Face Generation with a GAN

You will use a generative adversarial network to train on the CelebA Dataset and learn to generate face images. The top-level notebook ([login to view URL]) will guide you through the steps you need to take to implement and train a GAN. You will train two different models, the original GAN and LSGAN, which has a different loss function. The generator and discriminator network architectures you will implement are roughly based on DCGAN. We also provide with a notebook to help with debugging called GAN_debugging.ipynb. This notebook provides a small network you can use to train on MNIST. The small network trains very quickly so you can use it to verify that your loss functions and training code are correct. You will need to use a GPU for training your GAN. We recommend using Colab to debug, but a Google Cloud machine once your debugging is finished as you will have to run the GAN for a few hours to train fully.