This project is a part of Udacity Deep Learning Nanodegree Program.
This project defines and trains a DCGAN on a dataset of faces. The goal is to get a generator network to generate new images of faces that look as realistic as possible! The project is broken down into a series of tasks from loading in data to defining and training adversarial networks.
Generative Adversarial Network (GAN) is used to implement it. The CelebFaces Attributes Dataset (CelebA) is used to train the network.
- Python (version 3.6.3)
- Pytorch (version 0.4.0)
- Jupyter Notebook