trashnet
Trash Classifier
A Torch-based deep learning framework for image classification of trash
Dataset of images of trash; Torch-based CNN for garbage image classification
582 stars
28 watching
181 forks
Language: Lua
last commit: almost 2 years ago
Linked from 2 awesome lists
convolutional-neural-networksdatasetdeep-learninggarbageimage-classificationtorchtrash
Related projects:
Repository | Description | Stars |
---|---|---|
| Develops an attention-based trash classification model using transfer learning and feature learning with attention module for effective waste management. | 39 |
| A Lua-based implementation of a multi-GPU training framework for image classification using the Alexnet model. | 4 |
| Provides a toolkit for object detection in images of waste, including annotations and a demo application. | 603 |
| AI system for detecting plastic waste in environment | 185 |
| A PyTorch project for comparing image classification models and facilitating quick experiment setup | 366 |
| A Torch implementation of a novel neural network architecture designed to improve the generalization ability of deep image classification models. | 129 |
| A toolkit for training and deploying a state-of-the-art image classification architecture on TensorFlow | 136 |
| Provides a basic framework for training deep learning models on image classification tasks using PyTorch | 187 |
| An image classification model using a third-generation deep residual network. | 27 |
| An implementation of PNASNet-5 architecture in TensorFlow for image classification on ImageNet. | 102 |
| Implementing a deep learning framework for image classification using Residual Attention Network architecture | 682 |
| A collection of Torch implementations for training various types of Generative Adversarial Networks (GANs) | 55 |
| An OverFeat image classifier and feature extractor wrapper around Torch7 | 44 |
| A Python-based deep learning model for breast cancer classification from mammography images | 849 |
| Torch7 tutorials and demos providing hands-on experience with the deep learning framework. | 355 |