Unpaired_Image_To_Image_Translation_Using_CycleGAN_PyTorch

Did this project in "Generative Adversarial Network" module during completion of Udacitty Deep Learning Nanodegree.Built a CycleGAN to and trained on the unlabeled and unpaired dataset images of "summer" and "winter" from "Yosemite National Park" dataset to transform the images from the "summer" domain to "winter" domain and vice versa. Defined two sets of Discriminator and Generartor, each for transforming images from summer to winter and vise versa. Trained the two Discriminator separately by optimizing respective discriminator losses and the two Generator together by optimizing addition of two generator losses and two cycle consistency losses and visualized the tranformed images across the two domains by the CycleGAN network.