Deploy machine learning models on mobile and IoT devices
TensorFlow Lite is an open source deep learning framework for on-device inference.
How it works
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 models to help with common mobile and edge use cases.
Identify hundreds of objects, including people, activities, animals, plants, and places.
A few of our TensorFlow Lite users
News & announcements
See updates to help you with your work, and subscribe to our monthly TensorFlow newsletter to get the latest announcements sent directly to your inbox.
Try out a new on-device transfer learning image classification example.
Build a human pose estimation app by detecting the positions of key body parts such as the position of a person’s elbows and/or knees.
Post-training float16 quantization reduces TensorFlow Lite model sizes up to 50% while sacrificing very little accuracy - and is great for GPUs!