garythung/trashnet
Dataset of images of trash; Torch-based CNN for garbage image classification
Implements a six-class waste classification CNN trained on 2,527 manually collected images using Torch with Kaiming weight initialization, achieving 75% test accuracy. Leverages CUDA-accelerated training on GPU (cutorch/cunn) with Python preprocessing (NumPy/SciPy) for image resizing, and includes the complete annotated dataset spanning glass, paper, cardboard, plastic, metal, and trash categories.
690 stars. No commits in the last 6 months.
Stars
690
Forks
204
Language
Lua
License
MIT
Category
Last pushed
Jun 02, 2023
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/garythung/trashnet"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Related frameworks
pedropro/TACO
🌮 Trash Annotations in Context Dataset Toolkit
patil215/scrapsort
A convnet classifier and hardware device to automatically sort recycling materials.
marine-debris/marine-debris.github.io
Quick Start Guide for MARIDA (Marine Debris Archive)
sumn2u/deep-waste-app
Managing waste in fun and easy way with AI ♻️😊🤖
gicait/pLitter
pLitter is a standardized, deep learning friendly dataset and pre-trained model that can be used...