vit-base-patch16-224-in21k-iiii Open-source Image Classification Model

Vit Base Patch16 224 In21k Iiii

Developed by Imene

This model is a fine-tuned Vision Transformer based on google/vit-base-patch16-224-in21k, primarily used for image classification tasks.

Image Classification

Transformers

Open Source License:Apache-2.0 #Vision Transformer #Transfer Learning #Image Classification

Downloads 21

Release Time : 9/2/2022

Model Overview

This is an image classification model based on the Vision Transformer architecture, fine-tuned on specific datasets for image recognition and classification tasks.

Model Features

ViT-based Architecture

Utilizes the Vision Transformer architecture with self-attention mechanisms for image data processing

Transfer Learning

Fine-tuned from the pre-trained vit-base-patch16-224-in21k model

Mixed Precision Training

Trained with mixed_float16 precision for improved training efficiency

Model Capabilities

Image Classification

Feature Extraction

Use Cases

Computer Vision

General Image Classification

Classify and recognize input images

Achieves 39.07% accuracy on the validation set

Train Loss	Train Accuracy	Train Top - 3 - accuracy	Validation Loss	Validation Accuracy	Validation Top - 3 - accuracy	Epoch
3.8068	0.0843	0.2108	3.6116	0.1721	0.3593	0
3.4497	0.2735	0.4840	3.3654	0.2779	0.4953	1
3.1913	0.3991	0.6314	3.1839	0.3512	0.5977	2
3.0017	0.4878	0.7311	3.0867	0.3872	0.6233	3
2.8947	0.5439	0.7916	3.0482	0.3907	0.6302	4

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 Iiii

Model Overview

Model Features

Model Capabilities

Use Cases

🚀 Imene/vit-base-patch16-224-in21k-iiii

🚀 Quick Start

📚 Documentation

Model description

Intended uses & limitations

Training and evaluation data

Training procedure

Training hyperparameters

Training results

Framework versions

📄 License