0021 MPSAI EN:修订间差异

来自Mcuzone Wiki
第48行: 第48行:
[[0005 MPS2242 2280 2280P(单SSD扩展板)#3.3 从SSD硬盘启动|点击直达烧写方法说明]]。
[[0005 MPS2242 2280 2280P(单SSD扩展板)#3.3 从SSD硬盘启动|点击直达烧写方法说明]]。


== '''四、树莓派OS下的AI(HAILO 8L)使用演示''' ==
== '''IV. AI (HAILO 8L) usage Demonstration on the Raspberry Pi OS''' ==


=== 4.1 概述 ===
=== 4.1 Overview ===
In various practical applications, the demand for camera image detection and recognition is gradually increasing, and there are many AI-based solutions available on the market. The solution demonstrated in this article involves the OV5647 camera, the MPSAI, and the HAILO 8L AI module paired with the Raspberry Pi 5.
In various practical applications, the demand for camera image detection and recognition is gradually increasing, and there are many AI-based solutions available on the market. The solution demonstrated in this article involves the OV5647 camera, the MPSAI, and the HAILO 8L AI module paired with the Raspberry Pi 5.


第71行: 第71行:
http://www.mcuzone.com/wiki/0005_MPS2242_2280/0005_MPS2242_2280_29.jpg
http://www.mcuzone.com/wiki/0005_MPS2242_2280/0005_MPS2242_2280_29.jpg


4.2.2 执行<code>sudo rpi-eeprom-update</code>,查看树莓派固件,确保树莓派的固件日期在2023年12月6日之后:
4.2.2 Run <code>sudo rpi-eeprom-update</code>to check the Raspberry Pi firmware and ensure that the firmware date is after December 6, 2023:


http://www.mcuzone.com/wiki/0005_MPS2242_2280/0005_MPS2242_2280_30.jpg
http://www.mcuzone.com/wiki/0005_MPS2242_2280/0005_MPS2242_2280_30.jpg


如上图所示,固件时间是2024年6月5日。
As shown in the above figure, the firmware date is June 5, 2024.


4.2.3 执行<code>sudo raspi-config</code>,根据下图依次选择对应选项:
4.2.3 Run <code>sudo raspi-config</code> ,select the corresponding options in sequence according to the following diagram:


http://www.mcuzone.com/wiki/0005_MPS2242_2280/0005_MPS2242_2280_31.jpg
http://www.mcuzone.com/wiki/0005_MPS2242_2280/0005_MPS2242_2280_31.jpg
第91行: 第91行:
http://www.mcuzone.com/wiki/0005_MPS2242_2280/0005_MPS2242_2280_36.jpg
http://www.mcuzone.com/wiki/0005_MPS2242_2280/0005_MPS2242_2280_36.jpg


选择完之后退出,系统会自动重启,如果没有自动重启,请手动执行 <code>sudo reboot</code> ,重启系统。
After making your selection and exiting, the system will automatically restart. If it does not restart automatically, please manually execute <code>sudo reboot</code> to restart the system.


=== 4.3 AI模块所需要的依赖安装 ===
=== 4.3 Install the depends required for the AI module ===
执行<code>sudo apt install hailo-all</code>,安装AI模块所需要的依赖安装:
Run <code>sudo apt install hailo-all</code>, install the depends required for the AI module:


http://www.mcuzone.com/wiki/0005_MPS2242_2280/0005_MPS2242_2280_37.jpg
http://www.mcuzone.com/wiki/0005_MPS2242_2280/0005_MPS2242_2280_37.jpg
第100行: 第100行:
http://www.mcuzone.com/wiki/0005_MPS2242_2280/0005_MPS2242_2280_38.jpg
http://www.mcuzone.com/wiki/0005_MPS2242_2280/0005_MPS2242_2280_38.jpg


完成后执行 <code>sudo reboot</code> ,重启系统,使这些设置生效。
After completing this, execute <code>sudo reboot</code> to restart the system and apply these settings.


