Upload chess board segmentation model (yolo11s-seg.pt -> 100 epochs)
Browse files
README.md
ADDED
|
@@ -0,0 +1,59 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
library_name: ultralytics
|
| 3 |
+
tags:
|
| 4 |
+
- object-detection
|
| 5 |
+
- chess
|
| 6 |
+
- computer-vision
|
| 7 |
+
- yolo
|
| 8 |
+
datasets:
|
| 9 |
+
- chess-pieces
|
| 10 |
+
pipeline_tag: object-detection
|
| 11 |
+
---
|
| 12 |
+
|
| 13 |
+
# Chess Piece Detection Model
|
| 14 |
+
|
| 15 |
+
This is a YOLO model trained to detect chess pieces on a chessboard.
|
| 16 |
+
|
| 17 |
+
## Model Details
|
| 18 |
+
|
| 19 |
+
- **Model Type**: YOLO11 Object Detection
|
| 20 |
+
- **Task**: Chess piece detection and classification
|
| 21 |
+
- **Framework**: Ultralytics YOLO
|
| 22 |
+
- **Repository**: dopaul/chess-board-segmentation
|
| 23 |
+
|
| 24 |
+
## Files
|
| 25 |
+
|
| 26 |
+
The following files are included in this model:
|
| 27 |
+
|
| 28 |
+
- `best.pt`
|
| 29 |
+
|
| 30 |
+
## Usage
|
| 31 |
+
|
| 32 |
+
```python
|
| 33 |
+
from ultralytics import YOLO
|
| 34 |
+
|
| 35 |
+
# Load the model
|
| 36 |
+
model = YOLO('path/to/best.pt')
|
| 37 |
+
|
| 38 |
+
# Run inference
|
| 39 |
+
results = model('path/to/chess_image.jpg')
|
| 40 |
+
|
| 41 |
+
# Display results
|
| 42 |
+
results[0].show()
|
| 43 |
+
```
|
| 44 |
+
|
| 45 |
+
## Model Performance
|
| 46 |
+
|
| 47 |
+
This model can detect and classify various chess pieces including:
|
| 48 |
+
- Pawns
|
| 49 |
+
- Rooks
|
| 50 |
+
- Knights
|
| 51 |
+
- Bishops
|
| 52 |
+
- Queens
|
| 53 |
+
- Kings
|
| 54 |
+
|
| 55 |
+
For both black and white pieces.
|
| 56 |
+
|
| 57 |
+
## Training Data
|
| 58 |
+
|
| 59 |
+
The model was trained on chess piece datasets to achieve robust detection across different chess sets and lighting conditions.
|