AIbase
EN
Home
Deit Tiny Patch16 224 Finetuned Og Dataset 10e
D

Deit Tiny Patch16 224 Finetuned Og Dataset 10e

Developed by Gokulapriyan
A lightweight image classification model based on the DeiT-tiny architecture, achieving 94.8% accuracy after fine-tuning on a custom image dataset
Image Classification
Transformers
Open Source License:Apache-2.0#High-precision image classification#Lightweight ViT model#Transfer learning optimization
Downloads 17
Release Time : 2/21/2023

Model Overview

This model is an image classifier fine-tuned from Facebook's DeiT-tiny model, suitable for general image classification tasks

Model Features

Efficient and Lightweight
Based on the DeiT-tiny architecture, it has a small number of parameters while maintaining high accuracy
Fast Fine-tuning
Achieves 94.8% validation accuracy with just 6 training epochs
Transfer Learning Friendly
Fine-tuned from a pre-trained model, suitable for small-scale datasets

Model Capabilities

Image classification
Transfer learning
Computer vision tasks

Use Cases

General Image Recognition
Object Classification
Classify and recognize common objects
Validation set accuracy of 94.8%
Educational Applications
Teaching Demonstration
Showcase the capabilities of lightweight vision models
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