# deep-chess-playground
Where deep learning meets chess.
This repository aims to implement techniques for neural chess engines, providing an in-depth look at the practical application of AI in chess game.
## Table of contents
1. [Play chessbots on lichess](#play-chessbots-on-lichess)
2. [Run chessbots locally](#run-chessbots-locally)
- [Setup](#setup)
- [Play](#play)
3. [Train your own chessbots](#train-your-own-chessbots)
- [Data loading](#data-loading)
- [Data processing](#data-processing)
- [Training](#training)
## Play chessbots on lichess
COMING SOON
## Run chessbots locally
### Setup
It is recommended to use Anaconda for managing your Python environment, especially if you plan to use GPU acceleration. However, we also provide instructions for standard Python with pip.
#### Option 1: Using Anaconda (recommended)
1. Download and install Anaconda from the official website: [https://www.anaconda.com/products/distribution](https://www.anaconda.com/products/distribution).
2. Open Anaconda Prompt and run the following command to create a virtual environment:
```
conda create --name deep_chess_playground python=3.10
```
3. Activate the environment:
```
conda activate deep_chess_playground
```
4. Install PyTorch. Follow the instructions at [PyTorch website](https://pytorch.org/get-started/locally/).
Choose the compute platform (CUDA or CPU) depending on whether you have a GPU or not.
5. Install PyTorch Lightning:
```
conda install pytorch-lightning -c conda-forge
```
6. Install deep-chess-playground:
```
pip install deep-chess-playground
```
#### Option 2: Using standard Python and pip
1. Ensure you have Python 3.10 or later installed. You can download it from [python.org](https://www.python.org/downloads/).
2. Create a virtual environment:
```
python -m venv deep_chess_env
```
3. Activate the virtual environment:
- On Windows:
```
deep_chess_env\Scripts\activate
```
- On macOS and Linux:
```
source deep_chess_env/bin/activate
```
4. Install PyTorch. Follow the instructions at [PyTorch website](https://pytorch.org/get-started/locally/).
Choose the compute platform (CUDA or CPU) depending on whether you have a GPU or not.
5. Install PyTorch Lightning:
```
pip install pytorch-lightning
```
6. Install deep-chess-playground:
```
pip install deep-chess-playground
```
### Play
COMING SOON
## Train your own chessbots
### Data loading
<p align="center">
<img src="assets/data_loading.png" alt="Data loading"/>
</p>
If you need a lot of training data, you can use the [lichess.org open database](https://database.lichess.org/) which has more than 5 000 000 000 games recorded starting from January 2013!
### Training
COMING SOON
Raw data
{
"_id": null,
"home_page": "https://github.com/PypayaTech/deep-chess-playground",
"name": "deep-chess-playground",
"maintainer": null,
"docs_url": null,
"requires_python": "<4.0,>=3.10",
"maintainer_email": null,
"keywords": "chess, deep learning, neural networks",
"author": "PypayaTech",
"author_email": null,
"download_url": "https://files.pythonhosted.org/packages/e4/14/6009d61ad4ff1e8d21dcaae4a81468319f8631d0492647bf1d5d89e01dbb/deep_chess_playground-0.0.4.tar.gz",
"platform": null,
"description": "# deep-chess-playground\n\nWhere deep learning meets chess.\n\n\n\nThis repository aims to implement techniques for neural chess engines, providing an in-depth look at the practical application of AI in chess game.\n\n## Table of contents\n\n1. [Play chessbots on lichess](#play-chessbots-on-lichess)\n2. [Run chessbots locally](#run-chessbots-locally)\n - [Setup](#setup)\n - [Play](#play)\n3. [Train your own chessbots](#train-your-own-chessbots)\n - [Data loading](#data-loading)\n - [Data processing](#data-processing)\n - [Training](#training)\n\n## Play chessbots on lichess\n\nCOMING SOON\n\n## Run chessbots locally\n\n### Setup\n\nIt is recommended to use Anaconda for managing your Python environment, especially if you plan to use GPU acceleration. However, we also provide instructions for standard Python with pip.