https://github.com/khanhlvg/digitclassifier

A end-to-end demo of how to build train a digit classifier using TensorFlow 2.0 (Keras API), then convert the model to TensorFlow Lite, and run inference on mobile apps
https://github.com/khanhlvg/digitclassifier

computer-vision keras tensorflow

Last synced: about 2 months ago
JSON representation

A end-to-end demo of how to build train a digit classifier using TensorFlow 2.0 (Keras API), then convert the model to TensorFlow Lite, and run inference on mobile apps

• Host: GitHub
• URL: https://github.com/khanhlvg/digitclassifier
• Owner: khanhlvg
• License: apache-2.0
• Created: 2019-07-02T14:08:00.000Z (about 7 years ago)
• Default Branch: master
• Last Pushed: 2019-08-09T01:02:51.000Z (almost 7 years ago)
• Last Synced: 2025-02-09T09:13:45.063Z (over 1 year ago)
• Topics: computer-vision, keras, tensorflow
• Language: Jupyter Notebook
• Homepage:
• Size: 699 KB
• Stars: 1
• Watchers: 0
• Forks: 0
• Open Issues: 0
• Metadata Files:
  • Readme: README.md
  • License: LICENSE

Awesome Lists containing this project

README

          
# Digit Classifier

This repository contains an end-to-end sample of a digit classifier model built with TensorFlow 2.0 (Keras API), and trained on MNIST dataset.

* Python Notebook showing how to train the model and convert to TensorFlow Lite format. 
[![Open In Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/khanhlvg/DigitClassifier/blob/master/notebook/mnist_tflite.ipynb)

* An [Android app](android/) that uses the TensorFlow Lite model to classify your handwritten digits.

![Screenshot](images/screenshot.png)