Open-source image classification model vit-base-patch16-224-finetuned - Suitable for custom image dataset classification

Vit Base Patch16 224 Finetuned

Developed by clp

An image classification model fine-tuned based on Google's Vision Transformer (ViT), trained on custom image datasets

Downloads 30

Release Time : 11/28/2022

Model Overview

This model is a fine-tuned version of google/vit-base-patch16-224 on an image folder dataset, primarily used for image classification tasks

Based on ViT Architecture

Utilizes Vision Transformer architecture, suitable for image classification tasks

Fine-tuned Model

Fine-tuned on specific image datasets to meet particular classification needs

Medium Scale

Based on ViT-base model, balancing performance and computational resource requirements

Image Classification

Visual Feature Extraction

Image Recognition

General Image Classification

Classify and recognize input images

Achieved 33.33% accuracy on the evaluation set

Training Loss	Epoch	Step	Validation Loss	Accuracy
No log	1.0	1	0.6063	0.6667
No log	2.0	2	0.6958	0.3333
No log	3.0	3	0.7617	0.3333

Property	Details
Model Type	Fine - tuned version of google/vit - base - patch16 - 224
Training Data	imagefolder
Metrics	Accuracy
Results	Loss: 0.7617, Accuracy: 0.3333

Featured Recommended AI Models

Empowering the Future, Your AI Solution Knowledge Base