V

Vc Bantai Vit Withoutambi Adunest V3

Developed by AykeeSalazar
An image classification model based on Google Vision Transformer (ViT) architecture, fine-tuned on a custom dataset with an accuracy of 82.18%
Downloads 30
Release Time : 8/3/2022

Model Overview

This model is a fine-tuned version of the google/vit-base-patch16-224-in21k pre-trained model for image classification tasks, primarily used for image classification.

Model Features

High Accuracy
Achieves an accuracy of 82.18% on the evaluation set, demonstrating excellent performance
Based on ViT Architecture
Utilizes the Vision Transformer architecture, effectively capturing global features in images
Fine-tuned Optimization
Trained for 200 epochs using linear learning rate scheduling and the Adam optimizer

Model Capabilities

Image Classification
Visual Feature Extraction

Use Cases

Image Recognition
Violation Content Classification
Can be used to identify and classify images with prohibited content
Performs well on the Violation-Classification dataset
Featured Recommended AI Models
AIbase
Empowering the Future, Your AI Solution Knowledge Base
Š 2025AIbase