{"id":24629445,"url":"https://github.com/bjornmelin/ml-vision-lab","last_synced_at":"2026-04-04T16:34:20.353Z","repository":{"id":274048243,"uuid":"921478829","full_name":"BjornMelin/ml-vision-lab","owner":"BjornMelin","description":"👁️ Production-grade computer vision implementations. Real-world applications in image processing, object detection, and video analytics with GPU acceleration. 📸","archived":false,"fork":false,"pushed_at":"2025-02-12T20:24:48.000Z","size":183,"stargazers_count":1,"open_issues_count":2,"forks_count":0,"subscribers_count":1,"default_branch":"main","last_synced_at":"2025-02-12T21:30:06.744Z","etag":null,"topics":["computer-vision","cuda","deep-learning","image-processing","object-detection","opencv","pytorch","video-analytics"],"latest_commit_sha":null,"homepage":"","language":"Python","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"mit","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/BjornMelin.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":"CONTRIBUTING.md","funding":null,"license":"LICENSE","code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null,"governance":null,"roadmap":null,"authors":null,"dei":null,"publiccode":null,"codemeta":null}},"created_at":"2025-01-24T02:48:22.000Z","updated_at":"2025-02-04T03:25:11.000Z","dependencies_parsed_at":"2025-02-14T11:32:35.877Z","dependency_job_id":null,"html_url":"https://github.com/BjornMelin/ml-vision-lab","commit_stats":null,"previous_names":["bjornmelin/ml-vision-lab"],"tags_count":0,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/BjornMelin%2Fml-vision-lab","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/BjornMelin%2Fml-vision-lab/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/BjornMelin%2Fml-vision-lab/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/BjornMelin%2Fml-vision-lab/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/BjornMelin","download_url":"https://codeload.github.com/BjornMelin/ml-vision-lab/tar.gz/refs/heads/main","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":244554042,"owners_count":20471172,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2022-07-04T15:15:14.044Z","host_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub","repositories_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories","repository_names_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repository_names","owners_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners"}},"keywords":["computer-vision","cuda","deep-learning","image-processing","object-detection","opencv","pytorch","video-analytics"],"created_at":"2025-01-25T06:12:50.775Z","updated_at":"2025-12-31T00:08:45.769Z","avatar_url":"https://github.com/BjornMelin.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"# ML Vision Lab 👁️\n\n[![Python](https://img.shields.io/badge/python-3.11%2B-blue.svg)](https://www.python.org/downloads/)\n[![PyTorch](https://img.shields.io/badge/pytorch-2.3%2B-red.svg)](https://pytorch.org/)\n[![TensorFlow](https://img.shields.io/badge/tensorflow-2.15%2B-orange.svg)](https://tensorflow.org/)\n[![OpenCV](https://img.shields.io/badge/opencv-5.0%2B-green.svg)](https://opencv.org/)\n[![CUDA](https://img.shields.io/badge/cuda-12.2%2B-green.svg)](https://developer.nvidia.com/cuda-toolkit)\n[![Projects](https://img.shields.io/badge/projects-5%2B-brightgreen.svg)](https://github.com/BjornMelin/ml-vision-lab/pulse)\n[![License](https://img.shields.io/badge/license-MIT-blue.svg)](LICENSE)\n\n\u003e Modular computer vision implementations - A collection of production-grade vision systems spanning multiple domains.