eIQ® for Arm® CMSIS-NN | NXP Semiconductors

Automotive

Industrial

Consumer

Technologies

eIQ® for Arm® CMSIS-NN

eIQArmCMSISNN

Arm CMSIS-NN is a collection of efficient neural network kernels used to maximize the performance and minimize the memory footprint of neural networks on Arm® Cortex®-M processor cores. For easy deployment, NXP eIQ integrates CMSIS-NN directly into MCUXpresso SDK, along with all the other Arm CMSIS components. The use of CMSIS-NN requires more manual intervention than TensorFlow Lite, but yields faster performance and small memory footprint, at the expense of a limited set of neural network operators. Therefore, some models are not supported. Arm also provides a conversion script to parse the network topology and automatically determine the appropriate functions to be used.

Diagram

eIQ for Arm® CMSIS-NN

eIQ for Arm<sup>®</sup> CMSIS-NN
Get diagram PDF

Features

  • Delivered as middleware in the MCUXpresso SDK
  • Supports i.MX RT applications processors, LPC55S69 MCUs, and Cortex-M based devices
  • Developed by Arm to provide neural network support for Cortex-M4 and Cortex-M7 cores
  • Faster and smaller than TF Lite because CMSIS-NN development flow is entirely offline, creating a binary targeting M-class platform
  • Supports a basic set of operations to implement common model layers (e.g, convolution, fully-connected, pooling, activation)
  • Conversion scripts (from Arm) to convert Caffe models into CMSIS-NN API calls

Supported Devices

  • i.MX-RT1050: i.MX RT1050 Crossover MCU with Arm® Cortex®-M7 Core
  • LPC55S6x: High Efficiency Arm® Cortex®-M33-Based Microcontroller Family
  • i.MX-RT1060: i.MX RT1060: Crossover MCU with Arm® Cortex®-M7

Downloads

Quick reference to our software types.
Filters

1 download

  • Examples and Quick Start Software

    MCUXpresso SDK Builder

    EXTERNALRev 1Jan 28, 20211 KBMCUXPRESSO-SDK-EIQ
    Download

Note: For better experience, software downloads are recommended on desktop.

Y true 0 SSPeIQArmCMSISNNen 2 Application Note Application Note t789 1 Fact Sheet Fact Sheet t523 1 en_US en_US en Application Note Application Note 1 1 0 English AN12781SW.zip /docs/en/application-note-software/AN12781SW.zip /docs/en/application-note-software/AN12781SW.zip CMSIS-NN is a collection of optimized Neural Network (NN) functions for Arm Cortex-M core microcontrollers to enable neural networks and machine learning. 1587111140388729768715 SSP 1.4 MB None None documents None 1587111140388729768715 /docs/en/application-note/AN12781.pdf 1434732 /docs/en/application-note/AN12781.pdf AN12781 documents N N 2020-04-17 Caffe Model Development on MNIST Dataset with CMSIS-NN Library /docs/en/application-note/AN12781.pdf /docs/en/application-note/AN12781.pdf Application Note N 645036621402383989 2024-07-08 pdf N en Apr 17, 2020 645036621402383989 Application Note Y N Caffe Model Development on MNIST Dataset with CMSIS-NN Library Fact Sheet Fact Sheet 1 2 4 Japanese Machine learning software for NXP i.MX and MCUs – libraries, example applications, inference engines, HALs 1562948465206707057398ja SSP 653.2 KB None None documents None 1562948465206707057398 /docs/ja/fact-sheet/EIQ-FS.pdf 653150 /docs/ja/fact-sheet/EIQ-FS.pdf EIQ-FS documents N N 2019-07-12 eIQ Software Fact Sheet /docs/ja/fact-sheet/EIQ-FS.pdf /docs/ja/fact-sheet/EIQ-FS.pdf Fact Sheet N 736675474163315314 2022-12-07 ja Jul 11, 2023 736675474163315314 Fact Sheet Y N eIQ 機械学習ソフトウェア開発環境 4 English Machine learning software for NXP i.MX and MCUs – libraries, example applications, inference engines, HALs 1562948465206707057398 SSP 653.2 KB None None documents None 1562948465206707057398 /docs/en/fact-sheet/EIQ-FS.pdf 653150 /docs/en/fact-sheet/EIQ-FS.pdf EIQ-FS documents N N 2019-07-12 eIQ Software Fact Sheet /docs/en/fact-sheet/EIQ-FS.pdf /docs/en/fact-sheet/EIQ-FS.pdf Fact Sheet N 736675474163315314 2022-12-07 pdf N en Jan 21, 2022 736675474163315314 Fact Sheet Y N eIQ Software Fact Sheet false 0 eIQArmCMSISNN downloads en true 1 Y SSP Y Y Application Note 1 /docs/en/application-note/AN12781.pdf 2020-04-17 1587111140388729768715 SSP 1 Apr 17, 2020 Application Note CMSIS-NN is a collection of optimized Neural Network (NN) functions for Arm Cortex-M core microcontrollers to enable neural networks and machine learning. None /docs/en/application-note/AN12781.pdf English documents 1434732 None 645036621402383989 2024-07-08 N /docs/en/application-note/AN12781.pdf Caffe Model Development on MNIST Dataset with CMSIS-NN Library /docs/en/application-note/AN12781.pdf documents 645036621402383989 Application Note N en None Y pdf 0 N N Caffe Model Development on MNIST Dataset with CMSIS-NN Library 1.4 MB AN12781 N 1587111140388729768715 Fact Sheet 1 /docs/en/fact-sheet/EIQ-FS.pdf 2019-07-12 1562948465206707057398 SSP 2 Jan 21, 2022 Fact Sheet Machine learning software for NXP i.MX and MCUs – libraries, example applications, inference engines, HALs None /docs/en/fact-sheet/EIQ-FS.pdf English documents 653150 None 736675474163315314 2022-12-07 N /docs/en/fact-sheet/EIQ-FS.pdf eIQ Software Fact Sheet /docs/en/fact-sheet/EIQ-FS.pdf documents 736675474163315314 Fact Sheet N en None Y pdf 4 N N eIQ Software Fact Sheet 653.2 KB EIQ-FS N 1562948465206707057398 true Y Softwares

Documentation

Quick reference to our documentation types.

Filters

2 documents

Compact List

Hardware

Quick reference to our board types.
Filters

3 hardware offerings

Related Software

Quick reference to our software types.

Filters

1 software offerings

To find a complete list of our partners that support this software, please see our Partner Marketplace.

Training

Filters

1 training