Welcome to my central hub of deep learning explorations and hands-on projects. This repository links together my work across various subfields of deep learning — from foundational models in PyTorch to FastAI experiments and computer vision applications. This is also the repo for my computer vision blog series on LinkedIn.
This repo is organized into key areas of focus. Each sub-repo explores deep learning techniques, coursework and applications with curated code, insights, and tutorials.
End-to-end CV projects with a storytelling angle and real-world relevance:
- MNIST Digit Recognition
- YOLO
- Semantic Segmentation
- Panoptic Segmentation
- Vision Transformer and Diffusion
A series of beginner-to-intermediate projects covering core deep learning concepts:
- Building neural networks from scratch
- Custom training loops
- Loss functions and optimizers
- Hands-on with MNIST, CIFAR, and more
Projects based on the brilliant FastAI course/book:
- Currently includes:
- Image classification on Pet Dataset
- Fine-tuned ResNet models on curated datasets
This hub documents my learning journey as I transition toward applied AI/ML research, with a strong focus on:
- 3D AI & Perception
- Vision-based Robotics
- Generative Models for Visual Understanding
My goal is to build impactful, deployable tools that merge creativity with deep technical understanding.
- 🔁 Regular project updates (new CV tasks, multimodal fusion, 3D scene understanding)
- 📝 Blog-style writeups for every major milestone
- 🎓 Open-source contributions to useful datasets + tools
If you’re working on computer vision, spatial AI, or anything 3D — let’s connect!
"Learning to see the world — pixel by pixel, point by point, layer by layer."
📂 Happy coding & exploring!