vit-base-patch16-224-in21k-finetuned-cifar10 Open-source Image Classification Model

Vit Base Patch16 224 In21k Finetuned Cifar10

Developed by karthiksv

This model is a fine-tuned version of Google's ViT-base model on the CIFAR-10 dataset, suitable for image classification tasks.

Downloads 14

Release Time : 5/13/2022

Model Overview

This is an image classification model based on the Vision Transformer (ViT) architecture, specifically fine-tuned for the CIFAR-10 dataset.

Based on ViT architecture

Utilizes the Vision Transformer architecture, employing self-attention mechanisms to process image data.

Fine-tuned on CIFAR-10

Specifically optimized for the CIFAR-10 dataset, suitable for 10-class image classification tasks.

Fine-tuned pre-trained model

Fine-tuned based on the ViT model pre-trained on ImageNet-21k, featuring strong feature extraction capabilities.

Image classification

Feature extraction

Computer vision

CIFAR-10 image classification

Classifies images into 10 categories from the CIFAR-10 dataset

Featured Recommended AI Models

Empowering the Future, Your AI Solution Knowledge Base