Yocto minimal image for setting up the AI on NXP i.MX8M Plus

🚧 Documentation under development

The Getting started with AI on NXP i.MX8M Plus guide is currently under active development. Some sections may be incomplete or change without notice.

Questions? Contact RidgeRun or email to support@ridgerun.com.

Getting started with AI on NXP i.MX8M Plus
Introduction
Overview i.MX8M Plus hardware specifications Development tools Development kit DART-MX8M-PLUS Development kit Quick getting started Yocto minimal image Flashing SD card First steps on the board
Development
Gatesgarth and Hardknott Yocto versions Downloading Yocto images for NXP based BSP Building an imx-core-image Flashing SD card Integrating multimedia software stack Installing GStreamer Installing OpenCV Integrating Artificial Intelligence software stack Installing TensorFlow Lite for NXP based images Installing R2Inference Installing GstInference Developing software for the board Building the SDK Crosscompiling apps for GStreamer, TensorFlow Lite, and OpenCV Exploring TensorFlow Lite delegates for prototyping
Neural Processing Unit
Introduction Profiling the NPU Installing gputop Setting the board on debug mode Use Case experiments: Smart Parking Introduction to the use case License Plate Detection TinyYOLO version 3 Training a model compatible with GstInference License Plate Recognition Rosetta Getting the model prototyping Bash scripts for CPU usage and time estimation Serial experiments Parallel Experiments Results
GStreamer
Exploring Rosetta element for character recognition Example pipelines Smart Parking Video inferences Image inferences Video streaming
Contact Us

Downloading and downloading Gatesgarth

Let's suppose we are working in $HOME as the root directory for this process.

So, move into that directory and create a folder in which the download will be performed:

cd $HOME
mkdir imx8-yocto-variscite
cd imx8-yocto-variscite

Initialize the repository using repo installed before:

repo init -u https://github.com/varigit/variscite-bsp-platform.git -b fsl-gatesgarth -m imx-5.10.9-1.0.0-var01.xml

Synchronize the local repo with the remote one:

repo sync

Configuring the environment for image building from XWayland distribution

Here we need to define distributions and the device by setting the following variables:

• DISTRO
• MACHINE

In this case, we have i.MX8M Plus from variscite and the chosen distro is xwayland, so the parameters are:

DISTRO=fsl-imx-xwayland
MACHINE=imx8mp-var-dart

Inside our development directory, we need to set a build directory:

mkdir build_xwayland

At first time configuring the environment we need to execute the bash script called var-setup-release.sh, and specify the build folder:

source var-setup-release.sh -b build_xwayland

At this point, some files will be created in $HOME/imx8-yocto-variscite/build_xwayland. Inside the build directory, a folder called conf contains two files:

• local.conf
• bblayers.conf

Go to local.conf and at the end of this file add the following lines (This is optional, this will add some protocols recommended by Variscite):

IMAGE_INSTALL_append = " \
    tcf-agent \
    openssh-sftp-server \
    "

Finally, we are ready to build the minimal image for testing the process explained:

bitbake core-image-minimal