CycleGAN Image to Image Translation

I created this project while participating in the Udacity Deep Learning Nanodegree
The goal of the project was to use a CycleGAN CNN model to transfer images from one domain to another
When domains represent a style/texture - the idea is to separate the image content from its style.
In this project I transferred Yosemtie national park images from "winter" to "summer" and vice versa.
Project is based on the "Unpaired Image-to-Image Translation using Cycle-Consistent Adversarial Networks" article.
Code is written in python with PyTorch library on a Jupyter Notebook platform.

Table of Contents

• Load the Notebook
• Dependencies
• Meta
• Contributing

Load the Notebook

• Clone via Github
• Download a zip file
• Google Colab

Dependencies:

• Anaconda Python 3
• Python libraries: PyTorch, numpy, pandas, matplotlib
• Jupyter Notebook

Meta

Eli Shay – El_mn123@hotmail.com

https://github.com/EliShayGH/cycle-gan-image2image-translation

Contributing

1. Fork it (https://github.com/EliShayGH/cycle-gan-image2image-translation/fork)
2. Create your feature branch (git checkout -b feature/fooBar)
3. Commit your changes (git commit -am 'Add some fooBar')
4. Push to the branch (git push origin feature/fooBar)
5. Create a new Pull Request