AIbase
EN
Home
Swin Tiny Patch4 Window7 224 Finetuned Og Dataset 10e Finetuned Og Dataset 10e
S

Swin Tiny Patch4 Window7 224 Finetuned Og Dataset 10e Finetuned Og Dataset 10e

Developed by Gokulapriyan
This is a vision model based on the Swin Transformer architecture, which performs excellently in image classification tasks after fine-tuning.
Image Classification
Transformers
Open Source License:Apache-2.0#High-precision image classification#Swin Transformer fine-tuning#Small window attention
Downloads 15
Release Time : 2/17/2023

Model Overview

This model is a fine-tuned version based on the Swin Transformer Tiny architecture, specifically designed for image classification tasks. It achieved an accuracy of 98.78% on the evaluation set.

Model Features

High accuracy
Achieved a classification accuracy of 98.78% on the evaluation set
Efficient inference
Can process 72 samples per second, suitable for real-time applications
Lightweight architecture
Based on the Swin Transformer Tiny variant, computationally efficient

Model Capabilities

Image classification
Feature extraction

Use Cases

Computer vision
General image classification
Classify and recognize common objects and scenes
Evaluation accuracy 98.78%
Featured Recommended AI Models
AIbase
Empowering the Future, Your AI Solution Knowledge Base
EnglishįŽ€äŊ“中文įšéĢ”中文ãĢãģんご
Š 2025AIbase