🧠 Contribution Guidelines – Garbage Classification with Transfer Learning Thank you for showing interest in contributing to Garbage Classification with Transfer Learning! This project uses cutting-edge deep learning models to classify waste into six types and helps build a smarter, cleaner environment. Your ideas, code, and collaboration are truly appreciated.
🚀 Getting Started with Contributions Before you begin coding, please follow these steps:
✅ Check the Issues Section Look for issues labeled:
good first issue
bug
enhancement
Pick one that matches your interest and comment to get it assigned.
Read any linked discussions or instructions from the maintainers.
💡 Want to Suggest a New Feature or Improvement? Please open a new issue and include:
A clear and concise description of the feature or idea.
Screenshots or mockups (if applicable).
A short video demo (optional but appreciated).
Please wait for a maintainer’s review or feedback before submitting a Pull Request.
🛠️ How to Contribute 📥 Set Up the Project Locally Follow the instructions in README.md or relevant setup notebooks (Week1/Week2) to:
Prepare your environment (Python + TensorFlow/Keras)
Load the dataset correctly using the given structure
Run the notebook or main scripts for model training or prediction
🌿 Create a New Branch bash Copy Edit git checkout -b feature/your-feature-name ✏️ Make Your Changes Ensure your changes are tested locally before submitting.
Maintain modular structure of model code (e.g., dataset loading, preprocessing, evaluation).
Document your code where necessary.
If working on UI (Gradio/Streamlit), preserve layout consistency.
✅ Commit Your Changes bash Copy Edit git commit -m "Add: your feature description" 📤 Push and Create a Pull Request bash Copy Edit git push origin feature/your-feature-name Go to GitHub and open a Pull Request (PR) targeting the main branch.
Link the PR to the relevant issue if applicable.
Add a brief explanation of what you've changed or added.
🌟 Contributor Tips Use meaningful variable names and follow PEP-8 standards.
Reuse components (e.g., data augmentations, model blocks) when possible.
Run notebooks end-to-end before submitting.
Be open to feedback from mentors and project maintainers.
🙌 Let’s Collaborate! By contributing, you're helping build a more sustainable and intelligent future using AI. We welcome contributors from all backgrounds — whether you're new to machine learning or an experienced developer.
Together, let's create impact through clean code and clean data! ♻️💻