Tflite-model Maker

It uses transfer learning to reduce the amount of training data required and shorten the training time. This guide walks you through creating a custom object detector and deploying it on Android.

This tutorial shows you how to construct a TensorFlow Lite model that can be incrementally trained and improved within an installed Android app. Note: The on-device training technique can be added to existing TensorFlow Lite implementations, provided the devices you are targeting support local file storage.

TensorFlow Lite is Google’s machine learning framework to deploy machine learning models on multiple devices and surfaces such as mobile (iOS and Android), desktops and other edge devices .