🧠 Vision DL Architectures 🖼️

Welcome! 🚀 This repo is part of my journey to dive deep into Deep Learning (DL) for computer vision. It’s a personal project to document my learning journey to implement DL architectures from scratch. I’ll update it as I progress.

---

📚 About

This repository is a work in progress, where I:

• Explore and implement classic and SOTA DL architectures.
• Focus on understanding the inner workings of these models.
• Document my learning process and practical use cases.

---

🌟 Features

• Implemented Architectures:

  • CNNs: ResNet, VGG, etc.
  • Transformers: ViTs and variants.
  • Lightweight models: MobileNet, EfficientNet.
  • New approaches: Swin Transformers, ConvNeXt.

• Flexible Training Framework:

  • Pipelines for training and evaluation.

---

🚀 Getting Started

Installation

1. Clone the repository:

   git clone https://github.com/AhmedNasr7/vision-models
   cd vision-models

2. Install dependencies

   pip install -r requirements.txt

This repo is for personal reference and growth. Feel free to explore or adapt it for your own learning!