{"id":26753140,"url":"https://github.com/gitarber/cnn-image-classifier","last_synced_at":"2026-04-13T22:34:32.841Z","repository":{"id":284446134,"uuid":"954974438","full_name":"gitarber/cnn-image-classifier","owner":"gitarber","description":"A CNN-based image classifier built with PyTorch and FastAPI. Features model training, evaluation metrics, visualizations, and a web interface for real-time predictions. Includes comprehensive documentation and Jupyter notebooks.","archived":false,"fork":false,"pushed_at":"2025-03-25T23:00:20.000Z","size":20,"stargazers_count":0,"open_issues_count":0,"forks_count":0,"subscribers_count":1,"default_branch":"master","last_synced_at":"2025-06-13T03:46:27.149Z","etag":null,"topics":["cifar10","cnn","computer-vision","deep-learning","fastapi","image-classification","machine-learning","ml-project","python","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/gitarber.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}},"created_at":"2025-03-25T22:56:27.000Z","updated_at":"2025-03-25T23:03:29.000Z","dependencies_parsed_at":null,"dependency_job_id":"162eba23-eca3-433b-b79f-6f73c7d23d9d","html_url":"https://github.com/gitarber/cnn-image-classifier","commit_stats":null,"previous_names":["gitarber/cnn-image-classifier"],"tags_count":0,"template":false,"template_full_name":null,"purl":"pkg:github/gitarber/cnn-image-classifier","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/gitarber%2Fcnn-image-classifier","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/gitarber%2Fcnn-image-classifier/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/gitarber%2Fcnn-image-classifier/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/gitarber%2Fcnn-image-classifier/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/gitarber","download_url":"https://codeload.github.com/gitarber/cnn-image-classifier/tar.gz/refs/heads/master","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/gitarber%2Fcnn-image-classifier/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":286080680,"owners_count":31774117,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2026-04-13T20:17:16.280Z","status":"ssl_error","status_checked_at":"2026-04-13T20:17:08.216Z","response_time":93,"last_error":"SSL_read: unexpected eof while reading","robots_txt_status":"success","robots_txt_updated_at":"2025-07-24T06:49:26.215Z","robots_txt_url":"https://github.com/robots.txt","online":false,"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":["cifar10","cnn","computer-vision","deep-learning","fastapi","image-classification","machine-learning","ml-project","python","pytorch"],"created_at":"2025-03-28T13:17:58.686Z","updated_at":"2026-04-13T22:34:32.834Z","avatar_url":"https://github.com/gitarber.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"# CNN Image Classifier\n\nA deep learning project that implements a Convolutional Neural Network (CNN) for image classification using PyTorch and FastAPI. The project includes model training, evaluation, visualization, and a web interface for real-time predictions.\n\n## Features\n\n- **Model Architecture**: Customizable CNN implementation with configurable layers\n- **Data Pipeline**: Efficient data loading and preprocessing with augmentation\n- **Training**: Configurable training loop with early stopping and checkpointing\n- **Evaluation**: Comprehensive metrics and visualizations\n- **Web Interface**: FastAPI-based web application for real-time predictions\n- **Documentation**: Detailed documentation and interactive notebooks\n\n## Documentation\n\n- [Technical Documentation](docs/TECHNICAL.md) - Detailed technical specifications and implementation details\n- [API Documentation](docs/API.md) - API endpoints and usage guide\n- [Development Guide](docs/DEVELOPMENT.md) - Guide for developers and contributors\n\n## Project Structure\n\n```\ncnn-image-classifier/\n├── src/\n│   ├── data/           # Data loading and preprocessing\n│   ├── models/         # Model architecture and training\n│   ├── utils/          # Utility functions\n│   └── config.py       # Configuration settings\n├── app/                # FastAPI web application\n├── docs/              # Documentation\n├── notebooks/         # Jupyter notebooks\n├── data/             # Dataset storage\n├── models/           # Saved models\n├── results/          # Training results and visualizations\n└── logs/             # Training logs\n```\n\n## Installation\n\n1. Clone the repository:\n```bash\ngit clone https://github.com/gitarber/cnn-image-classifier.git\ncd cnn-image-classifier\n```\n\n2. Create and activate a virtual environment:\n```bash\npython -m venv venv\n# On Windows:\n.\\venv\\Scripts\\activate\n# On Unix or MacOS:\nsource venv/bin/activate\n```\n\n3. Install dependencies:\n```bash\npip install -r requirements.txt\n```\n\n## Usage\n\n### Training the Model\n\n```bash\npython -m src.main\n```\n\nThis will:\n- Load and preprocess the CIFAR-10 dataset\n- Train the CNN model\n- Generate visualizations and metrics\n- Save the best model\n\n### Running the Web Interface\n\n```bash\npython -m app.main\n```\n\nAccess the web interface at `http://localhost:8000/docs`\n\n## Configuration\n\nThe project is highly configurable through `src/config.py`:\n- Dataset parameters\n- Model architecture\n- Training settings\n- Data augmentation\n- Visualization options\n\n## Results\n\nThe training process generates:\n- Model checkpoints\n- Training history plots\n- Confusion matrix\n- Feature maps\n- Class activation maps\n\n## Contributing\n\nContributions are welcome! Please feel free to submit a Pull Request. See our [Development Guide](docs/DEVELOPMENT.md) for more details.\n\n## License\n\nThis project is licensed under the MIT License - see the LICENSE file for details.\n\n## Author\n\n- **Arber Shquti** - [GitHub](https://github.com/gitarber) ","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fgitarber%2Fcnn-image-classifier","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fgitarber%2Fcnn-image-classifier","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fgitarber%2Fcnn-image-classifier/lists"}