NXP Semiconductors’ eIQ Machine Learning (ML) software environment provides the key ingredients to perform inference of neural network models on embedded systems, and to deploy various ML algorithms on NXP microprocessors and microcontrollers at edge nodes.
The eIQ environment includes inference engines, neural network compilers and hardware abstraction layers. It also supports four main inference engines and libraries:
- OpenCV
- Arm® NN
- CMSIS-NN
- Google TensorFlow Lite
The eIQ ML software currently supports NXP’s i.MX and i.MX RT series of processors. Over time, NXP will extend device compatibility to cover its MCUs and other MPUs as well .
The software includes a variety of application examples which demonstrate how to integrate neural networks into voice, vision and sensor applications. Users can take advantage of existing MCUs or MPUs to accelerate ML application development without requiring hardware specific to machine learning.
The eIQ ML software for i.MX RT crossover processors is fully integrated into the MCUXpresso SDK release v.2.6.x. It is also included in NXP’s Yocto Linux® board support package and MCUXpresso software development kit v.2.6.0 release.
Features
| Applications
|
