Machine Learning Guide


Our newest QSXP-ML81 CoM with the NXP i.MX8M Plus processor comes with a Machine-Learning-Unit (MLU) on-board.

There are different Machine Learning demos you can run on the processor’s NPU.

Further information can be read at the i.MX Machine Learning User’s Guide

Demo Video

Precompiled Images


Precompiled Image



qsxp-ml81-ml in Download Area

Machine Learning Demo Image.


tx8p-ml81-ml in Download Area

Machine Learning Demo Image.


tx8p-ml82-ml in Download Area

Machine Learning Demo Image.


qsxp-ml81-basler in Download Area

Machine Learning Demo Image with Basler Camera support.

Yocto Setup

For creating the neccessary RootFS, a complete Yocto build environment is required.

Depending on your module choose the correct guide - if not already set up.


QSXP, TX8P use NXP Yocto BSP Guide

  1. Setup the Yocto build-directory as described in the Yocto guide for your machine. Use the following values:

  • DISTRO=karo-xwayland

  • MACHINE=<desired-machine>

  1. Compile the image.

bitbake karo-image-ml


If you want to compile the image with basler camera support, follow the additional steps described at Basler Camera.

Then compile:

bitbake karo-image-basler


Live Object Detection


For this demo a camera is mandatory. The following example was tested with karo-image-basler and a Basler camera.

The pre-trained eIQ DeepViewRT model from NXP allows it, to run a live eIQ DeepViewRT GStreamer Detection Demo on the NPU of the i.MX8M Plus.

  1. Download the eIQ Demo File Archive and unpack it to your target.

  2. On the target, run the following command to show the example using the CPU:

./ssdcam-gst -m mobilenet_ssd_v1_1.00_trimmed_quant_anchors.rtm -c /dev/video2
  1. Run the following commands to show the example using the NPU:

modelrunner -m mobilenet_ssd_v1_1.00_trimmed_quant_anchors.rtm -e ovx -H 10818 &
./ssdcam-gst -m mobilenet_ssd_v1_1.00_trimmed_quant_anchors.rtm -r -u 1 -c /dev/video2