AIbase
EN
Home
Swin Base Patch4 Window7 224 In22k Finetuned Cifar10
S

Swin Base Patch4 Window7 224 In22k Finetuned Cifar10

Developed by Weili
This model is an image classification model based on the Swin Transformer architecture, achieving 98.9% accuracy after fine-tuning on the CIFAR-10 dataset.
Image Classification
Transformers
Open Source License:Apache-2.0#High-precision image classification#Swin-Transformer architecture#CIFAR10 fine-tuning
Downloads 19
Release Time : 12/7/2022

Model Overview

This is a Swin Transformer model fine-tuned on the CIFAR-10 dataset, primarily used for image classification tasks.

Model Features

High accuracy
Achieves 98.9% classification accuracy on the CIFAR-10 test set.
Based on Swin Transformer
Utilizes the advanced Swin Transformer architecture with powerful feature extraction capabilities.
Transfer learning
Fine-tuned on the ImageNet-22k pre-trained model, effectively improving performance.

Model Capabilities

Image classification
Feature extraction

Use Cases

Computer vision
CIFAR-10 image classification
Classifies images from the 10 categories in the CIFAR-10 dataset.
98.9% test accuracy
General image classification
Can be transferred to other image classification tasks of similar scale.
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