This project, defines and train 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!
Face Generation
Introduction
In this project, you’ll use generative adversarial networks to generate new images of faces.
Processed CelebA face data.
This project requires Python 3.6.0 and the following Python libraries installed:
In a terminal or command window, navigate to the top-level project directory Generate-Faces/ (that contains this README) and run the following command:
jupyter notebook dlnd_face_generation.ipynb
or
jupyter notebook dlnd_face_generation.ipynb
on any Jupyter Notebook.
This will open the iPython Notebook software and project file in your browser.
Generated faces after 30 epochs.
Train Loss for 30 epochs.
This project uses the MIT License.