Upload folder using huggingface_hub

README.md

@@ -1,3 +1,162 @@
----
-license: mit
----
+---
+license: mit
+tags:
+  - yolov8
+  - object-detection
+  - image-classification
+  - dinov2
+  - sports
+  - motogp
+  - motorcycle-racing
+  - computer-vision
+  - pytorch
+datasets:
+  - custom
+pipeline_tag: object-detection
+library_name: ultralytics
+---
+
+# 🏍️ MotoGP Team Detection & Re-ID Models
+
+<div align="center">
+
+**Fine-tuned weights for detecting and identifying MotoGP teams from race broadcast footage.**
+
+[![GitHub](https://img.shields.io/badge/GitHub-Repository-181717?style=for-the-badge&logo=github)](https://github.com/johnamit/mgp-detect)
+
+</div>
+
+## Model Overview
+
+This repository contains trained model weights for the [MotoGP Team Detection](https://github.com/johnamit/mgp-detect) project — a deep learning pipeline for **real-time MotoGP team detection, tracking, and re-identification** from race broadcast footage.
+
+### Included Weights
+
+| File | Description | Size |
+|------|-------------|------|
+| `motogp_yolov8m_detector.pt` | Fine-tuned YOLOv8m for motorcycle detection | ~50MB |
+| `dinov3_team_classifier.pkl` | Logistic Regression classifier trained on DINOv3 embeddings | ~35KB |
+
+## Pipeline Architecture
+
+```
+Video Frame → YOLOv8 Detector → Crop → DINOv3 Feature Extraction → Team Classifier → Re-ID Tracking
+```
+
+1. **Detection**: YOLOv8m (fine-tuned) localizes motorcycles in each frame
+2. **Feature Extraction**: DINOv3 ViT-S/16 extracts dense semantic features from detected regions
+3. **Classification**: Logistic Regression head predicts team identity from DINO embeddings
+4. **Re-ID & Tracking**: ByteTrack + Cosine Similarity Memory Bank for persistent tracking
+
+## Supported Teams (2025 Season)
+
+| Manufacturer | Teams |
+|--------------|-------|
+| **Ducati** | Lenovo Team, Gresini Racing, VR46 Racing |
+| **Aprilia** | Factory Racing, Trackhouse Racing |
+| **KTM** | Factory Racing, Tech3 |
+| **Honda** | Repsol HRC, LCR Honda |
+| **Yamaha** | Monster Energy, Prima Pramac |
+
+## Usage
+
+### 1. Download Weights
+
+```python
+from huggingface_hub import hf_hub_download
+
+# Download YOLOv8 detector
+detector_path = hf_hub_download(
+    repo_id="johnamit/motogp-team-detection",
+    filename="motogp_yolov8m_detector.pt"
+)
+
+# Download team classifier
+classifier_path = hf_hub_download(
+    repo_id="johnamit/motogp-team-detection",
+    filename="dinov3_team_classifier.pkl"
+)
+```
+
+### 2. Prerequisites (Base Models)
+
+These weights require the following base models:
+
+#### YOLOv8 (Ultralytics)
+```bash
+pip install ultralytics
+```
+[YOLOv8 Documentation](https://docs.ultralytics.com/models/yolov8/)
+
+#### DINOv3 (Meta AI)
+Clone the DINOv3 repository for feature extraction:
+```bash
+git clone https://github.com/facebookresearch/dinov3.git
+```
+Download the ViT-S/16 pretrained weights from the [DINOv3 repo](https://github.com/facebookresearch/dinov3).
+
+### 3. Inference Example
+
+```python
+from ultralytics import YOLO
+import torch
+import joblib
+
+# Load detector
+detector = YOLO(detector_path)
+
+# Load classifier
+classifier = joblib.load(classifier_path)
+
+# Run detection
+results = detector.predict(source="race_frame.jpg", conf=0.5)
+
+# For each detection, extract DINOv3 features and classify
+# See full pipeline: https://github.com/johnamit/mgp-detect
+```
+
+## Training Details
+
+### YOLOv8 Detector
+- **Base Model**: YOLOv8m
+- **Dataset**: 501 annotated instances (404 motorcycles, 97 null/background)
+- **Augmentation**: Rotations, exposure adjustments, noise injection
+- **Platform**: [Roboflow](https://app.roboflow.com)
+
+### DINOv3 Team Classifier
+- **Backbone**: DINOv3 ViT-S/16 (frozen, pretrained on LVD-142M)
+- **Head**: Scikit-learn Logistic Regression
+- **Dataset**: ~700 high-quality crops across 11 teams
+- **Features**: 384-dimensional embeddings
+
+## Performance
+
+The system is optimized for broadcast footage with:
+- High-speed motion blur handling
+- Rapid camera cut recovery
+- Persistent identity tracking across occlusions
+- Label locking after high-confidence agreement
+
+## Citation
+
+If you use these weights in your research, please cite:
+
+```bibtex
+@software{motogp_team_detection_2025,
+  author = {Amit John},
+  title = {MotoGP Team Detection and Re-Identification},
+  year = {2025},
+  publisher = {GitHub},
+  url = {https://github.com/johnamit/mgp-detect}
+}
+```
+
+## License
+
+MIT License - See the [GitHub repository](https://github.com/johnamit/mgp-detect) for full details.
+
+## Acknowledgments
+
+- [Ultralytics](https://ultralytics.com/) for YOLOv8
+- [Meta AI](https://github.com/facebookresearch/dinov3) for DINOv3
+- [Roboflow](https://roboflow.com/) for annotation tools

dinov3_team_classifier.pkl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:be39b1d411cd99a60ad78f19d31eb70a5bba1d59b9d79232b9de36d1911337c5
+size 35063

motogp_yolov8m_detector.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c315f1711280cf24907935f08589c2504ef6f858e9ec4e815a7c4ed44160dd0d
+size 52038354