Instructions how to install the HAILO-8L AI HAT on the RPI5 computer and running the examples using different inputs.

rpi5-hailo-ai-hat-installation.md

Raspberry Pi 5 Hailo AI HAT Installation

Update your Raspberry Pi to run the latest software:

sudo apt update && sudo apt full-upgrade

Set PCIe to Gen3

While using Gen2 is an option, it will result in lower performance. The Hailo AI HAT is auto detected as Gen3, but if you are using the M.2 HAT, you will need to set it manually.

sudo raspi-config

Select option 6 Advanced Options > A8 PCIe Speed then choose Yes to enable PCIe Gen 3 mode, and then reboot the device.

Run Raspberry Pi configuration tool,
under Advanced Options > Bootloader Version choose Latest:

sudo raspi-config

This should also prompt you and install the latest firmware, if it didn't, run sudo rpi-eeprom-update -a. And finally reboot the device:

sudo reboot

Test HAT and Hailo Tools

To confirm the HAT installation run hailortcli fw-control identify and you should see something like this:

Executing on device: 0001:01:00.0
Identifying board
Control Protocol Version: 2
Firmware Version: 4.20.0 (release,app,extended context switch buffer)
Logger Version: 0
Board Name: Hailo-8
Device Architecture: HAILO8L
Serial Number: HLDDLBB242601189
Part Number: HM21LB1C2LAE
Product Name: HAILO-8L AI ACC M.2 B+M KEY MODULE EXT TMP

Test TAPPAS Core installation by running the following commands:

gst-inspect-1.0 hailotools

Expected result:

god@pi5ai:~ $ gst-inspect-1.0 hailotools
Plugin Details:
  Name                     hailotools
  Description              hailo tools plugin
  Filename                 /lib/aarch64-linux-gnu/gstreamer-1.0/libgsthailotools.so
  Version                  3.31.0
  License                  unknown
  Source module            gst-hailo-tools
  Binary package           gst-hailo-tools
  Origin URL               https://hailo.ai/

  hailoaggregator: hailoaggregator - Cascading
  hailocounter: hailocounter - postprocessing element
  hailocropper: hailocropper
  hailoexportfile: hailoexportfile - export element
  hailoexportzmq: hailoexportzmq - export element
  hailofilter: hailofilter - postprocessing element
  hailogallery: Hailo gallery element
  hailograytonv12: hailograytonv12 - postprocessing element
  hailoimportzmq: hailoimportzmq - import element
  hailomuxer: Muxer pipeline merging
  hailonv12togray: hailonv12togray - postprocessing element
  hailonvalve: HailoNValve element
  hailooverlay: hailooverlay - overlay element
  hailoroundrobin: Input Round Robin element
  hailostreamrouter: Hailo Stream Router
  hailotileaggregator: hailotileaggregator
  hailotilecropper: hailotilecropper - Tiling
  hailotracker: Hailo object tracking element

  18 features:
  +-- 18 elements

Install Hailo RPi5 Basic Pipelines

Clone the examples repository:

git clone https://github.com/hailo-ai/hailo-rpi5-examples.git

Run the automated install process:

cd hailo-rpi5-examples && ./install.sh

Running the examples

While inside hailo-rpi5-examples activate the Python virtual environment:

source setup_env.sh

This is the expected result:

god@pi5ai:~/hailo/hailo-rpi5-examples $ source setup_env.sh
Setting up the environment...
Setting up the environment for hailo-tappas-core...
TAPPAS_VERSION is 3.31.0. Proceeding...
You are not in the venv_hailo_rpi5_examples virtual environment.
Virtual environment exists. Activating...
TAPPAS_POST_PROC_DIR set to /usr/lib/aarch64-linux-gnu/hailo/tappas/post_processes
DEVICE_ARCHITECTURE is set to: HAILO8L
(venv_hailo_rpi5_examples) god@pi5ai:~/hailo/hailo-rpi5-examples $ 

Run simple detection example:

python basic_pipelines/detection_simple.py

Run full detection example:

python basic_pipelines/detection.py

To close the applications press Ctrl+C

Running with Raspberry Pi camera input:

python basic_pipelines/detection.py --input rpi

Running with USB webcam input:

python basic_pipelines/detection.py --input usb