eIQ Machine Learning (ML) software

development environment leverages

inference engines, neural network compilers,

optimized libraries, deep learning toolkits

and open-source technologies for easier,

more secure system-level application

development and ML algorithm enablement,

as well as auto-quality ML enablement.

OVERVIEW

The NXP

eIQ (“edge intelligence”) ML software

environment provides the key ingredients to do inference

with neural network (NN) models on embedded systems

and deploy ML algorithms on NXP microprocessors and

microcontrollers for edge nodes. It includes inference

engines, NN compilers, libraries and hardware abstraction

layers that support TensorFlow Lite, Glow, Arm

NN and

Arm CMSIS-NN.

With NXP’s i.MX applications processors and i.MX RT

crossover MCUs based on Arm Cortex

-A and M cores,

respectively, embedded designs can now support deep

learning applications that require high-performance

data analytics and fast inferencing.

eIQ machine learning software includes a variety of

application examples that demonstrate how to integrate

neural networks into voice, vision and sensor applications.

The developer can choose whether to deploy their ML

applications on Arm Cortex A, Cortex M and GPUs, or for

high-end acceleration on the neural processing unit of the

i.MX 8M Plus.

APPLICATIONS

eIQ ML software helps enable a variety of vision and sensor

applications working in conjunction with a collection of

device drivers and functions for cameras, microphones and

a wide range of environmental sensor types.

• Object detection and recognition

• Voice command and keyword recognition

• Anomaly detection

• Image and video processing

• Other AI and ML application domains include:

– Smart wearables

– Intelligent factories and smart buildings

– Healthcare and diagnostics

– Augmented reality

– Logistics

– Public safety

FEATURES

• Machine learning workflow tool

• Open-source and proprietary inference engines

• Neural network compilers

• Model validation and profiling tools

• Optimized libraries

• Application samples

• Runtime components included in NXP’s Yocto Linux

BSP and MCUXpresso SDK software releases

eIQ

MACHINE LEARNING

SOFTWARE DEVELOPMENT

ENVIRONMENT

FACT SHEET

eIQ™ ML SOFTWARE

www.nxp.com/eiqwww.nxp.com/eiq 2

NXP eIQ MACHINE LEARNING SOFTWARE — DEVELOPMENT TOOLS

eIQ TOOLKIT

The eIQ machine learning software development

environment includes the eIQ Toolkit, an easy-to-use

ML workflow tool designed to ease ML development.

The eIQ Toolkit enables graph-level profiling capabilities

with runtime insights to optimize neural network

architectures for execution on EdgeVerse™ processors.

The eIQ Toolkit output seamlessly feeds into

DeepViewRT™, TensorFlow™ Lite, TensorFlow Lite Micro,

Glow and Arm NN inference engines.

eIQ TOOLKIT WORKFLOW

eIQ PORTAL

The eIQ Portal is an intuitive graphical user interface (GUI)

within the eIQ Toolkit that simplifies ML development. It

allows users to create, optimize, debug, convert and export

ML models. In addition, embedded developers can import

datasets and models from TensorFlow and ONNX formats,

and then rapidly train and deploy neural network models

and ML workloads.

eIQ TOOLKIT — COMMAND LINE HOST

TOOL SUPPORT

The eIQ Toolkit and the eIQ Portal are provided with

examples demonstrating use cases and guidelines for the

different process flow options such as importing pretrained

models based on popular frameworks, creating, importing

and augmenting datasets to develop models.

The eIQ Toolkit, including eIQ Portal, is delivered with a

single click at www.nxp.com/eIQ.

User data User machine learning model

Deploy model to target

Validate model on target

Train model

Select and optimize

model for target

(Optional) Augment dataset

Import dataset

eIQ Portal

Bring Your Own Data

eIQ™ Toolkit

Deploy model to target

Convert and optimize model

Load and visualize model

eIQ Portal / Model Tool

Bring Your Own Model

Prediction

eIQ inference engines

eIQ

TOOLKIT BLOCK DIAGRAM