A custom YOLO11 object detection model trained on the IP102 dataset ā designed for pest detection in precision agriculture.
> Model Purpose: Detect and classify 102 pest species in real-time field conditions using computer vision.
- Model: YOLO11 Small - Dataset: IP102 (Balanced, 34K+ images) - Image Sizes: Trained on 640x640 and 896x896 - Classes: 102 pest species - Framework: Ultralytics YOLO11s - Hardware: NVIDIA A100 GPU - Epochs: 77 - License: MIT License
| Metric | Train Set | Validation Set | |----------------------|-----------|-----------------| | Precision | 0.912 | 0.744 | | Recall | 0.923 | 0.789 | | [email protected] | 0.941 | 0.815 | | [email protected]:0.95 | 0.838 | 0.605 |
--- š Class List The model detects 102 agricultural pests, including:
āļø License This project is released under the MIT License ā free for personal and commercial use.
š Citation If you use this model in research or production, please cite the IP102 dataset:
Wu, S., Zhan, C., et al. "IP102: A Large-Scale Benchmark Dataset for Insect Pest Recognition." CVPR, 2019.
š¬ Questions? Open an issue or reach me on Hugging Face Discussions.
Run inference results = model.predict("yourimage.jpg", imgsz=640)