Attentional Learning of Trash Classification
-
Updated
Jan 4, 2021 - Python
Attentional Learning of Trash Classification
Deep Learning based Waste Segregation Project to classify waste images into different classes.
Classification of trash images using Convolutional Neural nets
WasteAI: Snap, Sort, Succeed || Waste Segregation
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.
Waste AI: Snap, Sort, Succeed || Waste Segregation
Waste image classification using CNN (MobileNetV2 & DenseNet121) on the TrashNet dataset with augmentation and class weighting.
The cleaned Trashnet dataset has been annotated using Pascal VOC standard for object detection
A CNN benchmark on TrashNet, six waste classes over 2,527 images. ResNet50, EfficientNet-B0 and MobileNetV2 compared under an imbalance-aware pipeline, fused into a soft-voting ensemble, explained with Grad-CAM.
AIUB Computer Vision and Pattern Recognition projects covering custom CNN classification, Grad-CAM, patch-based industrial defect localization, and model efficiency analysis.
YOLO11 waste detection -- six-class detector (plastic, paper, cardboard, metal, glass, organic) fine-tuned on public datasets only, with open-set 'rest' rejection and ONNX/TensorRT export
TrashNet waste classification refactored out of a notebook into a modular, config-driven, tested Python package. MobileNetV2 transfer learning at 90.3% validation accuracy against a 54.5% from-scratch baseline, with Grad-CAM, balanced class weights, a FastAPI inference service, and CI.
Add a description, image, and links to the trashnet topic page so that developers can more easily learn about it.
To associate your repository with the trashnet topic, visit your repo's landing page and select "manage topics."