eIQ™ Inference with TensorFlow™ Lite Micro

Overview

The eIQ inference with TensorFlow™ Lite for Microcontrollers (TF Micro) is optimized for running machine learning models on resource constrained devices, including NXP's i.MX RT crossover MCUs.

Faster and smaller than the traditional TensorFlow Lite open source platform for machine learning, this TF Micro implementation enables inferencing at the edge with lower latency and smaller binary size.

Features

Delivered as middleware in NXP MCUXpresso SDK
Optimized for running machine learning models on i.MX RT crossover MCUs
Provides the ability to run inferencing on Arm® Cortex®-M
Faster and smaller than TensorFlow Lite
Enables inference at the edge with lower latency and smaller binary size

Features

Delivered as middleware in NXP MCUXpresso SDK
Optimized for running machine learning models on i.MX RT crossover MCUs
Provides the ability to run inferencing on Arm® Cortex®-M
Faster and smaller than TensorFlow Lite
Enables inference at the edge with lower latency and smaller binary size

eIQ^™ TensorFlow Lite

eIQ<sup>™</sup> TensorFlow Lite

eIQ^™ TensorFlow Lite

eIQ^™ TensorFlow Lite

eIQ<sup>™</sup> TensorFlow Lite

Supported Devices

i.MX-RT1010: i.MX RT1010 Crossover MCU with Arm^® Cortex^®-M7 Core
i.MX-RT1015: i.MX RT1015 Crossover MCU with Arm^® Cortex^®-M7 Core
i.MX-RT1020: i.MX RT1020 Crossover MCU with Arm^® Cortex^®-M7 Core
i.MX-RT1050: i.MX RT1050 Crossover MCU with Arm^® Cortex^®-M7 Core
i.MX-RT1060: i.MX RT1060 Crossover MCU with Arm^® Cortex^®-M7 Core
i.MX-RT1064: i.MX RT1064 Crossover MCU with Arm^® Cortex^®-M7 Core