Debian 12 images for TechNexion boards

Debian 12 features with TechNexion flexbuild

• Build or install using flexbuild
• Demo image is ready in file server

What's new?

• Access wide range of application software using apt-get
• NXP-specific hardware-accelerated components for i.MX
• Easy to customize RootFS type(desktop/server)
• TechNexion cameras support
• TechNexion VizionViewer support

VizionViewer with TEVS/VLS3

Click the VizionViewer icon in Applications

Or run vizionviewer in terminal

debian@imx8mp:~$ vizionviewer

GPU

debian@imx8mp:~$ glmark2-es2-wayland

Chromium Web Browser

Enjoy web browser with Hardware acceleration!

NPU

=== EDM-G-IMX8MP ===
Follow i.MX Machine Learning User's Guide => 7.1 Object detection pipeline example
with TEVS.

debian@imx8mp:~$ wget https://github.com/google-coral/test_data/raw/master/ssd_mobilenet_v2_coco_quant_postprocess.tflite
debian@imx8mp:~$ wget https://github.com/google-coral/test_data/raw/master/coco_labels.txt
debian@imx8mp:~$ export MODEL=$(pwd)/ssd_mobilenet_v2_coco_quant_postprocess.tflite
debian@imx8mp:~$ export LABELS=$(pwd)/coco_labels.txt

# replace video2 to video<X> if needed.
debian@imx8mp:~$ gst-launch-1.0 --no-position v4l2src device=/dev/video2 ! \
        video/x-raw,width=640,height=480,framerate=60/1 ! \
        tee name=t t. ! queue max-size-buffers=2 leaky=2 ! \
        imxvideoconvert_g2d ! \
        video/x-raw,width=300,height=300,format=RGBA ! \
        videoconvert ! video/x-raw,format=RGB ! \
        tensor_converter ! \
        tensor_filter framework=tensorflow-lite model=${MODEL} \
        custom=Delegate:External,ExtDelegateLib:libvx_delegate.so ! \
        tensor_decoder mode=bounding_boxes option1=mobilenet-ssd-postprocess option2=${LABELS} \
        option3=0:1:2:3,50 option4=640:480 option5=300:300 ! \
        mix. t. ! queue max-size-buffers=2 ! \
        imxcompositor_g2d name=mix latency=30000000 min-upstream-latency=30000000 \
        sink_0::zorder=2 sink_1::zorder=1 ! waylandsink