Deep Learning > TensorFlow Lite
Framework that optimizes TensorFlow models for on-device machine learning.
Contents
Past announcements:
Makes mobile development easier (Android sample code).
How to use the Hexagon Delegate to speed up model inference on mobile and edge devices. Also see blog post Accelerating TensorFlow Lite on Qualcomm Hexagon DSPs.
On-device training
Models with samples
Computer vision
| tutorial 1 | tutorial 2
| Blog post | Model card
| Realtime | Paper
| Paper
| Tutorial
| Overview | Android | Flutter
| Tutorial
| Tutorial
| Tutorial
| Tutorial
Computer vision / Detection
Computer vision / Generative
Post estimation
Other
Speech
Plugins and SDKs
A cross platform (mobile, desktop and Edge TPUs) AI pipeline by Google AI. (PM Ming Yong) | MediaPipe examples.
Provides a dart API similar to the TensorFlow Lite Java API for accessing TensorFlow Lite interpreter and performing inference in flutter apps. tflite_flutter on pub.dev.
Model zoo
ML Kit examples
Helpful links
A tool for visualizing models.
A repository showing non-trivial conversion processes and general explorations in TensorFlow Lite.
An Android-based app to profile TensorFlow Lite models and measure its performance on smartphone.
A repository refactors and rewrites all the TensorFlow Lite Android examples which are included in the TensorFlow official website.
A collection of Tensorflow Lite Android example Apps in Kotlin, to show different kinds of kotlin implementation of the example apps