Vision Transformers (ViTs) Blog

This repository contains a blog article titled "CNNs look, ViTs pay Attention"

Contents

• blog.md: A detailed blog post on Vision Transformers.
• images/: Folder containing images referenced in the blog.

Blog Overview

The blog discusses Vision Transformers (ViTs) and how they are used in computer vision tasks. It compares ViTs with traditional CNNs, explores their advantages, and covers real-world applications.

Images

The images/ folder contains the following images:

1. vit.png: Vision Transformer architecture.
2. transformer.png: Working of transformer in NLP task.
3. attention.png: Self-attention mechanism in ViTs.

Installation

To view the blog locally:

1. Clone the repository:

   git clone https://github.com/manyagupta13/ViT-Blog.git