{"id":22202450,"url":"https://github.com/msadeqsirjani/adaptive_edge_ai","last_synced_at":"2026-04-12T23:38:18.275Z","repository":{"id":264908899,"uuid":"894641912","full_name":"msadeqsirjani/adaptive_edge_ai","owner":"msadeqsirjani","description":"Optimizing deep learning models for edge devices through intelligent compression and knowledge distillation. Achieve up to 90% model size reduction while maintaining performance, enabling efficient AI deployment on resource-constrained devices.","archived":false,"fork":false,"pushed_at":"2024-11-26T18:14:27.000Z","size":404,"stargazers_count":2,"open_issues_count":0,"forks_count":0,"subscribers_count":1,"default_branch":"master","last_synced_at":"2025-03-29T07:45:20.614Z","etag":null,"topics":["deep-learning","edge-ai","knowledge-distillation","model-compression","onnx-optimization","pytorch"],"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/msadeqsirjani.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":"2024-11-26T18:04:50.000Z","updated_at":"2025-02-26T12:00:22.000Z","dependencies_parsed_at":"2024-11-26T19:31:06.986Z","dependency_job_id":null,"html_url":"https://github.com/msadeqsirjani/adaptive_edge_ai","commit_stats":null,"previous_names":["msadeqsirjani/adaptive_edge_ai"],"tags_count":0,"template":false,"template_full_name":null,"purl":"pkg:github/msadeqsirjani/adaptive_edge_ai","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/msadeqsirjani%2Fadaptive_edge_ai","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/msadeqsirjani%2Fadaptive_edge_ai/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/msadeqsirjani%2Fadaptive_edge_ai/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/msadeqsirjani%2Fadaptive_edge_ai/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/msadeqsirjani","download_url":"https://codeload.github.com/msadeqsirjani/adaptive_edge_ai/tar.gz/refs/heads/master","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/msadeqsirjani%2Fadaptive_edge_ai/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":281745923,"owners_count":26554473,"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","status":"online","status_checked_at":"2025-10-30T02:00:06.501Z","response_time":61,"last_error":null,"robots_txt_status":"success","robots_txt_updated_at":"2025-07-24T06:49:26.215Z","robots_txt_url":"https://github.com/robots.txt","online":true,"can_crawl_api":true,"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":["deep-learning","edge-ai","knowledge-distillation","model-compression","onnx-optimization","pytorch"],"created_at":"2024-12-02T16:23:00.877Z","updated_at":"2025-10-30T04:37:30.121Z","avatar_url":"https://github.com/msadeqsirjani.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"# Adaptive Edge AI 🤖\n\n![Edge AI Banner](https://github.com/msadeqsirjani/adaptive_edge_ai/blob/master/docs/images/banner.png)\n\n## 📋 Overview\n\nAdaptive Edge AI is a project focused on optimizing and deploying deep learning models for edge devices through model compression and knowledge distillation techniques. This solution enables efficient AI model deployment on resource-constrained devices while maintaining high performance.\n\n## 🌟 Key Features\n\n- 🔄 Model Compression\n- 📚 Knowledge Distillation\n- 📱 Edge Device Optimization\n- 📊 Adaptive Performance Scaling\n- 🚀 ONNX Export Support\n\n## 🏗️ Architecture\n\n```mermaid\ngraph LR\nA[Teacher Model] --\u003e B[Knowledge Distillation]\nB --\u003e C[Student Model]\nC --\u003e D[Model Compression]\nD --\u003e E[Edge Deployment]\n```\n\n\n## 🛠️ Installation\n\n1. Clone the repository\n\n```bash\ngit clone https://github.com/msadeqsirjani/adaptive_edge_ai.git\n```\n\n2. Create and activate virtual environment\n\n```bash\npython -m venv .venv\nsource .venv/bin/activate # Linux/Mac\n# or\n.venv\\Scripts\\activate # Windows\n```\n\n3. Install dependencies\n\n```bash\npip install -r requirements.txt\n```\n\n\n## 📊 Performance Metrics\n\n| Model | Size | Accuracy | Inference Time |\n|-------|------|----------|----------------|\n| Teacher | 500MB | 95% | 100ms |\n| Student | 50MB | 92% | 20ms |\n| Compressed | 10MB | 90% | 5ms |\n\n## 💻 Usage\n\n### Training the Teacher Model\n\n```bash\npython main.py --mode train_teacher --data_path data/\n```\n\n### Knowledge Distillation\n\n```bash\npython main.py --mode distill --teacher_model best_teacher_model.pth\n```\n\n### Model Compression\n\n```bash\npython main.py --mode compress --model student_model.pth\n```\n\n\n## 📁 Project Structure\n\n```bash\nadaptive_edge_ai/\n├── data/ # Dataset directory (gitignored)\n├── src/\n│ ├── models/ # Model architectures\n│ ├── optimization/ # Compression algorithms\n│ ├── training/ # Training utilities\n│ └── utils/ # Helper functions\n├── outputs/ # Saved models \u0026 results\n├── tests/ # Unit tests\n├── requirements.txt # Dependencies\n└── main.py # Entry point\n```\n\n\n## 📈 Results\n\nOur compressed models achieve:\n- 📉 90% size reduction\n- ⚡ 20x faster inference\n- 💪 Minimal accuracy loss\n\n## 🤝 Contributing\n\nContributions are welcome! Please feel free to submit a Pull Request. For major changes, please open an issue first to discuss what you would like to change.\n\n## 📄 License\n\nThis project is licensed under the MIT License - see the [LICENSE](LICENSE) file for details.\n\n## 📬 Contact\n\n- `Mohammad Sadegh Sirjani` - [@msadeqsirjani](https://twitter.com/msadeqsirjani)\n- Email - `m.sadeq.sirjani@gmail.com`\n\n## 🙏 Acknowledgments\n\n- Thanks to relevant papers or projects\n- Special thanks to contributors\n- Inspired by related work\n\n---\n⭐ Don't forget to star this repo if you find it helpful!","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fmsadeqsirjani%2Fadaptive_edge_ai","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fmsadeqsirjani%2Fadaptive_edge_ai","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fmsadeqsirjani%2Fadaptive_edge_ai/lists"}