Categories: NewsTech

TensorFlow Lite machine learning integrates into Android to improve application size and performance

More and more applications make up the machine learning on the device itself to offer a lower latency in predictions, a more efficient use of the battery and above all not to depend on a network connection, but this also entails some problems that now Google wants to solve.

Google has found that developers who implement machine learning in their applications run into application size limitations, performance differences, and limitations in the latest advances in machine learning. To solve these three problems Google will integrate TensorFlow Lite machine learning into Android.


{“videoId”: “x81e3ql”, “autoplay”: true, “title”: “ANDROID 12: BETA PRINTS AND HOW TO INSTALL IT”}

TensorFlow Lite for Android

Currently most of the applications that make use of machine learning integrate the library TensorFlow Lite in its APK by increasing the size of the application, with which Google has decided integrate TensorFlow Lite directly into Google Play Services.

TensorFlow Lite integration on all compatible mobiles prevents applications from having to integrate that library, thereby slightly reduces the size of applications, but it also brings two other important novelties.

This integration will also allow Google improve optimal performance on all the devices in your library. On some devices, machine learning may enable the hardware acceleration when available for some AI tasks to run in less time.

By integrating TensorFlow Lite API into Google Play Services you will receive regular updates on all versions of Android 4.4 or higher, thus covering practically all active devices on the market. In addition, Google is also working with chip vendors to update hardware drivers through Google Play, Qualcomm being the first partner.

The integration of TensorFlow Lite in the Google Play Services will come to Android by the end of the year. Starting today developers can point to preview

to test the machine learning machine integration on Android.

Via | Android Developers


The news

TensorFlow Lite machine learning integrates into Android to improve application size and performance

was originally published in

Engadget Android

for
Cosmos

.

Me Time Tech

Recent Posts

The Rise of Spatial Computing: Evolution of Human-Computer Interaction

The Rise of Spatial Computing: Evolution of Human-Computer Interaction

2 months ago

Top 10 Benefits of AWS

Top 10 Benefits of AWS

3 months ago

Data Loss on Windows? Here’s How Windows Recovery Software Can Help

Data Loss on Windows? Here's How Windows Recovery Software Can Help

7 months ago

Integrating Widgets Seamlessly: Tips for Smooth Implementation and Functionality

Integrating Widgets Seamlessly: Tips for Smooth Implementation and Functionality

8 months ago

6 Tips to Reach Parents About Your School Sports Day Event

School sports days are a fun event for all students, but it’s important that the…

9 months ago

9 Reasons for Developing Your Own Mortgage App

9 Reasons for Developing Your Own Mortgage App

11 months ago