🧠 "Computer Vision is how machines see — let's teach them better."
This book is a curated collection of short-form, high-impact tutorials that cover everything from image fundamentals to generative AI, designed for learners who prefer:
- 🔍 Clear visuals
- 🧪 Hands-on code
- 🚀 Fast, practical insights
Whether you're a beginner exploring pixel arrays, or an AI engineer diving into transformers and CLIP, this is for you.
Let's Dive in
💡 Each tutorial is designed to answer one question well.
| 🧩 Topic | 🔧 Core Skills |
|---|---|
| Image Basics | RGB, grayscale, histograms, pixel ops |
| Filters & Features | Edge detection, blurring, thresholding |
| Deep Learning in CV | CNNs, segmentation, detection |
| Vision Transformers | ViT, DETR, object queries |
| Multimodal Models | CLIP, BLIP, OWL-ViT |
| Generative AI in Vision | Diffusion, inpainting, stable pipelines |
| Datasets & Pipelines | Loading, preprocessing, augmentation |
- Explore: Use the sidebar or keyboard navigation.
- Run: Every code block is executable via Jupyter Notebook.
- Apply: Use the mini challenges at the end of tutorials.
- Contribute: Help grow the book by adding your own chapters!
👉 Click here to start with the first lesson →
A 5-minute intro to images, pixels, and what a computer “sees.”
- 🧪 Jupyter Book
- 📷 OpenCV
- 📈 Matplotlib
- 🔗 GitHub Actions
📬 Stay connected: @shravankumar147
🔗 https://shravan147.github.io/GenAI-lab-tutorials/cv-tutorials/