Deploy machine learning models on mobile and IoT devices

TensorFlow Lite is an open source deep learning framework for on-device inference.

See the guide

Guides explain the concepts and components of TensorFlow Lite.

See examples

Explore TensorFlow Lite Android and iOS apps.

See tutorials

Learn how to use TensorFlow Lite for common use cases.

How it works

Pick a model

Pick a new model or retrain an existing one.

Convert

Convert a TensorFlow model into a compressed flat buffer with the TensorFlow Lite Converter.

Deploy

Take the compressed .tflite file and load it into a mobile or embedded device.

Optimize

Quantize by converting 32-bit floats to more efficient 8-bit integers or run on GPU.

Solutions to common problems

Explore optimized TF Lite models and on-device ML solutions for mobile and edge use cases.

Image classification

Identify hundreds of objects, including people, activities, animals, plants, and places.

Object detection

Detect multiple objects with bounding boxes. Yes, dogs and cats too.

Question answering

Use a state-of-the-art natural language model to answer questions based on the content of a given passage of text with BERT.

News & announcements

Check out our blog for additional updates, and subscribe to our monthly TensorFlow newsletter to get the latest announcements sent directly to your inbox.

August 18, 2021  
Pose estimation and classification on edge devices with MoveNet

MoveNet is the state-of-the-art pose estimation model for mobile devices which can run in realtime on modern smartphones. Learn about recent updates and how you can do custom pose classification on Android, iOS and Raspberry Pi.

July 20, 2021  
Build fast, sparse on-device models with the new TF MOT Pruning API

To bridge the gap between mobile and web ML development, you can easily deploy the TensorFlow Lite Task Library to the web with the power of WebAssembly.

June 2, 2021  
How TensorFlow helps Edge Impulse make ML accessible to embedded engineers

The TensorFlow ecosystem enables companies like Edge Impulse to put artificial intelligence in the hands of domain experts who are building the next generation of consumer and industrial technologies.

May 20, 2021  
Train your own custom object detection model with TensorFlow Lite

Learn how to train a custom object detection model and deploy it to an Android app with just a few lines of code. All you need are Android Studio and a web browser. No machine learning knowledge is required.