Generative Adversarial Networks for the MNIST dataset
Switch branches/tags
Nothing to show
Clone or download
Latest commit 1b6f427 Apr 24, 2017

README.md

MNIST Generative Adversarial Networks (PyTorch)

Sam Greydanus. April 2017. MIT License.

About

I use the classic MNIST dataset to achieve ultra-simple GAN results. Think of this repo as a lab where you can get comfortable with GANs before trying them on something more complex (e.g. CIFAR, ImageNet).

Samples

Vanilla discriminator (D) and generator (G) networks

vanilla-gan

CNN discriminator (D) and vanilla generator (G) network

cnn-gan

Dependencies

  • All code is written in python 3.6. You will need:
  • Numpy
  • matplotlib
  • PyTorch: much easier to write and debug than TensorFlow!
  • Jupyter