Create README.md

README.md

@@ -0,0 +1,207 @@
+---
+license: cc-by-nc-4.0
+library_name: onnx
+tags:
+- chess
+- deep-learning
+- pytorch
+- onnx
+- strategy
+- game-ai
+datasets:
+- Rafs-an09002/chessmate-opening-stats
+language:
+- en
+pipeline_tag: reinforcement-learning
+---
+
+# ♟️ ChessMate AI - CNN Evaluation Model
+
+<div align="center">
+
+![ChessMate Banner](https://capsule-render.vercel.app/api?type=waving&color=0:3498db,100:2c3e50&height=180&section=header&text=ChessMate%20Model&fontSize=50&animation=fadeIn&fontAlignY=35&desc=ONNX%20Chess%20Evaluation%20Network)
+
+[![License: CC BY-NC 4.0](https://img.shields.io/badge/License-CC%20BY--NC%204.0-lightgrey.svg)](https://creativecommons.org/licenses/by-nc/4.0/)
+![Format](https://img.shields.io/badge/Format-ONNX-blue)
+![Input](https://img.shields.io/badge/Input-12x8x8%20Tensor-orange)
+
+[**Live Demo**](https://chessmate-engine.onrender.com) • [**GitHub Repository**](https://github.com/Rafsan1711/Chessmate-Engine)
+
+</div>
+
+## 📖 Model Description
+
+This is a **Convolutional Neural Network (CNN)** trained to evaluate chess positions. It takes a board state as input and outputs a scalar evaluation score between `-1` (Black winning) and `+1` (White winning).
+
+It is the core "brain" of the **ChessMate AI** project, designed to run efficiently in web browsers using `onnxruntime-web`.
+
+- **Architecture:** 3-Layer CNN with Batch Normalization and ReLU activation.
+- **Framework:** Trained in PyTorch, exported to ONNX (Opset 14).
+- **Size:** ~7.5 MB (Highly optimized for web loading).
+- **Training Data:** 100,000+ Master-level games from Lichess (Standard Rated > 2000 ELO).
+
+## 🛠️ Technical Specifications
+
+### Input Shape
+The model expects a Tensor of shape `(1, 12, 8, 8)` representing the board state using One-Hot Encoding.
+
+- **Channels (12):**
+  - 0-5: White Pieces (Pawn, Knight, Bishop, Rook, Queen, King)
+  - 6-11: Black Pieces (Pawn, Knight, Bishop, Rook, Queen, King)
+- **Dimensions (8x8):** The chess board squares.
+
+### Output
+- **Shape:** `(1, 1)`
+- **Value:** Float between `-1.0` and `1.0`.
+  - `> 0`: Advantage White
+  - `< 0`: Advantage Black
+  - `~ 0`: Equal/Draw
+
+## 💻 Usage (JavaScript / ONNX.js)
+
+This model is designed to be used directly in the browser via `onnxruntime-web`.
+
+```javascript
+import * as ort from 'onnxruntime-web';
+
+// 1. Load the session
+const session = await ort.InferenceSession.create('./chess_model.onnx');
+
+// 2. Prepare Input (Float32Array of size 12*8*8)
+// Convert FEN string to 12x8x8 one-hot encoded array
+const inputData = new Float32Array(768).fill(0); 
+// ... (Fill array based on piece positions) ...
+
+const tensor = new ort.Tensor('float32', inputData, [1, 12, 8, 8]);
+
+// 3. Run Inference
+const results = await session.run({ board_state: tensor });
+const evaluation = results.evaluation.data[0];
+
+console.log(`Position Score: ${evaluation}`);
+```
+
+## 🧠 Training Details
+
+- **Loss Function:** Mean Squared Error (MSE)
+- **Optimizer:** Adam (lr=0.001)
+- **Epochs:** 50 (with Early Stopping)
+- **Target Label:** Normalized Stockfish Evaluation / Game Result (Win/Loss/Draw).
+
+## ⚠️ License & Limitations
+
+This model is licensed under **CC BY-NC 4.0** (Attribution-NonCommercial 4.0 International).
