Projects

A collection of projects I’ve built to learn and experiment with deep learning, computer vision, and efficient ML.

Vision Transformers

ViT

Transformers

PyTorch

From attention mechanisms to ViT, DETR, and SegFormer — implemented from scratch in PyTorch.

Computational Photography with Halide

Computational Photography

Halide

C++

Implementation of image processing pipelines and computational photography algorithms using the Halide domain-specific language.

Integrating ncnn with Apache TVM

ML Compilation

Edge AI

C++

Integrated Tencent’s ncnn inference engine into Apache TVM via BYOC, achieving 30% speedup over Arm Compute Library on Raspberry Pi 4B.

Iris Landmark Localization

Computer Vision

PyTorch

Landmark Detection

Edge AI

ncnn

Dense iris landmark regression trained on synthesized eye images — end-to-end from synthetic data generation to real-world inference.