Home
Knowledge Base
Mixtile Blade 3
Use Cases
Using a Hailo AI Accelerator on Mixtile Blade 3

Using a Hailo AI Accelerator on Mixtile Blade 3

Mixtile Blade 3 (also known as Blade 3) has a U.2 interface that can be extended to M.2 with an adapter, making it possible to integrate with a Hailo AI accelerator for higher AI performance.

This document describes how to install a Hailo-8L M.2 AI accelerator to Blade 3 and run YOLO demos on Hailo-8L.

Prerequisites

Before you start, make sure you have:

Installed Ubuntu 22.04 Desktop on Blade 3 (see Installing an Operating System on Mixtile Blade 3).
Connected Blade 3 to the Internet.
Connected Blade 3 to a monitor.
Installed the Hailo AI accelerator to Blade 3 as follows:

Note:

To avoid insufficient power supply, it’s recommended that you install the OS first before installing the Hailo AI accelerator.

Setting up Hailo environments

To integrate a Hailo AI accelerator with Blade 3, install HailoRT, PCIe Driver, and TAPPAS.

Installing HailoRT and PCIe Driver

Install dkms:

sudo apt-get update -y && sudo apt-get install -y dkms

Download HailoRT and PCIe Driver to a desired directory:

wget https://downloads.mixtile.com/doc-files/hailo/hailort-pcie-driver_4.19.0_all.deb \
https://downloads.mixtile.com/doc-files/hailo/hailort_4.19.0_arm64.deb

Install HailoRT and PCIe Driver:

sudo apt install ./hailort-pcie-driver_4.19.0_all.deb ./hailort_4.19.0_arm64.deb

If messages below are prompted, input y:

Do you wish to activate hailort service? (required for most pyHailoRT use cases) [y/N]:
Do you wish to use DKMS? [Y/n]:

Reboot Blade 3.

Verify if the Hailo AI accelerator is recognized by the system:

hailortcli fw-control identify

If you see an output similar to the one below, the Hailo AI accelerator is recognized successfully:

Executing on device: 0002:21:00.0
Identifying board
Control Protocol Version: 2
Firmware Version: 4.19.0 (release,app,extended context switch buffer)
Logger Version: 0
Board Name: Hailo-8
Device Architecture: HAILO8L
Serial Number: HLDDLBB242602797
Part Number: HM21LB1C2LAE
Product Name: HAILO-8L AI ACC M.2 B+M KEY MODULE EXT TMP

Installing TAPPAS

TAPPAS is Hailo’s set of full application examples, implementing pipeline elements and pre-trained AI tasks. You can install it as follows:

Install dependencies:

sudo apt-get install -y rsync ffmpeg x11-utils python3-dev python3-pip python3-setuptools python3-virtualenv python-gi-dev \
libgirepository1.0-dev gcc-12 g++-12 cmake git libzmq3-dev librga-dev libopencv-dev python3-opencv libcairo2-dev libgirepository1.0-dev \
libgstreamer1.0-dev libgstreamer-plugins-base1.0-dev libgstreamer-plugins-bad1.0-dev gstreamer1.0-plugins-base gstreamer1.0-plugins-good \
gstreamer1.0-plugins-bad gstreamer1.0-plugins-ugly gstreamer1.0-libav gstreamer1.0-tools gstreamer1.0-x gstreamer1.0-alsa gstreamer1.0-gl \
gstreamer1.0-gtk3 gstreamer1.0-qt5 gstreamer1.0-pulseaudio python-gi-dev python3-gi python3-gi-cairo gir1.2-gtk-3.0

Install TAPPAS:
```
git clone https://github.com/hailo-ai/tappas -b v3.29.0
cd tappas
./install.sh --skip-hailort
```
Note:
1. The installation may take about an hour to complete.
2. Enter the password when prompted.

Verify TAPPAS installation:

gst-inspect-1.0 hailotools

If you see an output similar to the one below, TAPPAS is installed successfully:

mixtile@mixtile-ubuntu:~$ gst-inspect-1.0 hailotools
Plugin Details:
Name                     hailotools
Description              hailo tools plugin
Filename                 /opt/hailo/tappas/lib/aarch64-linux-gnu/gstreamer-1.0/libgsthailotools.so
Version                  3.29.0
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

Running Hailo demos

Download the Hailo demo project to a desired directory (let’s say the home directory):

cd ~
git clone https://github.com/hailo-ai/hailo-rpi5-examples.git
git checkout 123e675 # The main branch currently has an unfixed bug. Checkout to this tested commit as a workaround.
cd hailo-rpi5-examples

Set up environments:
```
source setup_env.sh
```
Install dependencies:
```
pip install -r requirements.txt
```
Download resources:
```
./download_resources.sh
```
Run the demos below as needed:
Important:
- If you have performed the operations above from remote access such as SSH, before running the demos below, you need to connect Blade 3 to a monitor, open Blade 3’s terminal, and perform steps 1-2 again to set up the environments. Otherwise, errors will occur.
- If you have restarted Blade 3 or opened a new terminal, also perform steps 1-2 again to set up the environments.
1. Object detection (YOLOv6n):
```
python basic_pipelines/detection.py --input resources/detection0.mp4
```
  You should see an output video similar to the one below:
2. Instance segmentation (YOLOv5n):
```
python basic_pipelines/instance_segmentation.py --input resources/detection0.mp4
```
  You should see an output video similar to the one below:
3. Pose estimation (YOLOv8s pose):
```
python basic_pipelines/pose_estimation.py --input resources/detection0.mp4
```
  You should see an output video similar to the one below: