Sam Greydanus. April 2017. MIT License.
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).
- vanilla-gan: 100 lines of code
- cnn-gan: 130 lines of code
Vanilla discriminator (D) and generator (G) networks
CNN discriminator (D) and vanilla generator (G) network