Welcome to the Echo-Sort-ML repository. This repository contains the core implementation of the machine learning model used for the Echosort project. The model is designed to enhance the recycling process by automating the classification of recyclable materials.
Echosort is the final project in the Data Science program. It employs a Convolutional Neural Network (CNN) model, optimized using the cross-entropy loss function, to perform image classification tasks. The model identifies objects in images and categorizes them into one of three labels:
- Plastic
- Paper
- Other
- Model Training: The repository includes scripts for training the CNN model on a diverse dataset of labeled images representing the three categories.
- Model Testing: Tools for validating and testing the model's performance, including accuracy and other metrics.
- Dataset Preparation: Preprocessing scripts to prepare the dataset for optimal training results.
- Clone the repository:
git clone https://github.com/BenBashi/Echo-Sort-ML.git
- Navigate to the repository directory and follow the setup instructions in the
setup.mdfile. - Run the training or testing scripts as needed.