This repository contains the source code and documentation for the Waste Classification project. The project includes a Laravel-based web backend, Python prediction scripts, and a Jupyter notebook with experiments and analysis.
- Backend and web app:
app/Waste-classification-main - Prediction script:
app/Waste-classification-main/rac-ai/scripts/predict_waste.py - Experiment notebook:
buiquangchien_6_waste_classification.ipynb - Pretrained models:
models/(large model files are not included by default; seemodels/README.md)
- Python 3.8+ for the prediction scripts and notebook
- PHP 8+ and Composer for the Laravel backend (if you run the web app)
- Node.js and npm/yarn to build frontend assets (optional)
- Create a virtual environment (recommended):
python -m venv .venv
# Windows PowerShell
.\.venv\Scripts\Activate.ps1
# macOS / Linux
# source .venv/bin/activate- Install Python dependencies:
pip install -r requirements.txtpython app/Waste-classification-main/rac-ai/scripts/predict_waste.py --image path/to/img.jpg --model-dir app/Waste-classification-main/rac-ai/storage/app/modelModel weight files in models/ are often large and therefore not committed to the repository. See models/README.md for recommended options to manage models (Git LFS, releases, or external storage) and for instructions how to download them. A helper script is available at app/Waste-classification-main/scripts/download_models.py (populate MODELS with URLs).
- Fork the repository, create a branch, and open a pull request. Follow the existing code style and include tests or examples where appropriate.