Upload folder using huggingface_hub

README.md

@@ -0,0 +1,70 @@
+# YOLOv11 Tennis Detection Model
+
+Fine-tuned YOLOv11 model for comprehensive tennis analysis with multi-class object detection.
+
+## Model Performance
+
+| Metric | Score |
+|--------|-------|
+| mAP@50 | **92.13%** |
+| mAP@50-95 | **85.49%** |
+| Precision | 92.9% |
+| Recall | 92.0% |
+
+## Classes Detected (10)
+
+1. **racket** - Tennis rackets
+2. **tennis_ball** - Tennis balls
+3. **court** - Full court area
+4. **net** - Tennis net
+5. **left-service-box** - Left service box
+6. **right-service-box** - Right service box
+7. **left-doubles-alley** - Left doubles alley
+8. **right-doubles-alley** - Right doubles alley
+9. **top-dead-zone** - Top baseline area
+10. **bottom-dead-zone** - Bottom baseline area
+
+## Training Details
+
+- **Base Model**: YOLOv11n
+- **Epochs**: 150
+- **Image Size**: 640x640
+- **Optimizer**: AdamW
+- **Learning Rate**: 0.001 (cosine decay to 0.01)
+- **Device**: MPS (Apple Silicon)
+
+## Usage
+
+```python
+from ultralytics import YOLO
+
+# Load the model
+model = YOLO('training/runs_combined/combined_final/weights/best.pt')
+
+# Run inference
+results = model.predict('tennis_match.jpg', conf=0.25)
+
+# Process results
+for r in results:
+    boxes = r.boxes
+    for box in boxes:
+        cls = int(box.cls[0])
+        conf = float(box.conf[0])
+        print(f"Detected: {model.names[cls]} ({conf:.2f})")
+```
+
+## Training Curves
+
+The model converged smoothly over 150 epochs with consistent improvement in both precision and recall metrics.
+
+## Applications
+
+- Real-time tennis match analysis
+- Player tracking and movement analysis
+- Ball trajectory prediction
+- Court zone occupancy analysis
+- Automated highlight generation
+
+## License
+
+MIT License

config.txt

@@ -0,0 +1,5 @@
+# Configuration
+model_name: tennis-detection-yolov11
+framework: ultralytics
+architecture: yolov11n
+task: object-detection

example.py

@@ -0,0 +1,17 @@
+#!/usr/bin/env python
+# Example usage for tennis-detection-yolov11
+
+from ultralytics import YOLO
+
+# Load model from local file
+model = YOLO('model.pt')
+
+# Or download from Hugging Face (after upload)
+# model = YOLO('hf://YOUR_USERNAME/tennis-detection-yolov11/model.pt')
+
+# Predict on image
+results = model.predict('image.jpg', conf=0.3)
+results[0].show()
+
+# Predict on video
+results = model.predict('video.mp4', conf=0.3, save=True)

model.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:be98152dc5ddcf5552d2b71ae6480d2c6bcf360a1f2369e21b4dc66da442dfcb
+size 5488986

requirements.txt

@@ -0,0 +1,5 @@
+ultralytics>=8.0.0
+torch>=2.0.0
+opencv-python>=4.0.0
+pillow>=9.0.0
+numpy>=1.20.0