Skip to content

Latest commit

 

History

History
19 lines (11 loc) · 710 Bytes

README.md

File metadata and controls

19 lines (11 loc) · 710 Bytes
Raw

Tensorflow digit classification

RealTime Digit Recognition model built with Tensorflow and OpenCV in python to recognize 
                           digits written in canvas.

goal : Serving MNIST digit classification model to website through Tensorflow.js

link : https://nagaraj-u.github.io/Tensorflow-Quizzler/

This Project has following stages:

  1. Training MNSIT dataset to classify handwritten digits using Tensorflow using Multi layer perceptron.
  2. Saving and loading trained model.
  3. converting Tensorflow model to Tensorflow.js model to serve through website.
  4. Using OpenCv to preprocess the digits written in CANVAS and convert them to Tensors.
  5. Serving model through website.