Introduction of TENSORFLOW in Android

In this blog, We will discuss about the Basic introduction of machine learning through new Google’s Open Source library TensorFlow.

So we can start now,

“TensorFlow is a open source library of machine learning through Data Flow Graphs. The graph nodes represent mathematical operations, while the graph edges represent the multidimensional data arrays (tensors) that flow between them.” 

Initially, TensorFlow was developed by researchers and engineers working on the Google Brain team for the purposes of conducting machine learning and deep neural networks research.

Neural networks are a set of algorithms, modelled loosely after the human brain, that are designed to recognize patterns. 

Basically, Google has given us some demo app for machine learning using Tensonflow,

• • TensorFlowAndroidMNIST: This is a demo app for Android with Tensorflow to detect handwritten digits.
    https://github.com/miyosuda/TensorFlowAndroidMNIST
    
    Screen-Shots:

• TensorFlow Android Camera Demo: The demos in this folder are designed to give straightforward samples of using TensorFlow in mobile applications. This application gives the basic object recognition by Camera using the TensorFlow.
  https://github.com/tensorflow/tensorflow/tree/master/tensorflow/examples/android
  Screen-Shots:
  

  In the above screen-shot, we can see that Mobile can detect the Object. Like in first image it recognized the backpack and in the second computer mouse.

The “TF Classify” the camera Android demo app uses the Google Inception model.

This machine learning library, correct almost 80% of the time, and it has the correct classification in its top 5 choices almost 95% of the time.

We will see how to use this Tensorflow library in android for image recognition In Next Chapter. And for now stay updated and stay super.

Demo apps, 

• https://play.google.com/store/apps/details?id=org.tensorflow.app
• https://play.google.com/store/apps/details?id=org.tensorflow.detect
• https://play.google.com/store/apps/details?id=uk.tensorzoom

More Learning Resources,

• https://medium.com/@daj/creating-an-image-classifier-on-android-using-tensorflow-part-1-513d9c10fa6a