This project is part of the Machine Learning Path Dicoding. The goal of this project is to develop an image classification model capable of recognizing different types of waste automatically.

This project utilizes a Deep Learning approach by leveraging the Convolutional Neural Network (CNN) model and the Xception architecture. The main objective is to build a model capable of classifying waste into specific categories.

• Dataset: The dataset used can be found at Kaggle Garbage Classification Dataset.
• Model: Built using CNN and Xception.
• Model Formats:
  • .h5 (HDF5)
  • SavedModel (TensorFlow)
  • TF-Lite (for mobile devices)
  • TFJS (for web-based applications)
• Jupyter Notebook: The project implementation is available on Kaggle Notebook.

1. Install Dependencies Ensure you have installed the required dependencies:

   pip install -r requirements.txt

2. Download the Dataset Download the dataset from this link and place it in the appropriate directory.

3. Train the Model Run the notebook to train the model:

   jupyter notebook

4. Export the Model The trained model can be exported into various formats for use on different platforms.

• notebooks/: Contains Jupyter Notebook files for training and evaluation.
• models/: Stores the models in various formats.
• data/: Directory where the dataset is stored.

• Python
• TensorFlow
• Keras
• Scikit-learn
• Jupyter Notebook

Contributions are welcome! If you want to contribute, feel free to fork this repository, create a new branch, and submit a pull request.

git clone https://github.com/alrescha79-cmd/garbage-classification.git

git checkout -b new-feature

This project was created by:

• Anggun Caksono

If you encounter any issues, feel free to open a new issue.