♻️ Garbage Sorting Image Classification 🚮

This project is an AI-powered image classification web application that classifies uploaded waste images into one of four categories:

• 🥫 METAL
• 🍃 ORGANIC
• 📄 PAPER
• 🛍️ PLASTIC

It leverages a pretrained MobileNetV2 model fine-tuned on a custom waste classification dataset and is deployed through an interactive Streamlit web interface.

✨ Streamline waste management with intelligent sorting for a cleaner, greener future! 🌱

---

Table of Contents

1. Overview
2. Project Features
3. Setup Instructions
4. Run the Application
5. Model Details
6. App Usage
7. Sample Output

---

Overview

The Waste Classifier Web App enables users to upload an image of waste, and the model will predict its category. This solution aims to:

• Automate waste sorting for environmental sustainability.
• Leverage deep learning transfer learning techniques using MobileNetV2.
• Provide an easy-to-use interface using Streamlit.

---

Project Features

• Image Classification: Predicts waste categories (METAL, ORGANIC, PAPER, PLASTIC).
• Pretrained Model: MobileNetV2 pretrained on ImageNet, fine-tuned on a waste dataset.
• Interactive Web App: Built using Streamlit for easy image uploads and predictions.

---

Setup Instructions

1. Clone the Repository

Clone the project repository to your local machine:

git clone https://github.com/RohmaButt/garbage-sorting-image-classification.git
cd waste-classifier-streamlit

2. Create and Activate a Virtual Environment

Create an isolated Python environment using venv:

python3 -m venv venv
source venv/bin/activate  # For Linux/Mac
venv\Scripts\activate     # For Windows

3. Install Dependencies

Install all required Python libraries using pip:

pip install -r requirements.txt

4. Save the Model

Ensure the trained MobileNetV2 model (mobilenetv2_waste_classifier.h5) is present in the project directory.

If not, place the model file in the project root.

Run the Application To run the Streamlit app, execute the following command in your terminal:

streamlit run app.py

Once the app is running, it will provide the Local URL and Network URL:

Local URL: http://localhost:8501
Network URL: http://<your-ip-address>:8501

Open the Local URL in your browser to interact with the app.

Sample Output

Below are some demo screenshots of the Waste Classifier Web App in action:

---

1. Uploaded Image and Prediction

Screenshot 1: Uploading an image and getting the predicted waste category.

---

2. Prediction Result

Screenshot 2: The model predicts the class along with the confidence score.

---