Trashbot_v1 Open-Source Image Segmentation Model - Free Deployment for Accurate Identification of Various Types of Garbage

Home

Trashbot V1

Developed by mraottth

An image segmentation model fine-tuned based on nvidia/mit-b5 for garbage recognition tasks

Image Segmentation

Transformers

Open Source License:Other #Garbage Image Segmentation #Environmental Monitoring #High-Precision Classification

Downloads 16

Release Time : 1/30/2023

Model Overview

This model is a visual image segmentation model specifically designed for garbage recognition tasks. It is fine-tuned on the mraottth/all_locations_pooled dataset based on the nvidia/mit-b5 architecture and can accurately identify garbage areas in images.

Model Features

High-Precision Garbage Recognition

Achieves a garbage category accuracy and IoU of 0.7995 on the evaluation set

Lightweight Model

Based on the mit-b5 architecture, it maintains relatively high performance while being lightweight

End-to-End Training

Adopts a complete end-to-end training process to optimize segmentation results

Model Capabilities

Image Segmentation

Garbage Area Recognition

Pixel-Level Classification

Use Cases

Environmental Technology

Smart Waste Sorting

Used in smart trash bins or waste sorting stations for garbage recognition systems

Accurately identifies garbage categories to assist in waste sorting

Environmental Monitoring

Monitors garbage distribution in public areas

Provides garbage distribution heatmaps to assist in environmental management

Smart City

Street Cleaning Management

Identifies garbage accumulation on streets

Optimizes cleaning routes and resource allocation

🚀 trashbot

Trashbot is a fine - tuned model based on nvidia/mit-b5 on the mraottth/all_locations_pooled dataset. It offers high - performance in image segmentation tasks, achieving excellent results on the evaluation set.

🚀 Quick Start

This model is a fine - tuned version of nvidia/mit-b5 on the mraottth/all_locations_pooled dataset. It achieves the following results on the evaluation set:

Loss: 0.0191
Mean Iou: 0.3997
Mean Accuracy: 0.7995
Overall Accuracy: 0.7995
Accuracy Unlabeled: nan
Accuracy Trash: 0.7995
Iou Unlabeled: 0.0
Iou Trash: 0.7995

📚 Documentation

Model description

More information needed

Intended uses & limitations

More information needed

Training and evaluation data

More information needed

Training procedure

Training hyperparameters

The following hyperparameters were used during training:

learning_rate: 6e - 05
train_batch_size: 3
eval_batch_size: 3
seed: 42
optimizer: Adam with betas=(0.9,0.999) and epsilon = 1e - 08
lr_scheduler_type: linear
num_epochs: 10

Training results

Training Loss	Epoch	Step	Validation Loss	Mean Iou	Mean Accuracy	Overall Accuracy	Accuracy Unlabeled	Accuracy Trash	Iou Trash
0.0748	1.0	90	0.0386	0.3630	0.7259	0.7259	nan	0.7259	0.7259
0.039	2.0	180	0.0242	0.3803	0.7607	0.7607	nan	0.7607	0.7607
0.0194	3.0	270	0.0242	0.3605	0.7210	0.7210	nan	0.7210	0.7210
0.0112	4.0	360	0.0205	0.3995	0.7991	0.7991	nan	0.7991	0.7991
0.0169	5.0	450	0.0192	0.4000	0.8000	0.8000	nan	0.8000	0.8000
0.041	6.0	540	0.0196	0.3838	0.7677	0.7677	nan	0.7677	0.7677
0.0188	7.0	630	0.0191	0.4139	0.8277	0.8277	nan	0.8277	0.8277
0.0073	8.0	720	0.0190	0.4069	0.8138	0.8138	nan	0.8138	0.8138
0.025	9.0	810	0.0191	0.4087	0.8174	0.8174	nan	0.8174	0.8174
0.006	10.0	900	0.0191	0.3997	0.7995	0.7995	nan	0.7995	0.7995

Framework versions

Transformers 4.26.0
Pytorch 1.13.1+cu116
Datasets 2.9.0
Tokenizers 0.13.2

📄 License

other

Property	Details
Model Type	Fine - tuned version of nvidia/mit-b5
Training Data	mraottth/all_locations_pooled dataset

Featured Recommended AI Models

Empowering the Future, Your AI Solution Knowledge Base

English 简体中文繁體中文にほんご