Open-source Image Multi-class Classification Models - Efficient and Accurate Identification of Image Categories

Image Multi Class Classification

Developed by autoevaluate

This model is an image classification model fine-tuned on the MNIST dataset based on the Swin Transformer architecture, achieving an accuracy of 98.33%

Image Classification

Transformers

Open Source License:Apache-2.0 #MNIST High Accuracy #Swin Fine-tuning #Lightweight Classification

Downloads 69

Release Time : 6/21/2022

Model Overview

An image classification model for handwritten digit recognition, fine-tuned on the MNIST dataset using the Swin-Tiny architecture

Model Features

High Accuracy

Achieves 98.33% accuracy on the MNIST test set

Based on Swin Transformer

Utilizes the advanced vision Transformer architecture

Lightweight Model

Adopts the Tiny version architecture, suitable for resource-limited environments

Model Capabilities

Handwritten Digit Recognition

Image Classification

Use Cases

Education

Handwritten Digit Recognition System

Used for automatically recognizing students' handwritten digit assignments

Recognition accuracy of 98.33%

Finance

Check Digit Recognition

Automatically recognizes handwritten amount digits on checks

Property	Details
Model Type	Image Classification
Training Data	mnist, autoevaluate/mnist - sample
Metrics	accuracy

Task	Dataset	Metric	Value
Image Classification	mnist	Accuracy	0.9833333333333333

Training Loss	Epoch	Step	Validation Loss	Accuracy
0.3743	1.0	422	0.0556	0.9833

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

Image Multi Class Classification

Model Overview

Model Features

Model Capabilities

Use Cases

🚀 Image Classification

🚀 Quick Start

📚 Documentation

Model Information

Model Performance

Training Procedure

Training Hyperparameters

Training Results

Framework Versions

📄 License