In this project, It'll be defined and trained 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 will be broken down into a series of tasks from loading in data to defining and training adversarial networks. That project aims to build a model that must be able to create samples that should look like fairly realistic faces with small amounts of noise.
You'll be using the CelebFaces Attributes Dataset (CelebA) to train the adversarial networks.
Some samples:
It is suggested to use virtualenv (https://docs.python.org/3/tutorial/venv.html)
Then use pip to install the requirement:
pip install -r requirement.txt
This project is just for your reference and fun purposes. Additionally, I share it as a portfolio of my work.