Skip to content

README.md

Latest commit

 

History

History
39 lines (34 loc) · 1.8 KB

README.md

File metadata and controls

39 lines (34 loc) · 1.8 KB

Generative Adversarial Networks (GANs)

Vanilla GAN and DCGAN

Requirements

  • Python 3.x
  • Tensorflow > 0.12
  • Numpy
  • SciPy
  • OpenCV
  • lmdb (for processing LSUN dataset only)

Pre-execution instructions

Datasets to download

Download following files in the program root dirctory (*.../gan)

Results

Vanilla GAN

  • Dataset class: LSUN/church outdoor

Generated sample:

Each epoch:

Loss graph:

DCGAN

  • Dataset class: LSUN/church outdoor

Generated sample:

Each epoch:

Loss graph:

Reference papers

  • I. Goodfellow, J. Pouget-Abadie, M. Mirza, B. Xu, D. Warde-Farley, S. Ozair, A. Courville, and Y. Bengio. Generative Adversarial Nets. NIPS 2014
  • I. Goodfellow. NIPS 2016 Tutorial: Generative Adversarial Networks. NIPS 2016
  • A. Radford, L. Metz, and S. Chintala. Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networks. ICLR 2016
⚡