Skip to main content
Version: BSP 6.x.y

Building Machine Learning Software with Reference Images for Yocto Project


In this article, we will show how to integrate to the Toradex Reference Images for Yocto Project Software the following AI runtimes:

Toradex BSP Versionmeta-ml versionAI Runtimes
Based on NXP BSP L6.1.22_2.0.0​
Download documentation (requires login)
TensorFlow Lite v2.10.0
OpenCV 4.6.0


NXP eIQ software provides the basis for Machine Learning application optimized for i.MX SoCs, enabling Neural Network acceleration on NXP SoCs on the GPU or NPU through the OpenVX backend.

When executing inference on Cortex-A cores, NXP eIQ inference engines support multi-threaded execution. eIQ based on NXP BSP L5.15.71_2.2.x also supports DeepViewRT (install guide/documentation).

You can find more detailed information on the features of eIQ for each specific version on the i.MX Machine Learning User's Guide available on the NXP's Embedded Linux Documentation.


OpenVX provides NPU/GPU acceleration for TensorFlow Lite, but not OpenCV (as stated on the i.MX Machine Learning User's Guide).

TensorFlow Lite

As stated in the TensorFlow Lite Documentation:

TensorFlow Lite is a set of tools that enables on-device machine learning by helping developers run their models on mobile, embedded, and IoT devices.

In order to execute TensorFlow models with TensorFlow Lite, you need to use the TensorFlow Lite Converter. The TensorFlow Lite version needs to match the TensorFlow version used to design the model.


Not every TensorFlow model is directly convertible to TensorFlow Lite, because some TensorFlow operators (ops) do not have a TensorFlow Lite equivalent. However, in some situations, you can use a mix of TensorFlow and TensorFlow Lite ops by enabling the Select TensorFlow Ops feature. Please, see the TensorFlow Lite Documentation for more information about this feature and how to enable it.

Torizon OS

To learn how to use Tensorflow-lite with Torizon, read the following article:


Adding eIQ recipes to Reference Images for Yocto Project

Cloning the Toradex BSP repository

In an empty directory, use git-repo to obtain the Toradex BSP on the version 6.4.0, as explained in the section First-time Configuration of the Build a Reference Image with Yocto Project article:


To improve the comprehension of this article, we will create a directory named ~/yocto-ml-build.

$ mkdir -p ~/yocto-ml-build/bsp-toradex
$ cd ~/yocto-ml-build/bsp-toradex
$ repo init -u git:// -b kirkstone-6.x.y -m tdxref/default.xml
$ repo sync

Source the file export to setup the environment. On the first invocation, this also copies a sample configuration to build/conf/*.conf

$ . export

Getting eIQ

eIQ is provided on a Yocto layer called meta-imx/meta-ml.


The next steps expect the current directory to be <project-folder>/build.

Git clone the meta-imx repository to your project directory:

$ git clone --depth 1 -b mickledore-6.1.22-2.0.0 ../meta-imx

Copying the Recipes to your environment

First, create a layer named meta-ml, add it to your environment and remove the example recipe:


This step may fail due to missing packages in your computer:
ERROR: The following required tools (as specified by HOSTTOOLS) appear to be unavailable in PATH, please install them in order to proceed: lz4c
If that is the case, install the required packages and repeat this step.

$ bitbake-layers create-layer ../layers/meta-ml
$ bitbake-layers add-layer ../layers/meta-ml
$ rm -rf ../layers/meta-ml/recipes-example

Copy the recipes from meta-imx to your layer:

$ cp -r ../meta-imx/meta-ml/recipes-* ../layers/meta-ml/

Adding the recipes to your distribution

Add the meta-ml recipes and some image processing libraries to your image:

$ echo 'IMAGE_INSTALL:append = " tensorflow-lite tensorflow-lite-vx-delegate opencv python3-pillow adwaita-icon-theme "' >> conf/local.conf

In order to build the image a little bit faster, for now, we will remove the Qt packages. Keep it if you are planning to use Qt in your image.

$ echo 'IMAGE_INSTALL:remove = " packagegroup-tdx-qt5 wayland-qtdemo-launch-cinematicexperience "' >> conf/local.conf

Configuring the Machine

If you want to build for a machine based on an NXP SoM, some downloads require you to read and accept the NXP/Freescale EULA available in <project-folder>/layers/meta-freescale/EULA.

You have to state your acceptance by appending the following line to your <project-folder>/build/conf/local.conf file:


Select the SoM in <project-folder>/build/conf/local.conf by uncommenting (removing the # in) the line corresponding to your SoM. For example, for the Verdin iMX8MP:

MACHINE ?= "verdin-imx8mp"


Build the tdx-reference-multimedia-image image for your target SoM as explained on the Build a Reference Image with Yocto Project article:

$ bitbake tdx-reference-multimedia-image

In some situations of internet or server instability, trying to build may fail with:
do_fetch: Fetcher failure for URL:
In most cases, this issue is solved by re-trying to build.

Building with reduced RAM usage

Your computer may run out of RAM while compiling some packages. To reduce the RAM usage, limit the number of threads used by BitBake and Make.

Flashing the image

To flash your image to the board, see the Quickstart Guide for your SoM.

Executing Demos

NXP provides an inference example, supporting CPU, GPU, and NPU.

To execute it, cd to the example's directory:

# cd /usr/bin/tensorflow-lite-2.10.0/examples/

This demo will take an arbitrary picture (grace_hopper.bmp) as an input of an image classification neural network based on Mobilenet V1 (224x224 input size). See more information about this demo on the NXP's i.MX Machine Learning User's Guide.

To run the demo:

# USE_GPU_INFERENCE=0 ./label_image -m mobilenet_v1_1.0_224_quant.tflite -i grace_hopper.bmp -l labels.txt --external_delegate_path=/usr/lib/

See below a comparison of Inference Time executing this demo:

SomInference TimeFPS (1/Inference Time)
Verdin iMX8M Plus - CPU only44.70 ms22.37 fps
Verdin iMX8M Plus with GPU Support160.07 ms6.25 fps
Verdin iMX8M Plus with NPU Support2.57 ms389.11 fps
Apalis iMX8Q Max - CPU only41.17 ms24.29 fps
Apalis iMX8Q Max with GPU Support13.08 ms76.45 fps
Colibri iMX8QX Plus - CPU only99.59 ms10.04 fps
Colibri iMX8QX Plus with GPU Support118.70 ms8.42 fps

Alternatively, you can run the same example using a Python implementation:

# USE_GPU_INFERENCE=0 python3 -e /usr/lib/

As explained on the NXP's Application Note AN12964, the i.MX 8M Plus SoC requires an Warmup Time of about 7 seconds to initiate before delivering its expected high performance. You will observe this extra time when starting an application with NPU support.

Additional Resources

See the version-specific NXP's i.MX Machine Learning User's Guide for more information about eIQ.

Send Feedback!