NXP Semiconductors eIQ Machine Learning Software Dev Environment

More About NXP Semiconductors

NXP Semiconductors eIQ Machine Learning Software Development Environment is a combination of libraries and development tools for use with NXP microprocessors and microcontrollers. The eIQ Machine Learning Software includes the DeepViewRT™ proprietary inference engine. The software makes inferences from neural network (NN) artificial intelligence (AI) models on embedded systems. eIQ Machine Learning (ML) Software offers the key ingredients to deploy various ML algorithms at the edge (eIQ = edge intelligence) and includes inference engines, NN compilers, vision and sensor solutions, and hardware abstraction layers. Four main inference engines & libraries – OpenCV, Arm^® NN, Arm CMSIS-NN, TensorFlow Lite, and proprietary DeepViewRT runtime inference are supported.

Embedded designs can now support a variety of ML/AI applications that require high-performance data computations for fast inferencing with NXP’s i.MX applications processors and i.MX RT crossover processors based on Arm Cortex^®-A and M Cores. eIQ includes a variety of application examples to demonstrate how to integrate neural networks into voice, vision, and sensor applications. The eIQ Machine Learning Software Development Environment takes advantage of existing hardware to accelerate ML application development without requiring hardware specific for machine learning.

eIQ Machine Learning Software

Features
• Open source inference engines
• Optimized libraries
• Application samples
• Compatibility with open source technology
• Included in NXP’s Yocto Linux BSP (L4.14.y series) and MCUXpresso SDK (v2.6.0) software releases

Products Supported
• eIQ ML Software now supports the following NXP products:
• eIQ for i.MX processors officially support the i.MX 8 Series applications processor family (i.MX 8M Mini, i.MX 8M Nano, 8M, 8QuadXPlus, 8QuadMax, i.MX 8M Plus)
• eIQ for MCUs officially supports the i.MX RT1060, i.MX RT1050, and i.MX RT600 crossover processors
• Check www.nxp.com/eIQ for additional newly supported boards

Applications
• Object detection
• Voice recognition
• Image processing
• Video encoding/decoding & analysis
• Smart wearables
• Intelligent factories
• Medical
• Augmented reality

Download Now

Glow - NN Compiler for i.MX RT is an open source, community project released by Facebook in 2018 (Apache License 2.0). Glow can convert neural network models directly to machine code by using its Ahead-of-Time compilation model (AOT). NXP integrated optimized libraries for Arm Cortex M and Cadence HiFi4 DSP. Visit eIQ™ for Glow Neural Network Compiler.

Yocto Release – eIQ software for i.MX processors is supported on the current L5.43.2.0.0 series Yocto Linux alpha release.
For detailed instructions on how to add eIQ to your Yocto build please visit https://community.nxp.com/docs/DOC-343575.

MCUXpresso SDK – eIQ software for MCUs is fully integrated into the MCUXpresso SDK for i.MX RT crossover MCU platforms.

• Go to https://mcuxpresso.nxp.com and search for the i.MX RT1050 or i.MX RT1060 EVK
• Take the action: “Build MCUXpresso SDK”
Once on the SDK builder page, click on the eIQ middleware item and verify the option is now checked.
Then scroll to the bottom and click on “Download SDK”. You will be prompted to agree to the NXP Software License Agreement.
• It will be saved as a zip file.
• eIQ project can be found in the \boards\<board_name>\eiq_examples folder
• eIQ source code can be found in the \middleware\eiq folder