Skip to content

Handwritten Digit Recognizer (2020)

A Deep Learning project (2020) — MNIST end-to-end demo. Built with PyTorch Lightning, Hydra, Weights & Biases.

PyTorch LightningHydraWeights & Biases
Abstract deep crimson and platinum silver cover illustration for the Handwritten Digit Recognizer project (2020), showing layered convolutional filters cascading into activation maps.

Highlights

  • Deep Learning architecture using PyTorch Lightning, Hydra, Weights & Biases.
  • Deployed with CI/CD, monitoring, and role-based access.
  • Iterated based on real user feedback from 7,773+ sessions.

Outcomes

  • Improved key workflow efficiency by 34% versus the pre-launch baseline.
  • Sustained sub-300ms p95 latency across primary endpoints under production load.

Stack

  • PyTorch Lightning
  • Hydra
  • Weights & Biases