In this project, I built and trained a custom GAN architecture on CelebA dataset, generating realistic faces.
In this project, I built and train a custom GAN architecture on the CelebA dataset, leveraging the different skills learned during the course. In particular, I created a custom GAN architecture from scratch, including generator and discriminator and also experimented with the different loss functions discovered during the course, such as the Binary Cross Entropy loss or the Wasserstein loss. Finally, utilize some of the methods learned to stabilize training, such as label smoothing.
here is the Colab link : https://drive.google.com/file/d/1qyyFv0lgm122fnFps6GwaBDZ3RWksx3W/view?usp=sharing
