{"id":31132979,"url":"https://github.com/arsh-pixel-cmd/ai-image-classifier","last_synced_at":"2026-04-10T06:49:37.941Z","repository":{"id":314492797,"uuid":"1055731302","full_name":"Arsh-pixel-cmd/AI-Image-Classifier","owner":"Arsh-pixel-cmd","description":"AI Image Classifier is a web app that uses AI and deep learning to classify images in real-time. Built with Streamlit, TensorFlow (MobileNetV2), OpenCV, and NumPy, it allows users to upload single or multiple images and get the top-3 predictions with confidence scores instantly in the browser.","archived":false,"fork":false,"pushed_at":"2025-09-12T19:38:55.000Z","size":74,"stargazers_count":0,"open_issues_count":1,"forks_count":0,"subscribers_count":0,"default_branch":"main","last_synced_at":"2025-09-12T20:52:25.808Z","etag":null,"topics":["docker","numpy","opencv","python3","streamlit","tensorflow2","uv"],"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/Arsh-pixel-cmd.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,"zenodo":null,"notice":null,"maintainers":null,"copyright":null,"agents":null,"dco":null,"cla":null}},"created_at":"2025-09-12T17:58:52.000Z","updated_at":"2025-09-12T19:55:05.000Z","dependencies_parsed_at":"2025-09-12T20:52:27.571Z","dependency_job_id":"c26b8871-73e4-4190-95cf-4ce7ac7279b1","html_url":"https://github.com/Arsh-pixel-cmd/AI-Image-Classifier","commit_stats":null,"previous_names":["arsh-pixel-cmd/ai-image-classifier"],"tags_count":null,"template":false,"template_full_name":null,"purl":"pkg:github/Arsh-pixel-cmd/AI-Image-Classifier","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Arsh-pixel-cmd%2FAI-Image-Classifier","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Arsh-pixel-cmd%2FAI-Image-Classifier/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Arsh-pixel-cmd%2FAI-Image-Classifier/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Arsh-pixel-cmd%2FAI-Image-Classifier/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/Arsh-pixel-cmd","download_url":"https://codeload.github.com/Arsh-pixel-cmd/AI-Image-Classifier/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Arsh-pixel-cmd%2FAI-Image-Classifier/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":279002215,"owners_count":26083340,"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":"2025-10-09T02:00:07.460Z","response_time":59,"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":["docker","numpy","opencv","python3","streamlit","tensorflow2","uv"],"created_at":"2025-09-18T05:02:16.085Z","updated_at":"2025-10-09T23:03:33.838Z","avatar_url":"https://github.com/Arsh-pixel-cmd.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"# 🖼️ AI Image Classifier\n\nAn AI-powered image classification web app built with **Streamlit**, **TensorFlow (MobileNetV2)**, **OpenCV**, and **NumPy**. Upload single or multiple images and get real-time AI predictions directly in your browser.\n\n![Python](https://img.shields.io/badge/Python-3.12-blue.svg)\n![TensorFlow](https://img.shields.io/badge/TensorFlow-2.x-orange.svg)\n![Streamlit](https://img.shields.io/badge/Streamlit-1.x-red.svg)\n![License](https://img.shields.io/badge/License-MIT-green.svg)\n\n---\n\n## 🚀 Features\n\n- ✅ **Multi-image upload** with drag \u0026 drop support\n- ✅ **MobileNetV2** pre-trained on ImageNet dataset (1000+ classes)\n- ✅ **Top-3 predictions** with confidence percentages\n- ✅ **Grid preview** for batch image processing\n- ✅ **Real-time classification** with instant results\n- ✅ **Error handling** for invalid file formats\n- ✅ **Lightweight** - runs locally with zero setup complexity\n\n---\n\n## 🛠️ Tech Stack\n\n| Component | Technology |\n|-----------|------------|\n| **Frontend/UI** | [Streamlit](https://streamlit.io/) |\n| **AI Model** | TensorFlow Keras (MobileNetV2) |\n| **Image Processing** | OpenCV, Pillow (PIL) |\n| **Data Handling** | NumPy |\n| **Package Manager** | uv |\n\n---\n\n## 📂 Project Structure\n\nAI-image-classifier/\n├── main.py # Streamlit application\n├── pyproject.toml # Project metadata \u0026 dependencies\n├── uv.lock # Lockfile for reproducible installs\n├── README.md # Project documentation\n└── .venv/ # Virtual environment (auto-created)\n\n\n---\n\n## ⚡ Quick Start\n\n### Prerequisites\n- Python 3.12 or higher\n- uv package manager ([Install uv](https://docs.astral.sh/uv/getting-started/installation/))\n\n### Installation\n\n### 1️⃣ Clone the repository\n\n```bash\ngit clone https://github.com/Arsh-pixel-cmd/AI-Image-Classifier.git\ncd AI-Image-Classifier\n```\n\n###  2️⃣ Create virtual environment\n```bash\nuv venv --python 3.12\nsource .venv/bin/activate   # On macOS/Linux\n```\n\n# On Windows (PowerShell):\n```bash\n.venv\\Scripts\\activate\n```\n\n###  3️⃣ Install dependencies\n```bash\nuv add streamlit opencv-python pillow tensorflow numpy\n```\n\n💻 For macOS with Apple Silicon (M1/M2/M3)\n```bash\nuv add tensorflow-macos tensorflow-metal\n```\n\n###  **Access the app:**\n```\n- **Local:** http://localhost:8501\n- **Network:** URL shown in terminal\n```\n---\n\n## 🖥️ How It Works\n\n1. **Upload Images** → Drag \u0026 drop or browse files (JPG, PNG, JPEG)\n2. **Preprocessing** → Images resized to 224×224 pixels for MobileNetV2\n3. **AI Classification** → Model predicts from 1000+ ImageNet classes\n4. **Results Display** → Top-3 predictions with confidence scores\n\n### Supported Formats\n- JPG, JPEG, PNG\n- Multiple images (batch processing)\n- Maximum file size: 200MB per file\n\n---\n\n## 📊 Example Output\n\n🖼️ **Predictions for \"golden_retriever.jpg\"**\n\n- **Golden retriever:** 94.27%\n- **Labrador retriever:** 3.81%\n- **Nova Scotia duck tolling retriever:** 1.02%\n\n---\n\n## 🔧 Configuration\n\n### Custom Model Settings\n\nIn `main.py`, modify these parameters:\n\n```python\nIMG_SIZE = (224, 224)             # MobileNetV2 input size\nTOP_K = 3                          # Number of top predictions\nCONFIDENCE_THRESHOLD = 0.01        # Minimum confidence to display\n```\n\n---\n\n## 📈 Performance\n\n- **Model Size:** ~14MB (MobileNetV2)\n- **Inference Time:** ~100-300ms per image\n- **Accuracy:** 71.3% top-1 on ImageNet validation\n- **Classes:** 1000 ImageNet categories\n\n---\n\n## 🚀 Deployment Options\n\n### Local Development\n\n```bash\nuv run streamlit run main.py\n```\n\n---\n\n### Streamlit Cloud\n1. Push to GitHub\n2. Connect to [Streamlit Cloud](https://streamlit.io/cloud)\n3. Deploy with one click\n\n---\n\n### Docker (Optional)\n\n```dockerfile\nFROM python:3.12-slim\n\nWORKDIR /app\n\nCOPY . .\n\nRUN pip install uv \u0026\u0026 uv sync\n\nEXPOSE 8501\n\nCMD [\"uv\", \"run\", \"streamlit\", \"run\", \"main.py\", \"--server.port=8501\"]\n\n```\n\n---\n\n## 📌 Roadmap\n\n- [ ] **Export Results** → Download predictions as CSV/JSON\n- [ ] **Confidence Charts** → Visual probability bars\n- [ ] **Custom Models** → Upload your own trained models\n- [ ] **Batch Analysis** → Process entire folders\n- [ ] **API Endpoint** → REST API for programmatic access\n- [ ] **Enhanced UI** → Dark mode, animations, themes\n\n---\n\n## 🤝 Contributing\n\n1. Fork the repository\n2. Create feature branch (`git checkout -b feature/amazing-feature`)\n3. Commit changes (`git commit -m 'Add amazing feature'`)\n4. Push to branch (`git push origin feature/amazing-feature`)\n5. Open a Pull Request\n\n---\n\n## 📄 License\n\nThis project is licensed under the **MIT License** - see the [LICENSE](LICENSE) file for details.\n\n---\n\n## 👨‍💻 Author\n\n**Arsh Mishra**\n- 🚀 Passionate about AI, ML, and Full-Stack Development\n- 💼 Building innovative solutions with modern tech stacks\n- 📧 [LinkedIn](https://www.linkedin.com/in/arsh-mishra-030093325/) \n- 🐙 [GitHub](https://github.com/Arsh-pixel-cmd)\n\n---\n\n## 🙏 Acknowledgments\n\n- TensorFlow team for MobileNetV2 architecture\n- Streamlit for the amazing web framework\n- ImageNet dataset contributors\n- Open source community\n\n---\n\n**⭐ Star this repo if you found it helpful!**\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Farsh-pixel-cmd%2Fai-image-classifier","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Farsh-pixel-cmd%2Fai-image-classifier","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Farsh-pixel-cmd%2Fai-image-classifier/lists"}