Skip to content

teodoraspasojevic/Light-Vision-Transformer

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

4 Commits
 
 
 
 
 
 
 
 

Repository files navigation

Light Vision Transformer (LightViT)

Welcome to the Light Vision Transformer (LightViT) repository! This project contains an implementation of the Light Vision Transformer from scratch, optimized for efficient image recognition tasks on devices with limited computational resources.

Overview

Light Vision Transformer (LightViT) is a streamlined and efficient adaptation of the Vision Transformer (ViT) architecture. It is designed to deliver high performance with reduced computational overhead, making it ideal for deployment on mobile and embedded systems.

Features

Lightweight Architecture: Optimized for minimal parameter count and reduced computational complexity. Efficient Attention Mechanisms: Implements optimized attention mechanisms to maintain high performance while reducing overhead. Flexible and Modular Codebase: Easy to customize and extend for various image recognition tasks.

Repository Contents

vision_transformer.py: The core implementation of the Light Vision Transformer model. vision_transformer_colab.ipynb: A Jupyter notebook for training the LightViT model on Google Colab.

About

No description, website, or topics provided.

Resources

License

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published