Skip to content

A generative adversarial networks trained to generate new images of human faces.

License

Notifications You must be signed in to change notification settings

ytobi/face-generation

Repository files navigation

Face Generation

In this project, I built a generative adversarial networks(GAN) to generate new images of faces. The project is part of fulfillment for a nanodegree at Udacity.

Installation

For best experience with managing dependency I advise you install Anconda or miniconda.

Create a virtual environment with conda

conda create --name deep-learning python=3

Activate environment.

source activate deep-learning

Install dependencies.

pip install -r requirements.txt

Download or clone this face-generation. Launch the app with jupyter-notebook.

jupyter-notebook dlnd_face_generation.ipynb

Usage

Setup

Download the celeba dataset. Unzip the folder and place it in this project's home directory, at the location processed_celeba_small/.

This is a zip file that you'll need to extract in the home directory of this notebook for further loading and processing. After extracting the data, you should be left with a directory of data processed_celeba_small/.

Note: If you are using a Windows machine, you are encouraged to use 7zip to extract the folder.

Run

Run all code cells in the notebook (This will take a very very long time to run on a CPU, preferably you should run on a GPU).

Notice that the generated faced though low-resolution are human faces.

About

A generative adversarial networks trained to generate new images of human faces.

Topics

Resources

License

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published