DCGAN :- Deep Convolutional Generative Adversial Network to generate celeb faces
In this project, I defined and trained a DCGAN on a dataset of faces. My goal was to get a generator network to generate new images of faces that look as realistic as possible!
This project is divided in the following key sections:
- Processing image data, building a pipeline to extract important facial data from source.
- Define a Deep learning network called DCGAN and training against the train data set.
- Python 3.5+, PyTorch, NumPy, Pandas, matplotlib, torchvision,
To clone the git repository:
git clone https://github.com/EagleDangar/generate-cleleb-faces-DCGAN.git
- You can run the Jupyter Notebook file and go through all the steps and learn about the PyTorch and Generative Adversail Networks.
- Udacity for providing an amazing Deep Learning Nanodegree Program