YAML Metadata Warning:empty or missing yaml metadata in repo card
Check out the documentation for more information.
🗑️ Waste Classification Model
📌 Overview
This repository contains a deep learning-based image classification model designed for waste segregation.
The system identifies whether waste is biodegradable or non-biodegradable, and further classifies it into specific categories such as plastic, metal, paper, cardboard, organic waste, glass types, clothes, shoes, batteries, and trash.
Beyond classification, the model can also provide suggestions for reuse, recycling, and appropriate disposal methods, supporting sustainable waste management practices.
📊 Dataset
The model is trained on the Garbage Classification Dataset, which consists of 15,150 images across 12 classes:
- 📰 Paper
- 📦 Cardboard
- 🌱 Biological (Organic waste)
- 🥤 Plastic
- 🥫 Metal
- 🍾 Green glass
- 🍶 Brown glass
- 🧴 White glass
- 👕 Clothes
- 👟 Shoes
- 🔋 Batteries
- 🗑️ Trash
🧠 Model
- Framework: TensorFlow / Keras
- Base architecture: EfficientNetB0 (transfer learning)
- Optimized for: Lightweight deployment (web & mobile-friendly)
- Output:
- Binary classification → Biodegradable / Non-biodegradable
- Multiclass classification → Specific waste category
🚀 Use Cases
- Smart bins: Automatically sort waste into appropriate compartments.
- Mobile apps: Help users identify how to dispose of items.
- Recycling facilities: Speed up manual waste segregation.
- Educational tools: Raise awareness about proper waste disposal.
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support