GAN

Simple docker code that trains custom GAN network to generate images (bad quality, but quite fast in docker)

CycleGAN architecture implemented using the Tensorflow's objective model API for the purpose of image to image translation.

In SupeRAuGAN we implement a novel data augmentation technique tailored to Generative Adversarial Networks in order to reduce discriminator overfitting and stabilize training

Attention Guided Image-to-Imagetranslation of Food Images Using GANs

Adaptive Generative Multi-Modal Framework for Trajectory Forecasting in Autonomous Vehicles

Toy implementation of Wasserstein GAN with Gradient Penalty