This repository is the official demo of the paper Deep Networks from the Principle of Rate Reduction by Kwan Ho Ryan Chan* (UC Berkeley), Yaodong Yu* (UC Berkeley), Chong You* (Google), Haozhi Qi (UC Berkeley), John Wright (Columbia), and Yi Ma (UC Berkeley).
To install the required packages, run
conda create --name redunet --file requirements.txt
Example files are located in gaussian3d.ipynb. To run this:
You may clone this repo on your local machine by running
git clone https://github.com/ryanchankh/redunet_demo
and run jupyter notebook.
You may click on the gaussian3d.ipynb link (or click here), and click on Open in Collab icon.
Or click here to directly open the notebook in Google Collab. Note that you will need to sign in to your Google account to run.