Skip to content
MNIST classifier built for TensorFlow Lite - Android, iOS and other "lite" platforms
Branch: master
Clone or download
Latest commit 91e9e95 May 20, 2019
Permalink
Type Name Latest commit message Commit time
Failed to load latest commit information.
android updated MNIST model with slightly better accuracy Jan 31, 2019
notebooks Notebook version for TensorFlow 2.0 alpha Apr 23, 2019
.gitignore init commit Jan 28, 2019
README.md Update README.md May 19, 2019

README.md

MNIST-TFLite

TensorFlow 2.0 (alpha)

This respository contains Jupyter Notebook with the code running on TensorFlow 2.0 alpha. As this is not yet stable version, entire code may break in any moment. Notebook was created just for the Colaboratory environment. It requires some changes to make it working on Docker environment described in the blog post.

Open In Colab

TensorFlow 1.x

Open In Colab

Example TensorFlow Lite implementation of MNIST classifier. This project was created to show how to build the simplest Machine Learning model and use it in mobile app. For more details see:

Blog post: Mobile intelligence - TensorFlow Lite classification model in Android

Jupyter Notebook containing: model training, export and converstion to TensorFlow Lite.

Example video

MNIST classifier in Android app

You can’t perform that action at this time.