Swin-Tiny-Patch4-Window7-224 Open-Source Vision Model - Free for Image Classification Tasks

Swin Tiny Patch4 Window7 224 Finetuned Aiornot Baseline

Developed by Thabet

A vision model based on the Swin Transformer Tiny architecture, fine-tuned on an unknown dataset for image classification tasks

Image Classification

Transformers

Open Source License:Apache-2.0 #High-precision image classification #Small window attention mechanism #Lightweight vision model

Downloads 17

Release Time : 1/30/2023

Model Overview

This model is a fine-tuned version of microsoft/swin-tiny-patch4-window7-224, primarily used for image classification tasks, demonstrating high accuracy and F1 score on the evaluation set

Model Features

High accuracy

Achieves 91.19% accuracy and 90.86% F1 score on the evaluation set

Efficient fine-tuning

Fine-tuned based on the pre-trained Swin Transformer Tiny model, with high training efficiency

Mixed precision training

Uses native AMP for mixed precision training to improve training speed

Model Capabilities

Image classification

Feature extraction

Use Cases

Computer vision

General image classification

Can be used for tasks involving image classification

Accuracy 91.19%, F1 score 90.86%

Training Loss	Epoch	Step	Validation Loss	Accuracy	F1	Log Loss
0.2538	0.98	32	0.2327	0.9055	0.9018	3.2647
0.1735	1.98	64	0.2029	0.9151	0.9122	2.9309
0.1562	2.98	96	0.2231	0.9119	0.9086	3.0422

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

Swin Tiny Patch4 Window7 224 Finetuned Aiornot Baseline

Model Overview

Model Features

Model Capabilities

Use Cases

🚀 swin-tiny-patch4-window7-224-finetuned-aiornot-baseline

🚀 Quick Start

📚 Documentation

Model description

Intended uses & limitations

Training and evaluation data

🔧 Technical Details

Training procedure

Training hyperparameters

Training results

Framework versions

📄 License