执行<code>hailortcli fw-control identify</code>,如果出现以下输出则成功安装了HAILO 8L的依赖:
Run <code>hailortcli fw-control identify</code>, If the following output appears, it indicates that the depends for HAILO 8L have been successfully installed:


http://www.mcuzone.com/wiki/0005_MPS2242_2280/0005_MPS2242_2280_39.jpg
http://www.mcuzone.com/wiki/0005_MPS2242_2280/0005_MPS2242_2280_39.jpg


最后再执行<code>rpicam-hello -t 10s</code>,打开摄像头并出现预览窗口,确定摄像头正常。
Finally, execute <code>rpicam-hello -t 10s</code> to turn on the camera and bring up the preview window, ensuring that the camera is functioning normally.


http://www.mcuzone.com/wiki/0005_MPS2242_2280/0005_MPS2242_2280_40.jpg
http://www.mcuzone.com/wiki/0005_MPS2242_2280/0005_MPS2242_2280_40.jpg


=== 4.4 图像识别检测 ===
=== 4.4 Image recognition and detection ===
执行:
Run:


<code>git clone --depth 1 <nowiki>https://github.com/raspberrypi/rpicam-apps.git</nowiki> ~/rpicam-apps</code>
<code>git clone --depth 1 <nowiki>https://github.com/raspberrypi/rpicam-apps.git</nowiki> ~/rpicam-apps</code>


克隆rpicam-apps库:
Clone the library of rpicam-apps:


http://www.mcuzone.com/wiki/0005_MPS2242_2280/0005_MPS2242_2280_41.jpg
http://www.mcuzone.com/wiki/0005_MPS2242_2280/0005_MPS2242_2280_41.jpg


克隆完成后,就可以开始进行图像的识别检测:
After cloning is completed, you can begin image recognition and detection:


<code>rpicam-hello -t 0 --post-process-file ~/rpicam-apps/assets/hailo_yolov6_inference.json --lores-width 640 --lores-height 640</code>
<code>rpicam-hello -t 0 --post-process-file ~/rpicam-apps/assets/hailo_yolov6_inference.json --lores-width 640 --lores-height 640</code>
第127行: 第127行:
http://www.mcuzone.com/wiki/0005_MPS2242_2280/0005_MPS2242_2280_43.jpg
http://www.mcuzone.com/wiki/0005_MPS2242_2280/0005_MPS2242_2280_43.jpg


'''<big>鉴于本开发板的测试需要在外网下载大量数据,为了方便用户进行测试,用户在购买本开发板后,可以联系我司获取已经配置完毕的树莓派OS镜像。</big>'''
'''<big>You should downloading a large amount of data from the internet out of China to use the testing of this development board, so users can contact our company after buying this development board to obtain a pre-configured Raspberry Pi OS image.</big>'''


== '''五、树莓派系统下使用SSD硬盘''' ==
== '''五、树莓派系统下使用SSD硬盘''' ==

2024年9月4日 (三) 11:27的版本

关键词

树莓派5、PCIe、驱动安装、操作演示、2230、2242、2280、NVMe SSD、固态硬盘 X1、AI、HAILO 8L、摄像头、OV5647、图像检测、图像识别

一、简介

二、硬件资源

1. 基于树莓派5设计,采用16Pin FPC和树莓派5的PCle接口连接;

2. 扩展板通过PCIe Switch进行一扩二;

3. 一路PCIe扩展M.2 M-key接口,2242尺寸,用于接AI模块 HAilo8,树莓派官方OS加载驱动;

4. 一路PCIe扩展M.2 M-key接口,接NVMe SSD(PCIe X1,仅支持Gen2模式),支持2230/2242/2280尺寸(默认焊接2280铜柱),不支持SATA和NGFF SSD硬盘;

5. SSD可用于存储数据和系统启动;从SSD启动时,需树莓派官方固件是2024.5.13以后的版本;

6. 40Pin GPIO部分采用开窗设计,可通过杜邦线连接,不影响树莓派5自身GPIO引脚使用;

7. PCB板沉金工艺,无铅生产,且通过UL认证,符合ROHS标准,防火等级94V-0;

8. 采用4个M2.5固定孔,和树莓派5定位孔吻合;

9. 可选配铝合金外壳。

0021_MPSAI_01.jpg

三、系统烧写及设置

3.1 概述

本文档采用树莓派OS、Ubuntu系统和OpenWrt系统进行测试。

1) 树莓派OS的版本为2024-07-04-raspios-bookworm-arm64.img.xz,树莓派OS下载地址:

https://www.raspberrypi.com/software/operating-systems/#raspberry-pi-os-64-bit

2) Ubuntu系统的版本为ubuntu-24.04-preinstalled-desktop-arm64+raspi.img.xz,Ubuntu OS下载地址:

https://ubuntu.com/download/raspberry-pi

3) OpenWrt系统版本:

openwrt-bcm27xx-bcm2712-rpi-5-squashfs-sysupgrade-linux-6.1.100-20240805.img.gz

3.2 系统烧写在SD(TF)卡上

点击直达烧写方法说明

3.3 系统烧写在SSD硬盘上

点击直达烧写方法说明

IV. AI (HAILO 8L) usage Demonstration on the Raspberry Pi OS

4.1 Overview

In various practical applications, the demand for camera image detection and recognition is gradually increasing, and there are many AI-based solutions available on the market. The solution demonstrated in this article involves the OV5647 camera, the MPSAI, and the HAILO 8L AI module paired with the Raspberry Pi 5.

