Skip to content
Daniele Cleri edited this page Sep 7, 2023 · 25 revisions

Introduction

Hailo offers a breakthrough microprocessor uniquely designed to accelerate embedded AI applications on edge devices.

Modules

You can take advantage of this microprocessor on our boards and system using the:

Compatible Boards/Systems

Celeron/Pentium/Atom/Processor Platforms

  • UP Squared Pro
  • UP Squared 6000
  • UP Squared v2
  • UP Squared Pro 7000

Core-i Platforms

  • UP Xtreme i11
  • UP Xtreme i12

Getting Started Guide

After assembling the Hailo-8 M.2 module on our compatible boards/systems, you would need to setup your system with Ubuntu operating system as described in our tutorial.

Boot into the newly setup Operating System, download the prerequisites_setup.sh and TAPPAS_vX.XX.X_withPCIeDriver.zip from our download section into your board.

Before starting make sure you have installed DKMS and your board kernel headers, if not please proceed with the following command (headers version may be different depending on your platform):

$ sudo apt install dkms linux-headers-$(uname -r)

Reboot the system before proceeding. After reboot, from the terminal, go to the folder where you have downloaded the setup file (e.g. /home/user/Downloads/), you can now execute the following commands:

$ chmod +x prerequisites_setup.sh

$ ./prerequisites_setup.sh

Now reboot the system and then open the terminal again, go to the hailo folder and run:

$ cd ~/hailo/

and then run the command:

$ ./run_tappas_docker.sh --tappas-image hailo-docker-tappas-v3.25.0.tar --container-name hailo_tappas_container

You will be prompted into the container terminal at the end of the setup process, you can exit anytime and for resuming an existing container (also after reboot) you can use the following commmand:

$ ./run_tappas_docker.sh --resume

To run one of the many sample applications included, you can run the following commands in this case for the Detection app:

$ cd apps/h8/gstreamer/general/detection/

$ ./detection.sh

Sample Application Documentation

The TAPPAS Documentation is available on Github: v3.25.0 Documentation

Model Zoo

If you need additional models to evaluate and develop your application, you can download the precompiled directly from Github: Model Zoo from this link . You can also use a simple script, available from here, to download directly all the models and then run the following commands from the terminal:

$ chmod +x download_Hailo_Model_Zoo_HEF.sh

$ ./download_Hailo_Model_Zoo_HEF.sh

SDK and additional Documentation

Please visit the Hailo Developer Zone and sign up to get access to the SDK and additional Documentation.

Clone this wiki locally