Multi-Class Waste Image Classification Dataset

Overview

This dataset is curated for multi-class waste classification using computer vision and deep learning techniques. It provides a structured, high-quality benchmark for training custom CNN architectures, benchmarking transfer learning models, and building automated waste sorting pipelines.

Dataset Structure

The dataset follows a standard directory format compatible with common deep learning frameworks (torchvision.datasets.ImageFolder, tf.keras.utils.image_dataset_from_directory):

dataset/
├── Plastic waste/
├── Paper and cardboard waste/
├── Glass waste/
├── Metal waste/
├── Organic waste/
├── Electronic waste/
├── Medicinal waste/
├── Hazardous waste/
└── General Waste/