Adversarial Nets

Dual Discriminator Generative Adversarial Nets (D2GAN)

This TensorFlow code implements an example of D2GAN for 2D synthetic data, presented in the paper "Dual Discriminator Generative Adversarial Nets" accepted at the 30th Conference on Neural Information Processing Systems (NIPS 2017).

The code is tested on Windows-based operating system with Python 3.6, TensorFlow 1.4.0.

Run the model using this command:

python main.py --num_z 256

Please kindly look at the file main.py for hyperparameter arguments.

Citation

Tu Dinh Nguyen, Trung Le, Hung Vu, Dinh Phung. "Dual Discriminator Generative Adversarial Nets". Advances in Neural Information Processing Systems 30, pages 2667-2677, 2017.

Bibtex

  @incollection{NIPS2017_6860,
    title = {Dual Discriminator Generative Adversarial Nets},
    author = {Nguyen, Tu and Le, Trung and Vu, Hung and Phung, Dinh},
    booktitle = {Advances in Neural Information Processing Systems 30},
    editor = {I. Guyon and U. V. Luxburg and S. Bengio and H. Wallach and R. Fergus and S. Vishwanathan and R. Garnett},
    pages = {2667--2677},
    year = {2017},
    publisher = {Curran Associates, Inc.},
    url = {http://papers.nips.cc/paper/6860-dual-discriminator-generative-adversarial-nets.pdf}
  }