Vit-base-patch16-224-in21k-finetuned-cifar10 Open-source Model

Vit Base Patch16 224 In21k Finetuned Cifar10

Developed by nielsr

This is a vision Transformer model based on Google's ViT base model, fine-tuned on the CIFAR10 dataset for image classification tasks.

Image Classification

Transformers

Open Source License:Apache-2.0 #High-precision Image Classification #ViT Fine-tuned Model #Few-shot Learning

Downloads 31

Release Time : 3/2/2022

Model Overview

This model is an image classification model based on the Vision Transformer (ViT) architecture, achieving 98.81% accuracy after fine-tuning on the CIFAR10 dataset.

Model Features

High Accuracy

Achieves 98.81% classification accuracy on the CIFAR10 test set.

Transformer-based Architecture

Uses the Vision Transformer (ViT) architecture, suitable for processing image data.

Fine-tuned Pre-trained Model

Fine-tuned based on the google/vit-base-patch16-224-in21k pre-trained model.

Model Capabilities

Image Classification

Visual Feature Extraction

Use Cases

Computer Vision

CIFAR10 Image Classification

Classify images in the CIFAR10 dataset.

Accuracy reaches 98.81%.

General Image Classification

Can be used for other image classification tasks of similar scale.

Property	Details
Model Type	Fine - tuned Vision Transformer
Training Data	image_folder
Base Model	google/vit-base-patch16-224-in21k
Metrics	Accuracy

Training Loss	Epoch	Step	Validation Loss	Accuracy
0.2455	1.0	190	0.2227	0.9830
0.1363	2.0	380	0.1357	0.9881
0.0954	3.0	570	0.1194	0.9878

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

Vit Base Patch16 224 In21k Finetuned Cifar10

Model Overview

Model Features

Model Capabilities

Use Cases

🚀 vit-base-patch16-224-in21k-finetuned-cifar10

🚀 Quick Start

📚 Documentation

Model Information

Training Procedure

Training Hyperparameters

Training Results

Framework Versions

📄 License