1. Manuals
  2. Brands
  3. Avnet Manuals
  4. Computer Hardware
  5. i.MX 8M Plus
  6. User manual

Avnet i.MX 8M Plus User Manual

Edge ai kit
Hide thumbs
Table of Contents

Advertisement

Quick Links

Download this manual
i.MX 8M Plus
Edge AI Kit
Linux Yocto User Manual
V1.0
1

Advertisement

Table of Contents
loading
Need help?

Need help?

Do you have a question about the i.MX 8M Plus and is the answer not in the manual?

Questions and answers

Related Manuals for Avnet i.MX 8M Plus

Summary of Contents for Avnet i.MX 8M Plus

  • Page 1 8M Plus Edge AI Kit Linux Yocto User Manual V1.0...
  • Page 2 Edge AI Kit-Linux-Yocto-User-Manual-v1.0 Copyright Statement: • The Edge AI Kit and its related intellectual property are owned by Avnet Manufacturing Services. • Avnet Manufacturing Services has the copyright of this document and reserves all rights. Any part of the document should not be modified, distributed or duplicated in any approach and form without the written permission issued by Avnet Manufacturing Services.

  • Page 3: Revision History

    Edge AI Kit-Linux-Yocto-User-Manual-v1.0 Revision History Rev. Description Author Date v1.0 Initial version Monica 2022/12/20 http://avnet.me/imx8mplus-edgeai...

  • Page 4: Table Of Contents

    Software ........................21 eIQ ..........................21 4.1.1 eIQ inference runtime overview for i.MX8M+ ..........21 4.1.2 Tensorflow Lite ....................21 Chapter 5 Appendix ........................25 Hardware Documents ....................25 Software Documents ....................25 Linux System Image and Application Development ........... 25 http://avnet.me/imx8mplus-edgeai...
  • Page 5 Edge AI Kit-Linux-Yocto-User-Manual-v1.0 5.3.1 Out of box System Image ................25 5.3.2 Yocto BSP ......................25 5.3.3 eIQ ........................25 Contact Information ............Error! Bookmark not defined. http://avnet.me/imx8mplus-edgeai...

  • Page 6: Chapter 1 Introduction

    Chapter 1 Introduction 1.1 Target Board Edge AI Kit is a development board developed by Avnet, based on the i.MX 8M+ processor from NXP. 1.2 Introduction This document provides a guide to prepare Edge AI Kit to boot up with the Verified Linux Package and introduces how to use the supported functions.

  • Page 7: Feature List

    2 x USB 3.0 Host + 2 x USB 2.0 Host + 1 x USB 2.0 OTG 4 UART (TTL) including debug port • External interfaces (I2C, UART, SPI, CAN, RS232 and GPIO) • • LVDS Display, HDMI 2.0 • I2S Audio MIPI-CSI Camera • H.265/4 encode / decode • http://avnet.me/imx8mplus-edgeai...

  • Page 8: Chapter 2 System Boot-Up

    2.1.2 Hardware Preparation You'll need a small phillips screwdriver to complete the following steps: 1. Plug the Avnet i.MX 8M Plus SMARC SOM into the EP5 carrier board at an angle, and then push down so it rests flat on the standoffs.

  • Page 9: Set Up Debug Using Rs-232 Cable

    Edge AI Kit-Linux-Yocto-User-Manual-v1.0 2. Use the provided screws to attach the heat sink to the Avnet i.MX 8M Plus SMARC SOM. 3. Connect the 12 volt, 3 amp power connector to the board, but do not plug it in yet.

  • Page 10: Software Tools Preparation

    2.1.4 Software Tools Preparation Install Tera Term terminal software For Windows-based command-line debug output and command entry, the use of • Tera Term terminal software is recommended • Download and install teraterm-***.exe and configure the relevant COM port as shown below: http://avnet.me/imx8mplus-edgeai...

  • Page 11: Booting The Edge Ai Kit

    The desired boot mode can be selected via a 4 pole Dipswitch located next to the microUSB port on the SMARC Carrier. The following table describes the available boot options for the Edge AI Kit. See the i.MX 8M Plus Applications Processor Reference Manual from NXP for a complete description.

  • Page 12: Boot From Sd Card

    Edge AI Kit-Linux-Yocto-User-Manual-v1.0 2.2.2 Boot from SD Card 2.2.2.1 Downloading operating system images http://avnet.me/imx8mplus-edgeai Visit the downloads page: to download the out of box Yocto image 2.2.2.2 Flash the SD Card You will need a 16+GB microSD card + adapter Download and install the flash tool –...
  • Page 13 Edge AI Kit-Linux-Yocto-User-Manual-v1.0 When the system boots-up, the TeraTerm will print the following: • Avnet Embedded Strudel Distro 0.1.0-ff2970817ef8e5172d4b6593e31cd82758a1477f sm2s- imx8mp ttymxc1 sm2s-imx8mp login: Enter username as “root”, no password. • The Linux system interface also supports directly attached keyboard and mouse •...

