{"id":24912369,"url":"https://github.com/bjornmelin/edge-ai-engineering","last_synced_at":"2026-05-02T13:33:33.920Z","repository":{"id":274049809,"uuid":"921751917","full_name":"BjornMelin/edge-ai-engineering","owner":"BjornMelin","description":"📱 Optimized ML for edge devices. Showcasing efficient model deployment, GPU-CPU memory transfer optimization, and real-world edge AI applications. 🤖","archived":false,"fork":false,"pushed_at":"2025-01-24T14:51:18.000Z","size":6,"stargazers_count":0,"open_issues_count":0,"forks_count":0,"subscribers_count":1,"default_branch":"main","last_synced_at":"2025-03-28T04:18:42.340Z","etag":null,"topics":["cuda","edge-computing","embedded-systems","gpu-optimization","iot","mobile-ml","model-optimization","python","tflite"],"latest_commit_sha":null,"homepage":"","language":null,"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":null,"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":"2025-01-24T14:49:12.000Z","updated_at":"2025-01-24T14:51:21.000Z","dependencies_parsed_at":"2025-01-24T15:43:31.347Z","dependency_job_id":null,"html_url":"https://github.com/BjornMelin/edge-ai-engineering","commit_stats":null,"previous_names":["bjornmelin/edge-ai-engineering"],"tags_count":0,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/BjornMelin%2Fedge-ai-engineering","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/BjornMelin%2Fedge-ai-engineering/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/BjornMelin%2Fedge-ai-engineering/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/BjornMelin%2Fedge-ai-engineering/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/BjornMelin","download_url":"https://codeload.github.com/BjornMelin/edge-ai-engineering/tar.gz/refs/heads/main","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":245966927,"owners_count":20701758,"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":["cuda","edge-computing","embedded-systems","gpu-optimization","iot","mobile-ml","model-optimization","python","tflite"],"created_at":"2025-02-02T05:19:24.884Z","updated_at":"2026-05-02T13:33:33.865Z","avatar_url":"https://github.com/BjornMelin.png","language":null,"funding_links":[],"categories":[],"sub_categories":[],"readme":"# Edge AI Engineering 📱\n\n[![Python](https://img.shields.io/badge/python-3.8%2B-blue.svg)](https://www.python.org/downloads/)\n[![TensorFlow Lite](https://img.shields.io/badge/tflite-2.14%2B-orange.svg)](https://www.tensorflow.org/lite)\n[![PyTorch Mobile](https://img.shields.io/badge/pytorch--mobile-2.2%2B-red.svg)](https://pytorch.org/mobile)\n[![CUDA](https://img.shields.io/badge/cuda-11.8%2B-green.svg)](https://developer.nvidia.com/cuda-toolkit)\n[![License](https://img.shields.io/badge/license-MIT-blue.svg)](LICENSE)\n\n\u003e Optimized machine learning models for edge and mobile devices. Showcasing efficient model deployment, optimization techniques, and real-world edge AI applications.\n\n[Features](#features) • [Installation](#installation) • [Quick Start](#quick-start) • [Documentation](#documentation) • [Contributing](#contributing)\n\n## 📑 Table of Contents\n- [Features](#features)\n- [Project Structure](#project-structure)\n- [Prerequisites](#prerequisites)\n- [Installation](#installation)\n- [Quick Start](#quick-start)\n- [Documentation](#documentation)\n  - [Models](#models)\n  - [Optimization](#optimization)\n  - [Benchmarks](#benchmarks)\n- [Contributing](#contributing)\n- [Versioning](#versioning)\n- [Authors](#authors)\n- [Citation](#citation)\n- [License](#license)\n- [Acknowledgments](#acknowledgments)\n\n## ✨ Features\n- Model quantization and optimization\n- Mobile-first architectures\n- Battery-efficient inference\n- Cross-platform deployment\n- Edge-optimized pipelines\n\n## 📁 Project Structure\n\n```mermaid\ngraph TD\n    A[edge-ai-engineering] --\u003e