+
+**You are free to:**
+- Use this model for research, education, and personal projects.
+- Modify and adapt the model.
+
+**You may NOT:**
+- Sell this model or use it in a commercial product without permission.
+
+---
+<div align="center">
+  <p>Created by <a href="https://github.com/Rafsan1711">Rafsan1711</a></p>
+</div>
+```
+
+---
+
+### 2. Dataset Repository (`chessmate-opening-stats`) - README
+
+এটি কপি করে আপনার **Dataset Repository**-র `README.md` ফাইলে পেস্ট করুন।
+
+```markdown
+---
+license: cc-by-nc-4.0
+task_categories:
+- reinforcement-learning
+- tabular-classification
+language:
+- en
+tags:
+- chess
+- opening
+- statistics
+- game-ai
+size_categories:
+- 1M<n<10M
+pretty_name: ChessMate Opening Statistics
+---
+
+# ♟️ ChessMate AI - Opening Statistics Database
+
+<div align="center">
+
+![Dataset Banner](https://capsule-render.vercel.app/api?type=waving&color=0:2c3e50,100:3498db&height=180&section=header&text=Opening%20Database&fontSize=50&animation=fadeIn&fontAlignY=35&desc=Optimized%20SQLite%20Stats%20for%20Chess%20Engines)
+
+[![License: CC BY-NC 4.0](https://img.shields.io/badge/License-CC%20BY--NC%204.0-lightgrey.svg)](https://creativecommons.org/licenses/by-nc/4.0/)
+![Format](https://img.shields.io/badge/Format-SQLite3-green)
+![Size](https://img.shields.io/badge/Size-140MB+-orange)
+
+[**Live Explorer**](https://chessmate-engine.onrender.com) • [**GitHub Repository**](https://github.com/Rafsan1711/Chessmate-Engine)
+
+</div>
+
+## 📖 Dataset Description
+
+This dataset contains aggregated opening statistics derived from over **100,000 high-rated Lichess games** (ELO 2000+). It maps chess board positions (FEN) to their historical outcomes (White Win, Draw, Black Win).
+
+It is designed to power the **ChessMate AI Opening Explorer** and serve as an opening book for the engine.
+
+- **Source:** Lichess Standard Rated Games (Feb 2016).
+- **Format:** SQLite Database (`.db`).
+- **Optimization:** Indexed by FEN for O(1) lookup speed.
+
+## 📂 File Structure
+
+The main file is `chess_stats.db`, which contains a single table:
+
+### Table: `positions`
+
+| Column | Type | Description |
+|--------|------|-------------|
+| `fen` | TEXT (PK) | The board position in Forsyth–Edwards Notation (Primary Key). |
+| `stats` | TEXT | JSON string containing move counts and win rates. |
+
+**Example JSON in `stats` column:**
+```json
+{
+  "total": 520,
+  "moves": {
+    "e4": { "white": 200, "black": 150, "draw": 170 },
+    "d4": { "white": 100, "black": 80, "draw": 20 }
+  }
+}
+```
+
+## 🛠️ Usage (Node.js / Better-SQLite3)
+
+This database is designed to be streamed or downloaded by a backend service.
+
+```javascript
+const Database = require('better-sqlite3');
+const db = new Database('chess_stats.db', { readonly: true });
+
+const fen = "rnbqkbnr/pppppppp/8/8/4P3/8/PPPP1PPP/RNBQKBNR";
+const row = db.prepare('SELECT stats FROM positions WHERE fen = ?').get(fen);
+
+if (row) {
+  console.log(JSON.parse(row.stats));
+}
+```
+
+## ⚠️ License
+
+This dataset is licensed under **CC BY-NC 4.0** (Attribution-NonCommercial 4.0 International).
+
+**You are free to:**
+- Use this data for research, education, and personal projects.
+
+**You may NOT:**
+- Sell this data or use it in a commercial product without permission.
+
+---
+<div align="center">
+  <p>Created by <a href="https://github.com/Rafsan1711">Rafsan1711</a></p>
+</div>