\n\n#### Option 1: Using Anaconda (recommended)\n\n1. Download and install Anaconda from the official website: [https://www.anaconda.com/products/distribution](https://www.anaconda.com/products/distribution).\n\n2. Open Anaconda Prompt and run the following command to create a virtual environment:\n ```\n conda create --name deep_chess_playground python=3.10\n ```\n\n3. Activate the environment:\n ```\n conda activate deep_chess_playground\n ```\n\n4. Install PyTorch. Follow the instructions at [PyTorch website](https://pytorch.org/get-started/locally/). \n Choose the compute platform (CUDA or CPU) depending on whether you have a GPU or not.\n\n5. Install PyTorch Lightning:\n ```\n conda install pytorch-lightning -c conda-forge\n ```\n\n6. Install deep-chess-playground:\n ```\n pip install deep-chess-playground\n ```\n\n#### Option 2: Using standard Python and pip\n\n1. Ensure you have Python 3.10 or later installed. You can download it from [python.org](https://www.python.org/downloads/).\n\n2. Create a virtual environment:\n ```\n python -m venv deep_chess_env\n ```\n\n3. Activate the virtual environment:\n - On Windows:\n ```\n deep_chess_env\\Scripts\\activate\n ```\n - On macOS and Linux:\n ```\n source deep_chess_env/bin/activate\n ```\n\n4. Install PyTorch. Follow the instructions at [PyTorch website](https://pytorch.org/get-started/locally/). \n Choose the compute platform (CUDA or CPU) depending on whether you have a GPU or not.\n\n5. Install PyTorch Lightning:\n ```\n pip install pytorch-lightning\n ```\n\n6. Install deep-chess-playground:\n ```\n pip install deep-chess-playground\n ```\n\n### Play\n\nCOMING SOON\n\n## Train your own chessbots\n\n### Data loading\n\n<p align=\"center\">\n <img src=\"assets/data_loading.png\" alt=\"Data loading\"/>\n</p>\n\nIf you need a lot of training data, you can use the [lichess.org open database](https://database.lichess.org/) which has more than 5 000 000 000 games recorded starting from January 2013!\n\n### Training\n\nCOMING SOON\n\n",
"bugtrack_url": null,
"license": "MIT",
"summary": "Where deep learning meets chess",
"version": "0.0.4",
"project_urls": {
"Homepage": "https://github.com/PypayaTech/deep-chess-playground",
"Repository": "https://github.com/PypayaTech/deep-chess-playground"
},
"split_keywords": [
"chess",
" deep learning",
" neural networks"
],
"urls": [
{
"comment_text": "",
"digests": {
"blake2b_256": "348ce4f08d11c1df04492028ec7ac88941178d24e4bc3445fca69c000d679e23",
"md5": "ca361b4c674d96ad819c8235672ab6bf",
"sha256": "b35e40368c724efe801765b2627d961607727841336189331ee0703e90d2bc24"
},
"downloads": -1,
"filename": "deep_chess_playground-0.0.4-py3-none-any.whl",
"has_sig": false,
"md5_digest": "ca361b4c674d96ad819c8235672ab6bf",
"packagetype": "bdist_wheel",
"python_version": "py3",
"requires_python": "<4.0,>=3.10",
"size": 31042,
"upload_time": "2024-10-10T19:06:49",
"upload_time_iso_8601": "2024-10-10T19:06:49.253974Z",
"url": "https://files.pythonhosted.org/packages/34/8c/e4f08d11c1df04492028ec7ac88941178d24e4bc3445fca69c000d679e23/deep_chess_playground-0.0.4-py3-none-any.whl",
"yanked": false,
"yanked_reason": null
},
{
"comment_text": "",
"digests": {
"blake2b_256": "e4146009d61ad4ff1e8d21dcaae4a81468319f8631d0492647bf1d5d89e01dbb",
"md5": "e8db7eb5bb57cee734f325a10e4e1644",
"sha256": "e7afe990bb20596c58bce931b04a15f70122f2d918cae3a0b10a13bc265a3aa5"
},
"downloads": -1,
"filename": "deep_chess_playground-0.0.4.tar.gz",
"has_sig": false,
"md5_digest": "e8db7eb5bb57cee734f325a10e4e1644",
"packagetype": "sdist",
"python_version": "source",
"requires_python": "<4.0,>=3.10",
"size": 24240,
"upload_time": "2024-10-10T19:06:50",
"upload_time_iso_8601": "2024-10-10T19:06:50.668057Z",
"url": "https://files.pythonhosted.org/packages/e4/14/6009d61ad4ff1e8d21dcaae4a81468319f8631d0492647bf1d5d89e01dbb/deep_chess_playground-0.0.4.tar.gz",
"yanked": false,
"yanked_reason": null
}
],
"upload_time": "2024-10-10 19:06:50",
"github": true,
"gitlab": false,
"bitbucket": false,
"codeberg": false,
"github_user": "PypayaTech",
"github_project": "deep-chess-playground",
"travis_ci": false,
"coveralls": false,
"github_actions": false,
"lcname": "deep-chess-playground"
}
JSON