B[models]\n    A --\u003e C[optimization]\n    A --\u003e D[deployment]\n    A --\u003e E[benchmarks]\n    B --\u003e F[tflite]\n    B --\u003e G[pytorch-mobile]\n    C --\u003e H[quantization]\n    C --\u003e I[compression]\n    D --\u003e J[android]\n    D --\u003e K[ios]\n    E --\u003e L[performance]\n    E --\u003e M[battery]\n```\n\n\u003cdetails\u003e\n\u003csummary\u003eClick to expand full directory structure\u003c/summary\u003e\n\n```plaintext\nedge-ai-engineering/\n├── models/            # Model implementations\n│   ├── tflite/       # TensorFlow Lite models\n│   └── pytorch/      # PyTorch Mobile models\n├── optimization/      # Optimization tools\n│   ├── quantization/ # Model quantization\n│   └── compression/  # Model compression\n├── deployment/       # Platform-specific deployment\n│   ├── android/     # Android deployment\n│   └── ios/         # iOS deployment\n├── benchmarks/       # Performance testing\n└── README.md         # Documentation\n```\n\u003c/details\u003e\n\n## 🔧 Prerequisites\n- Python 3.8+\n- TensorFlow Lite 2.14+\n- PyTorch Mobile 2.2+\n- Android SDK/NDK\n- Xcode (for iOS)\n\n## 📦 Installation\n\n```bash\n# Clone repository\ngit clone https://github.com/BjornMelin/edge-ai-engineering.git\ncd edge-ai-engineering\n\n# Create environment\npython -m venv venv\nsource venv/bin/activate\n\n# Install dependencies\npip install -r requirements.txt\n```\n\n## 🚀 Quick Start\n\n```python\nfrom edge_ai import optimization, deployment\n\n# Optimize model for mobile\noptimized_model = optimization.quantize_for_mobile(\n    model,\n    target_platform=\"android\",\n    quantization=\"int8\"\n)\n\n# Deploy to device\ndeployment = deployment.MobileDeployment(\n    model=optimized_model,\n    platform=\"android\",\n    optimize_battery=True\n)\n\n# Generate deployment package\ndeployment.export()\n```\n\n## 📚 Documentation\n\n### Models\n\n| Model | Task | Size | Latency (ms) |\n|-------|------|------|--------------|\n| MobileNetV3 | Classification | 4MB | 15 |\n| TinyYOLO | Detection | 8MB | 25 |\n| MobileViT | Vision | 6MB | 20 |\n\n### Optimization\n- Int8 quantization\n- Model pruning\n- Architecture optimization\n- Memory footprint reduction\n\n### Benchmarks\nPerformance on different devices:\n\n| Device | Model | Battery Impact | FPS | Memory |\n|--------|-------|----------------|-----|---------|\n| Pixel 6 | MobileNet | 2%/hr | 30 | 120MB |\n| iPhone 13 | TinyYOLO | 3%/hr | 25 | 150MB |\n| RPi 4 | MobileViT | N/A | 15 | 200MB |\n\n## 🤝 Contributing\n- [Contributing Guidelines](CONTRIBUTING.md)\n- [Code of Conduct](CODE_OF_CONDUCT.md)\n- [Development Guide](DEVELOPMENT.md)\n\n## 📌 Versioning\nWe use [SemVer](http://semver.org/) for versioning. For available versions, see the [tags on this repository](https://github.com/BjornMelin/edge-ai-engineering/tags).\n\n## ✍️ Authors\n**Bjorn Melin**\n- GitHub: [@BjornMelin](https://github.com/BjornMelin)\n- LinkedIn: [Bjorn Melin](https://linkedin.com/in/bjorn-melin)\n\n## 📝 Citation\n```bibtex\n@misc{melin2024edgeaiengineering,\n  author = {Melin, Bjorn},\n  title = {Edge AI Engineering: Optimized Mobile Machine Learning},\n  year = {2024},\n  publisher = {GitHub},\n  url = {https://github.com/BjornMelin/edge-ai-engineering}\n}\n```\n\n## 📄 License\nThis project is licensed under the MIT License - see the [LICENSE](LICENSE) file for details.\n\n## 🙏 Acknowledgments\n- TensorFlow Lite team\n- PyTorch Mobile developers\n- Mobile ML community\n- Edge computing researchers\n\n---\nMade with 📱 and ❤️ by Bjorn Melin\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fbjornmelin%2Fedge-ai-engineering","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fbjornmelin%2Fedge-ai-engineering","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fbjornmelin%2Fedge-ai-engineering/lists"}