ดูรายละเอียดการใช้งานได้ที่ Click

สินค้าประกอบด้วย
Weight: 0.042 kg

Package Contains

Raspberry Pi AI Kit ×1

Raspberry Pi AI Kit

Designed For Raspberry Pi 5

The Raspberry Pi AI Kit Bundles The Raspberry Pi M.2 HAT+ With A Hailo AI Acceleration Module For Use With Raspberry Pi 5, Provides An Accessible, Cost-Effective, And Power-Efficient Way To Integrate High-Performance AI, Suitable For Applications Including Process Control, Security, Home Automation, And Robotics.

Features At A Glance

• Contains a neural network inference accelerator capable of 13 tera-operations per second (TOPS), which is fully integrated into Raspberry Pi's camera software stack
• Thermal pad pre-fitted between module and HAT+ spreads heat across components, improving performance
• Conforms to Raspberry Pi HAT+ specification
  0℃ ~ 50℃ ambient operating temperature

Equipped With Hailo AI Acceleration Module

The AI module is a 13 TOPS neural network inference accelerator built around the Hailo-8L chip. The module uses the M.2 2242 form factor, and communicates with the Raspberry Pi 5 by accessing to the Raspberry PI M.2 HAT+.

When the host Raspberry Pi 5 is running an up-to-date Raspberry Pi OS image, it automatically detects the Hailo module and makes the NPU available for AI computing tasks. The built-in rpicam-apps camera applications in Raspberry Pi OS natively support the AI module, automatically using the NPU to run compatible post-processing tasks.

PERFORMANCE (INT8)	13 TOPS
FRAMEWORKS SUPPORT	TensorFLow, TensorFlow Lite, ONNX, Keras, Pytorch
HOST ARCHITECTURE SUPPORT	X86 or ARM
CERTIFICATIONS	CE, FCC Class A
OPERATING TEMPERATURE	0°C ~ 50°C
STORAGE/OPERATING HUMIDITY	5% ~ 90% RH (no condensation)
INTERFACE TYPE	M.2 Key B+M
DIMENSIONS	22 × 42mm
POWER SUPPLY	3.3V ± 5%
THERMAL DESIGN POWER (TDP)	6.6W
INTERFACE	PCIe Gen3, 2-lanes (x2)

Tailored For Raspberry Pi 5

Equipped With A 16Pin Official Cable For Connecting The Raspberry Pi M.2 HAT+ To The Pi5. Onboard NVMe Protocol High-Speed Reading/Writing M.2 Interface, Compatible With M.2 Solid State Drives In 2230/2242 Sizes

Please note that the Raspberry Pi motherboard and cooling fan are NOT included.

Installation

Can Be Used Together With The Pi5 Active Cooler B To Achieve Better Heat Dissipation Effect, Keeping It Cool Even Under Heavy Processing

Applied In The AI Field

Image recognition

 

Object recognition

 

Pose estimation

 

Position tracking

Outline Dimensions

Resources & Services

Wiki: www.waveshare.com/wiki/Raspberry_Pi_AI_Kit

Overview

Introduction

The Raspberry Pi AI Kit Bundles The Raspberry Pi M.2 HAT+ With A Hailo AI Acceleration Module For Use With Raspberry Pi 5.

Features

• Contains a Hailo AI module with Neural Processing Unit (NPU), with onboard Hailo-8L chip capable of 13 tera-operations per second (TOPS).
• Raspberry Pi M.2 HAT+ supports connecting the AI module to the Raspberry Pi 5.
• Thermal pads are pre-installed between the module and the M.2 HAT+.
• Support hardware kit installation.
• Onboard 16mm stacked GPIO connector.

Hardware Connection

Pay attention to the cable orientation, as shown below:

User Guide

Upgrade Software & Firmware

#1: update software
sudo apt update && sudo apt full-upgrade
sudo rpi-eeprom-update

#Configure CLI (Not required for systems above 2024)
sudo raspi-config
在Advanced Options -> Bootloader Version, select Latest. Then use Finish or Esc to exit raspi-config

#2: update firmware
sudo rpi-eeprom-update -a

Identify Devices

1: Enable PCIE interface:

Connect the hardware and the PCIE interface will automatically open as the latest system detects the hardware.
If it does not open, you can execute: add "dtparam=pciex1" in the /boot/firmware/config.txt

2: Enable PCIE Gen3: add the following content at /boot/firmware/config.txt: (Gne3 mode must be enabled):

dtparam=pciex1_gen=3

3: Reboot PI5 after modification, and then the device can be identified (or you can install the libraries before rebooting):

Test Demo

Running camera demos with rpicam-apps using the Hailo AI neural network accelerator.
Preparation:

1: Raspberry Pi 5 and Raspberry Pi AI Kit.
2: Install 64-bit Raspberry Pi OS Bookworm.
3: Install Raspberry Pi camera (for testing, using Raspberry_Pi_Camera _Module_3 to connect to the CAM1 interface).

1: Install the required dependencies for AI Kit:

sudo apt install hailo-all

2: Reboot the device:

sudo reboot

3: Check whether the driver is normal:

hailortcli fw-control identify

Or you can execute "dmesg | grep -i hailo" to check the log:

4: Check the camera:

rpicam-hello -t 10s
Please make sure the camera is working properly

5: Clone rpicam-apps

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

6: Test:

Object test:
rpicam-hello -t 0 --post-process-file ~/rpicam-apps/assets/hailo_yolov6_inference.json --lores-width 640 --lores-height 640
Yolov8 model:
rpicam-hello -t 0 --post-process-file ~/rpicam-apps/assets/hailo_yolov8_inference.json --lores-width 640 --lores-height 640
YoloX model:
rpicam-hello -t 0 --post-process-file ~/rpicam-apps/assets/hailo_yolox_inference.json --lores-width 640 --lores-height 640
Yolov5 characters and facial models
rpicam-hello -t 0 --post-process-file ~/rpicam-apps/assets/hailo_yolov5_personface.json --lores-width 640 --lores-height 640

Image segmentation:
rpicam-hello -t 0 --post-process-file ~/rpicam-apps/assets/hailo_yolov5_segmentation.json --lores-width 640 --lores-height 640 --framerate 20

Posture estimation:
rpicam-hello -t 0 --post-process-file ~/rpicam-apps/assets/hailo_yolov8_pose.json --lores-width 640 --lores-height 640

For more content, you can refer to GitHub and Hailo website.