0021_MPSAI_02.jpg

Note: The operation requires a stable internet connection to the regions out of China (you may need to find your own method). Otherwise, many files may not download or may only partially download, which could ultimately lead to the code failing to run.

4.2 Update system

Note: The following operational steps apply whether the system is booted from a TF card or an SSD.

4.2.1 Boot the Raspberry Pi OS and run commands in the terminal:

sudo apt update

sudo apt full-upgrade

0005_MPS2242_2280_28.jpg

0005_MPS2242_2280_29.jpg

4.2.2 Run sudo rpi-eeprom-updateto check the Raspberry Pi firmware and ensure that the firmware date is after December 6, 2023:

0005_MPS2242_2280_30.jpg

As shown in the above figure, the firmware date is June 5, 2024.

4.2.3 Run sudo raspi-config ,select the corresponding options in sequence according to the following diagram:

0005_MPS2242_2280_31.jpg

0005_MPS2242_2280_32.jpg

0005_MPS2242_2280_33.jpg

0005_MPS2242_2280_34.jpg

0005_MPS2242_2280_35.jpg

0005_MPS2242_2280_36.jpg

After making your selection and exiting, the system will automatically restart. If it does not restart automatically, please manually execute sudo reboot to restart the system.

4.3 Install the depends required for the AI module

Run sudo apt install hailo-all, install the depends required for the AI module:

0005_MPS2242_2280_37.jpg

0005_MPS2242_2280_38.jpg

After completing this, execute sudo reboot to restart the system and apply these settings.

Run hailortcli fw-control identify, If the following output appears, it indicates that the depends for HAILO 8L have been successfully installed:

0005_MPS2242_2280_39.jpg

Finally, execute rpicam-hello -t 10s to turn on the camera and bring up the preview window, ensuring that the camera is functioning normally.

0005_MPS2242_2280_40.jpg

4.4 Image recognition and detection

Run:

git clone --depth 1 https://github.com/raspberrypi/rpicam-apps.git ~/rpicam-apps

Clone the library of rpicam-apps:

0005_MPS2242_2280_41.jpg

After cloning is completed, you can begin image recognition and detection:

rpicam-hello -t 0 --post-process-file ~/rpicam-apps/assets/hailo_yolov6_inference.json --lores-width 640 --lores-height 640

0005_MPS2242_2280_42.jpg

0005_MPS2242_2280_43.jpg

You should downloading a large amount of data from the internet out of China to use the testing of this development board, so users can contact our company after buying this development board to obtain a pre-configured Raspberry Pi OS image.

五、树莓派系统下使用SSD硬盘

关于对SSD硬盘的基本操作,我们可以参考以下链接:

SSD用作存储扩展(树莓派OS下)

对SSD进行分区等操作

调整外设启动顺序

安装硬盘测速软件hdparm

关于如何测试SSD硬盘,我们可以参考以下链接:

SSD硬盘测试(树莓派OS下)

六、Ubuntu系统下使用SSD硬盘

关于对SSD硬盘的基本操作,我们可以参考以下链接,除了SSD用作存储扩展中与树莓派OS下操作略有不同,其余部分基本相同:

SSD用作存储扩展(Ubuntu系统下)

对SSD进行分区等操作

调整外设启动顺序

安装硬盘测速软件hdparm

关于如何测试SSD硬盘,我们可以参考以下链接:

SSD硬盘测试(Ubuntu系统下)

七、OpenWrt系统下使用SSD硬盘

关于如何在OpenWrt系统下使用SSD硬盘,我们可以参考以下链接:

SSD硬盘测试(OpenWrt系统下)

联系我们

4f7e81daf8791971.jpg 79c020da7ad0af9b.jpg 2851e01a0549e6f7.gif 0003_bb.jpg 0005_qq.jpg QQ:8204136

邮件:mcuzone@vip.qq.com

电话:13957118045

如本页面有任何疏漏、错误或者侵权,请通过上述途径联系我们,谢谢!

Copyright 2004-2024 野芯科技