From scratch, simple and easy-to-understand Pytorch implementation of various generative adversarial network (GAN): GAN, DCGAN, Conditional GAN (cGAN), WGAN, WGAN-GP, CycleGAN, LSGAN, and StarGAN.

Using a CGAN and the CelebHQ dataset from Kaggle, this project converts sketches into lifelike images, showcasing the potential of generating realistic images from freehand drawings.

Generative Adversarial Network Implementations in Keras