This is the fourth project of Udacity's Deep Learning Nanodegree Program (Using a DCGAN on the CelebA dataset to generate images of new and realistic human faces.)
At the end of the project, I was able to visualize the results of my trained Generator to see how it performsed; my generated samples looked like fairly realistic faces with small amounts of noise.
- For running this project on your local computer, first make sure you have git by typing
git --versionon cmd, if version number appears that means you have git installed. Go ahead and clone the repository:
git clone https://github.com/Sidrah-Madiha/Project-Face-Generation-Udacity.git
cd Project-Face-Generation-Udacity
- Now please open the file with filename: dlnd_face_generation.ipynb
-
Make sure to create an environment for running this project using conda (you can install Miniconda for this
-
Once you have Miniconda installed, please make an environment for the project like so:
conda create --name face_generation python=3.6
activate face_generation
- Install Pytorch:
conda install pytorch -c pytorch
pip install torchvision
- Install a few required pip packages, which are specified in the requirements text file.
pip install -r requirements.txt