\n\n[Featured Projects](#-project-matrix) • [Installation](#-installation) • [Quick Start](#-quick-start) • [Contributing](#-contributing)\n\n## 📑 Table of Contents\n\n- [Project Organization](#-project-organization)\n- [Core Features](#-core-features)\n- [Prerequisites](#-prerequisites)\n- [Tech Stack](#-tech-stack)\n- [Installation](#-installation)\n- [Quick Start](#-quick-start)\n- [Project Matrix](#-project-matrix)\n- [Development Standards](#-development-standards)\n- [Contributing](#-contributing)\n- [Documentation](#-documentation)\n- [Benchmarks](#-benchmarks)\n- [Versioning](#-versioning)\n- [Authors](#-authors)\n- [Citation](#-citation)\n- [License](#-license)\n- [Acknowledgments](#-acknowledgments)\n\n## 🗂️ Project Organization\n\n```mermaid\ngraph TD\n    A[ML Vision Lab] --\u003e B[projects]\n    A --\u003e C[core]\n    A --\u003e D[docs]\n    B --\u003e E[food-classification]\n    B --\u003e F[object-detection]\n    B --\u003e G[medical-imaging]\n    B --\u003e H[satellite-analysis]\n    C --\u003e I[utils]\n    C --\u003e J[models]\n    C --\u003e K[pipelines]\n    D --\u003e L[api]\n    D --\u003e M[guides]\n    D --\u003e N[architecture]\n```\n\n```\nml-vision-lab/\n├── projects/               # Individual vision projects\n│   ├── food-classification/  # Food analysis system\n│   ├── object-detection/      # Real-time detection\n│   ├── medical-imaging/       # DICOM processing\n│   └── satellite-analysis/    # Geospatial vision\n├── core/                   # Shared vision components\n│   ├── utils/              # Common utilities\n│   ├── models/             # Base model architectures\n│   └── pipelines/          # Processing workflows\n└── docs/                   # Project documentation\n```\n\n## ✨ Core Features\n\n```mermaid\nmindmap\n  root((ML Vision Lab))\n    Cross-Project\n      Modular architecture\n      Shared pipelines\n      Hardware optimization\n      Standardized metrics\n    Project Types\n      Classification\n      Detection\n      Medical\n      Satellite\n    Optimization\n      GPU acceleration\n      TensorRT\n      Memory efficiency\n    Development\n      MLflow tracking\n      DVC versioning\n      CI/CD pipelines\n```\n\n**Cross-Project Capabilities**\n\n- Modular project architecture\n- Shared preprocessing pipelines\n- Hardware-optimized inference\n- Standardized evaluation metrics\n- GPU-accelerated processing\n- Production deployment examples\n- Memory-efficient inference\n- TensorRT integration\n\n**Project Types**\n\n- Image Classification\n- Object Detection \u0026 Tracking\n- Medical Imaging Analysis\n- Satellite Imagery Processing\n- Industrial Quality Inspection\n\n## 🔧 Prerequisites\n\n- Python 3.11+\n- CUDA 12.2+\n- OpenCV 5.0+\n- PyTorch 2.3+\n- TensorFlow 2.15+\n- NVIDIA GPU (Compute Capability 6.0+)\n\n## 🛠️ Tech Stack\n\n```mermaid\ngraph TD\n    A[Tech Stack] --\u003e B[Core Libraries]\n    A --\u003e C[Project Libraries]\n    B --\u003e D[PyTorch]\n    B --\u003e E[TensorFlow]\n    B --\u003e F[OpenCV]\n    B --\u003e G[CUDA]\n    C --\u003e H[MONAI]\n    C --\u003e I[RasterIO]\n    C --\u003e J[DeepSORT]\n    C --\u003e K[MLflow]\n```\n\n**Core Libraries**\n\n- PyTorch - Deep learning framework\n- TensorFlow - Machine learning platform\n- OpenCV - Computer vision operations\n- CUDA - GPU acceleration\n- TensorRT - Inference optimization\n- NumPy - Numerical computing\n- Pandas - Data manipulation\n- Scikit-learn - Machine learning utilities\n- Matplotlib - Visualization\n- Plotly - Visualization\n- Pillow - Image processing\n\n**Project-Specific Libraries**\n\n- MONAI - Medical imaging\n- RasterIO - Geospatial analysis\n- DeepSORT - Object tracking\n- Albumentations - Image augmentation\n- MLflow - Experiment tracking\n- DVC - Data version control\n\n## 📦 Installation\n\n```bash\n# Clone repository\ngit clone https://github.com/BjornMelin/ml-vision-lab.git\ncd ml-vision-lab\n\n# Create virtual environment\npython -m venv .venv\nsource .venv/bin/activate  # Linux/MacOS\n# or\n.venv\\Scripts\\activate  # Windows\n\n# Install core requirements\npip install -r requirements.txt\n\n# Install project-specific requirements (optional)\npip install -r projects/food-classification/requirements.txt\n```\n\n## 🚀 Quick Start\n\n**Food Classification**\n\n```python\nfrom projects.food_classification import predict\n\nresult = predict(\"pizza.jpg\")\nprint(f\"Identified: {result.label} ({result.confidence:.1%})\")\n```\n\n**Object Detection**\n\n```python\nfrom projects.object_detection import VideoAnalyzer\n\nanalyzer = VideoAnalyzer(model=\"yolov9\")\nanalyzer.process_stream(\"input.mp4\", output=\"results.mp4\")\n```\n\n## 📊 Project Matrix\n\n| Project                                             | Task                 | Models              | Input Types   |\n| --------------------------------------------------- | -------------------- | ------------------- | ------------- |\n| [Food Classification](projects/food-classification) | Image Classification | EfficientNetV2, ViT | JPEG/PNG      |\n| [Object Detection](projects/object-detection)       | Real-time Tracking   | YOLOv9, DeepSORT    | Video Streams |\n| [Medical Imaging](projects/medical-imaging)         | DICOM Analysis       | UNet3+, MONAI       | CT/MRI Scans  |\n| [Satellite Analysis](projects/satellite-analysis)   | Geospatial ML        | ResNet50-ADE20K     | GeoTIFF       |\n\n## 🔧 Development Standards\n\n```mermaid\nflowchart TD\n    A[Development] --\u003e B[Code Quality]\n    A --\u003e C[Testing]\n    A --\u003e D[Documentation]\n    B --\u003e E[Black]\n    B --\u003e F[MyPy]\n    C --\u003e G[PyTest]\n    C --\u003e H[Coverage]\n    D --\u003e I[Docstrings]\n    D --\u003e J[Examples]\n```\n\n**Code Quality**\n\n```bash\n# Format all projects\nblack projects/\n\n# Type checking\nmypy projects/\n\n# Run tests\npytest projects/ --cov\n```\n\n**Project Structure Template**\n\n```\nprojects/new-project/\n├── app/          # Application interface\n├── engine/       # Core logic\n├── models/       # Trained weights\n├── tests/        # Unit tests\n├── README.md     # Project docs\n└── requirements.txt # Local dependencies\n```\n\n## 🤝 Contributing\n\n**Adding New Projects**\n\n1. Create project folder in `projects/`\n2. Follow structure template\n3. Add cross-links to:\n   - Core utilities (avoid duplication)\n   - Related projects\n4. Submit PR with:\n   - [ ] Black-formatted code\n   - [ ] Google-style docstrings\n   - [ ] Unit tests (≥80% coverage)\n\nSee [CONTRIBUTING.md](CONTRIBUTING.md) for full guidelines.\n\n## 📚 Documentation\n\n### Pipeline Optimization\n\n```mermaid\ngraph LR\n    A[Input] --\u003e B[Preprocessing]\n    B --\u003e C[Inference]\n    C --\u003e D[Postprocessing]\n    B --\u003e E[GPU Pipeline]\n    C --\u003e F[TensorRT]\n    D --\u003e G[Batch Processing]\n```\n\n- GPU-accelerated preprocessing\n- Batch processing optimization\n- Memory-efficient inference\n- TensorRT integration\n- Multi-GPU support\n- Mixed precision training\n\n### Models\n\n| Model      | Task         | Performance | Speed (FPS) |\n| ---------- | ------------ | ----------- | ----------- |\n| YOLOv8     | Detection    | mAP: 52.3   | 120         |\n| Mask R-CNN | Segmentation | mAP: 47.8   | 45          |\n| DeepSORT   | Tracking     | MOTA: 76.5  | 80          |\n\n## 📊 Benchmarks\n\nPerformance on standard datasets:\n\n| Task         | Dataset | Model      | GPU  | FPS | Accuracy   |\n| ------------ | ------- | ---------- | ---- | --- | ---------- |\n| Detection    | COCO    | YOLOv8     | A100 | 120 | mAP: 52.3  |\n| Segmentation | COCO    | Mask R-CNN | V100 | 45  | mAP: 47.8  |\n| Tracking     | MOT17   | DeepSORT   | 3090 | 80  | MOTA: 76.5 |\n\n## 📌 Versioning\n\nWe use [SemVer](http://semver.org/) for versioning. For available versions, see the [tags on this repository](https://github.com/BjornMelin/ml-vision-lab/tags).\n\n## ✍️ Authors\n\n**Bjorn Melin**\n\n- GitHub: [@BjornMelin](https://github.com/BjornMelin)\n- LinkedIn: [Bjorn Melin](https://linkedin.com/in/bjorn-melin)\n\n## 📝 Citation\n\n```bibtex\n@misc{melin2024mlvisionlab,\n  author = {Melin, Bjorn},\n  title = {ML Vision Lab: Production Computer Vision Implementations},\n  year = {2024},\n  publisher = {GitHub},\n  url = {https://github.com/BjornMelin/ml-vision-lab}\n}\n```\n\n## 📄 License\n\nThis project is licensed under the MIT License - see the [LICENSE](LICENSE) file for details.\n\n## 🙏 Acknowledgments\n\n- OpenCV community\n- YOLO authors and contributors\n- Deep SORT implementation team\n- Medical imaging community (MONAI)\n- Satellite imagery processing teams\n- TensorFlow and PyTorch teams\n- NVIDIA for CUDA and TensorRT support\n\n---\n\n![Architecture Overview](docs/architecture/overview.png)\n\nMade with 👁️ and ❤️ by Bjorn Melin\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fbjornmelin%2Fml-vision-lab","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fbjornmelin%2Fml-vision-lab","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fbjornmelin%2Fml-vision-lab/lists"}