  • Page 14: Chapter 3 Feature Configuration

    3.1.1 Available Device Tree overlays These are the overlays for the devices included in the Edge AI Kit. For overlays for additional compatible devices, see the MSC-LDK Manual from Avnet Embedded. SOM overlay: msc-sm2s-imx8mp-24N0600I-module.dtb Carrier overlay: overlay-baseboard-ep5.dtb...

  • Page 15: Selecting The Device Tree Blobs In U-Boot

    By default, both HDMI and LVDS are selected for the fdt_overlay, so HDMI should work out of the box. In U-Boot, use the printenv command to check: u-boot=> printenv fdt_overlay fdt_overlay=overlay-lvds0-ama-101a01.dtb overlay-hdmi.dtb overlay-cam1-ap1302-ar1335- dual.dtbo If you wish to use only HDMI and not LVDS, set the environment like this: setenv fdt_overlay 'overlay-hdmi.dtb overlay-cam1-ap1302.dtb’ http://avnet.me/imx8mplus-edgeai...

  • Page 16: Lvds Display

    CMOS active-pixel digital image sensors with a pixel array of 4208H x 3120V. The modules are manufactured by Rapyrus. The AR1335 digital image sensor features 1.1µm pixel technology that delivers superior low-light image quality through leading sensitivity, quantum efficiency and linear full well. http://avnet.me/imx8mplus-edgeai...

  • Page 17: Default Camera Streaming

    : set ar0144 dual config 3.3.3 Configure Dual vs Single Image Sensors The Edge AI Kit currently supports both single and dual camera configurations. Dual or single cameras can be configured using device tree overlays from U-Boot, like so: http://avnet.me/imx8mplus-edgeai...

  • Page 18: Configure Other Onsemi Image Sensors

    To configure dual AR0144, use this command and then reboot: ap1302-cfg.sh ar0144-dual 3.3.5 Troubleshooting Cameras You can check that both cameras boot with the status command: root@sm2s-imx8mp:~# ap1302-cfg.sh status U-Boot Env overlay configuration Cannot read environment, using default http://avnet.me/imx8mplus-edgeai...
  • Page 19 --list-devices /dev/v4l-subdev0 FSL Capture Media Device (platform:mxc-md): /dev/media0 vsi_v4l2dec (platform:vsi_v4l2dec): /dev/video1 vsi_v4l2enc (platform:vsi_v4l2enc): Check the CSI interface: root@sm2s-imx8mp:~# media-ctl -p The last command that can be run is the status/log of the CSI interface to check for ECC errors: http://avnet.me/imx8mplus-edgeai...

  • Page 20: V4L Commands

    -d $(media-ctl -e ap1302.4-003c) -c vflip=0 && \ v4l2-ctl -d $(media-ctl -e ap1302.4-003c) -c hflip=1 && \ v4l2-ctl -d $(media-ctl -e ap1302.4-003c) -c gamma=0 To change the white balance on the AR0144: v4l2-ctl -d $(media-ctl -e ap1302.4-003c) -c white_balance_auto_preset=0 http://avnet.me/imx8mplus-edgeai...

  • Page 21: Chapter 4 Software

    NXP’s processor by using delegates to accelerate supported operations in hardware. Read more about how delegates work in eIQ here: http://avnet.me/maaxboard-ml-delegates The following five inference engines are currently supported in the NXP eIQ software stack: TensorFlow Lite, ONNX Runtime, PyTorch, DeepView RT, and OpenCV.
  • Page 22 4.1.2.4 Verify whether acceleration is running on NPU or GPU To verify whether hardware acceleration is running on the Verisilicon NPU, you can look at the interrupt for the galcore-3D driver before and after running your model with the following command: root@sm2s-imx8mp:/usr/bin/tensorflow-lite-2.6.0/examples# cat /proc/interrupts | grep galcore:3d http://avnet.me/imx8mplus-edgeai...
  • Page 23 Note that the video examples take a path to a video file as input (720p30 video is recommended), while the camera examples target a single MIPI camera. For example, for the Mobilenet SSD Camera example, run the following script: gstnninferencedemo-mobilenet-ssd-camera http://avnet.me/imx8mplus-edgeai...
  • Page 24 Edge AI Kit-Linux-Yocto-User-Manual-v1.0 http://avnet.me/imx8mplus-edgeai...

  • Page 25: Chapter 5 Appendix

    The BSP is currently available by request only. To access the board support package (BSP) to build your own Yocto image for the Edge AI Kit, contact support.boards@avnet.com. In your email, please clearly state that you are working with the Edge AI Kit and would like that BSP.

Table of Contents