❯ Training of an AI using CNN, Residuals, advanced scheduler and optimizer

🔗 Table of Contents

• 📍 Overview
• 👾 Features
• 📁 Project Structure
  • 📂 File Purpose
• 🚀 Getting Started
  • ☑️ Prerequisites
  • ⚙️ Installation
  • 🤖 Usage
  • 🧪 Testing
• 📌 Project Roadmap
• 🔰 Contributing
• 🎗 License
• 🙌 Acknowledgments

---

📍 Overview

This project uses Convolutional Neural Networks (CNNs) and advanced deep learning techniques to develop a chess-playing AI. The AI is trained using residual connections, dynamic learning rate schedulers, and cutting-edge optimizers for superior performance and scalability. It can predict optimal moves and simulate gameplay, making for a interesting way to experience chess.

---

👾 Features

❯ Key highlights of this project include:

• Integration of Stockfish for generating high-quality training data.
• Implementation of CNNs with residual layers for deep feature extraction.
• Support and usage for advanced learning rate scheduling and optimizers.
• Interactive GUI for playing against the AI.
• Comprehensive project structure with modular code for scalability.

---

📁 Project Structure

└── chessAI/
    ├── dup.py
    ├── engine.py
    ├── get_data.py
    ├── images
    │   ├── *.png
    │   ├── new.svg  # logo above
    ├── main.py
    ├── requirements.txt
    ├── training.py
    └── utils.py

📂 File Purpose

training.py	❯ Contains the training loop, dataset structure, and the AI model
dup.py	❯ Checks how many lines are duplicates
utils.py	❯ Some helper functions
get_data.py	❯ Get training data using Stockfish
main.py	❯ Contains GUI loop to play against the AI
engine.py	❯ Handles the logic to load models and return best move
requirements.txt	❯ Requirements for this project

---

🚀 Getting Started

☑️ Prerequisites

Before getting started with chessAI, ensure your runtime environment meets the following requirements:

• Programming Language: Python
• Package Manager: Pip

⚙️ Installation

Install chessAI using one of the following methods:

Build from source:

1. Clone the chessAI repository:

git clone https://github.com/mp3skater/chessAI.git

2. Navigate to the project directory:

cd chessAI

3. Install the project dependencies:

Using pip  

❯ pip install -r requirements.txt

🤖 Usage

Run chessAI using the following command: Using pip  

sh ❯ python main.py

---

📌 Project Roadmap

• Task 1: Implement a straightforward chess ai using supervised learning.
• Task 2: Implement a active learning model.
• Task 3: Code and test on a large server a MCTS based AI with improvements.

---

🔰 Contributing

• 💬 Join the Discussions: Share your insights, provide feedback, or ask questions.
• 🐛 Report Issues: Submit bugs found or log feature requests for the chessAI project.
• 💡 Submit Pull Requests: Review open PRs, and submit your own PRs.

Contributing Guidelines

1. Fork the Repository: Start by forking the project repository to your github account.
2. Clone Locally: Clone the forked repository to your local machine using a git client.

   git clone https://github.com/mp3skater/chessAI

3. Create a New Branch: Always work on a new branch, giving it a descriptive name.

   git checkout -b new-feature-x

4. Make Your Changes: Develop and test your changes locally.
5. Commit Your Changes: Commit with a clear message describing your updates.

   git commit -m 'Implemented new feature x.'

6. Push to github: Push the changes to your forked repository.

   git push origin new-feature-x

7. Submit a Pull Request: Create a PR against the original project repository. Clearly describe the changes and their motivations.
8. Review: Once your PR is reviewed and approved, it will be merged into the main branch. Congratulations on your contribution!

Contributor Graph

---

🎗 License

This project is protected under the MIT-LICENSE License. For more details, refer to the LICENSE file.

---

🙌 Acknowledgments

• Credits go out to Scier for his chess AI tutorial where I let myself get some inspiration: video

---