Skip to content

Latest commit

 

History

History
39 lines (24 loc) · 1.98 KB

README.md

File metadata and controls

39 lines (24 loc) · 1.98 KB

Digit Classifier Extension 🔢

Description

A fun chrome extension that identifies the digits you draw.🤔

This project integrates the power of chrome extensions and serverless deployment to successfully classify the digits you draw. The ML model is run in the browser itself by converting it into ONNX format and loading the same in the extension using ONNX.js. This allows the extension to run without internet access while giving it faster inference time.

Features

Check out the README.md files inside the folders for additional info!🤓

  • Real time analysis: Extension actively modifies the output based on what you draw.
  • Probability display: Each number has a dynamic prediction column that shows the probability of the digit drawn being that specific number.
  • Machine Learning Integration: Using ONNX.js and Pytorch's MNIST model.

Benefits of running a model in the browser

A viable method for smaller models!😯

  • Faster inference times.
  • Easy to host and support (only static files).
  • Offline support.
  • Enhanced user privacy, as data is kept on the device.

Visuals

Demo of the project via images.🖼️

image image image image image