Hi everyone! 👋
I wanted to share a project I’ve been working on recently: YOLO CRAFT.
When fine-tuning YOLOv8 models for custom computer vision projects, I kept running into the same issue: most MLOps tools are packed with heavy frameworks, complex wrappers, or forced cloud setups. I wanted a solution that is extremely lightweight, fully transparent, and controlled directly through clean Python scripts—without any unnecessary overhead.
That’s why I built YOLO CRAFT:
Active Learning Loop (watcher.py): Automatically captures low-confidence frames from streams or webcams to continuously improve your model where it struggles most.
Multi-Class Labeler (labler.py): Interactive bounding box drawing with quick hotkeys (like using l to switch target classes) and built-in support for background-only frames.
Universal Edge Export (export_model.py): Exports trained models directly to TensorRT, TFLite, CoreML, or ONNX for real-time deployment on devices like Raspberry Pi or NVIDIA Jetson.
Visual Evaluation & Reports (report.py): Generates automated visual metrics and before-and-after performance comparisons.
The project is completely open-source! Feel free to check out the repository, give it a try, and let me know what you think:
👉 GitHub Repository: https://github.com/NovaAixYoussef/yolo-craft
If you find YOLO CRAFT useful or interesting for your computer vision projects, leaving a star ⭐️ on GitHub would mean a lot!
What do you think of this script-based approach? I’d love to hear your feedback or ideas for new features.
Top comments (0)