Skip to content

This Xamarin.Forms sample demonstrates how to take a model (of coin images) exported from the Custom Vision Service in the TensorFlow format and add it to an application for real-time image classification (determine if it's a coin or not)

zayenCh/Coin-or-Not-TensorFlow-Xamarin-real-time-image-classification

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

3 Commits
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

Coin-or-Not: Xamarin mobile app sample using real time image classification with TensorFlow for Android

This sample uses the Azure Custom Vision service in order to recognize if an image represents a coin or not. the Azure Custom Vision service creates models that can be exported as Tensorflow (Android) models to do image classification.

This sample is made after uploading a set of images then add tags on each image so the Azure Custom Vision service training can be made. The next step is to download and use these models offline from inside a mobile app, using Tensorflow on Android with Xamarin.Forms

Main steps:

Uploading images to the Azure Custom Vision service, adding tags then start the training

Export then the Tensorflow models

in the app, if you take a picture of select one from the gallery, you'll get a prediction according to the training , the picture then is displayed with the tags name and its probability

About

This Xamarin.Forms sample demonstrates how to take a model (of coin images) exported from the Custom Vision Service in the TensorFlow format and add it to an application for real-time image classification (determine if it's a coin or not)

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published