Home

Awesome

Generative Adversarial Notebooks

Collection of my Generative Adversarial Network implementations

Most codes are for python3, most notebooks works on

CycleGAN

CycleGAN results

<img src="img/cyclegan_58_11603.png" height=300 /> Result after 3 hours and 58 epochs on a GTX 1080. From top to bottom: Input, Fake, Recreate of the input. <img src="img/cyclegan_face.png" height=300 /> Face-off result. From top to bottom: Input, Fake, Recreate of the input. [youtube video](https://www.youtube.com/watch?v=Fea4kZq0oFQ)

pix2pix

pix2pix sample results

<img src="img/pix2pix.png" height="200" /> Validation result of edges-to-shoes after 12 epochs. From top to bottom: Input, Ground truth, the result. <img src="img/pix2pix_resnet.png" height="200" /> Validation result of facades dataset after 150 epochs using resnet. From top to bottom: Input, Ground truth, the result.

WGAN on CIFAR10

WGAN2 (improved WGAN/WGAN-gp)

WGAN2 sample results

<img src="img/wgan2-cifar10.png" height="100" /> <img src="img/wgan2-ac-cifar10.png" height="400" /> <img src="img/wgan2-anime.png" height="500" />

InfoGAN

InfoGAN sample results

<img src="img/infogan-mnist.png" height="300" />

DCGAN

DCGAN sample results

<img src="img/dcgan-cifar10.png" height="300" />