A full-stack web application to demonstrate how a convolutional neural network works with a fun game, Go!

This project is an implementation of BetaGo and uses its libraries to generate and serve a model to predict moves.

The web client is written in Angular 7.

These instructions will get you a copy of the project up and running on your local machine for development and testing purposes. See deployment for notes on how to deploy the project on a live system.

If you are on a Windows machine, the only available Tensorflow python library is 64-bit Python 3.5.x or Python 3.6.x. The python 3 packages are listed in the requirements.txt file. For the frontend Angular 7 you should install the latest release Node.

For the generate model and serve model backends use the command below in each directory.
pip install -r /path/to/requirements.txt

• Tensorflow - Keras backend implementation
• Keras - Convolutional neural network implementation
• Python 3 - Backend programming language
• Flask - Backend Http Server to serve the model
• BetaGo - SGF library files, tar extraction and model generation
• Angular - Web Client frontend
• Angular Material - Web UI Components

If you want to contribute to this project you can email me at antkaynak1@gmail.com or you can pull a request.

This project does not have versioning and made with learning purposes.

• Ant Kaynak - Initial work - antkaynak

This project is licensed under the MIT License - see the LICENSE.md file for details

• Huge thanks to the developers and contributers at BetaGo for making this project possible.
• This project is part of my Design Project I course.