Ecosyste.ms: Awesome
An open API service indexing awesome lists of open source software.
https://github.com/arpanpramanik2003/smart-waste-classification
This project utilizes MobileNet and the TrashNet dataset to classify waste into different categories and provide recycling suggestions. Built with TensorFlow and Streamlit, it allows users to upload an image of trash and get instant classification results along with eco-friendly disposal recommendations.
https://github.com/arpanpramanik2003/smart-waste-classification
cnn-classification deep-learning image-classification image-processing imshow keras mobilenetv2 smart-waste streamlit-webapp tensorflow2 transfer-learning trashnet
Last synced: 10 days ago
JSON representation
This project utilizes MobileNet and the TrashNet dataset to classify waste into different categories and provide recycling suggestions. Built with TensorFlow and Streamlit, it allows users to upload an image of trash and get instant classification results along with eco-friendly disposal recommendations.
- Host: GitHub
- URL: https://github.com/arpanpramanik2003/smart-waste-classification
- Owner: arpanpramanik2003
- License: apache-2.0
- Created: 2025-02-01T14:05:09.000Z (10 days ago)
- Default Branch: master
- Last Pushed: 2025-02-01T14:51:51.000Z (10 days ago)
- Last Synced: 2025-02-01T15:37:22.065Z (10 days ago)
- Topics: cnn-classification, deep-learning, image-classification, image-processing, imshow, keras, mobilenetv2, smart-waste, streamlit-webapp, tensorflow2, transfer-learning, trashnet
- Language: Jupyter Notebook
- Homepage: https://smart-waste-classification-arpan.streamlit.app/
- Size: 60.1 MB
- Stars: 0
- Watchers: 1
- Forks: 0
- Open Issues: 0
-
Metadata Files:
- Readme: README.md
- License: LICENSE
Awesome Lists containing this project
README
# Smart Waste Classification & Recycling Suggestion System
## Overview
This project implements a deep learning model using MobileNet for smart waste classification. It categorizes waste into different classes using the TrashNet dataset and provides recycling suggestions to promote sustainable waste management.
## Features
- **Real-time Image Classification:** Upload an image, and the model predicts the waste category.
- **Recycling Suggestions:** Get recommendations on how to dispose of or recycle the classified waste.
- **Streamlit Web Application:** A user-friendly interface for easy interaction.
## Dataset
- **Source:** TrashNet Dataset
- **Classes:** Plastic, Metal, Glass, Paper, Cardboard, and Organic Waste
- **Preprocessing:** Image resizing, normalization, and augmentation for better model generalization.
## Model Architecture
- **Base Model:** MobileNet (Pretrained on ImageNet)
- **Fine-tuning:** Last few layers trained on the TrashNet dataset
- **Optimizer:** Adam
- **Loss Function:** Categorical Cross-Entropy
- **Metrics:** Accuracy
## Installation
1. Clone the repository:
```bash
git clone https://github.com/arpanpramanik2003/smart-waste-classification.git
cd smart-waste-classification
```
2. Install dependencies:
```bash
pip install -r requirements.txt
```
3. Run the Streamlit app:
```bash
streamlit run trashnetST.py
```
## Usage
1. Open the Streamlit web app.
2. Upload an image of waste.
3. View the predicted category and recycling suggestions.
## Customization
- **Image Size Adjustment:** Ensures that uploaded images appear correctly in the app.
- **Expanded Recycling Information:** Provides more details on how to recycle different waste types.
## Results
- **Training Accuracy:** ~92%
- **Validation Accuracy:** ~88%
- **Loss:** Optimized for minimal classification error
## Deployment
- The model can be deployed on platforms like Render, AWS, or Hugging Face Spaces for online access.
## Contributing
Feel free to open issues and contribute to improving the project.
## License
Apache-2.0 Licence
## Author
**Arpan Pramanik**
For any queries, reach out via GitHub or LinkedIn.