← Haadhi Irfan

Deep Learning From Scratch: Vision & Multimodal

Self projects · 2021 – 2022

Prototype

EfficientNet-B0

Real coefficients and ImageNet results from the EfficientNet paper (Tan & Le, 2019) — the same compound scaling rule re-implemented from scratch in PyTorch. Each column is one of B0's seven MBConv stages: depth scaling stacks more blocks, width scaling fattens their channels, resolution scaling grows the input.

Image Caption Generator via Transformers (Sept 2022)

EfficientNet Core Re-implementation (June 2022)

Automated Vacuum Robotics (Jan 2021)

Technologies