Installation

System Requirements

The installation of RTX-A5000 on Intel x86_64 requires 30 GB of Disk Space.
The installation of GenAI on Intel 12~13th CPU requires 30 GB of Disk Space and 16 GB physical Memory.
The installation of GenAI on Jetson AGX Orin requires 25 GB of Disk Space and 16 GB physical Memory.

Install

NOTE:

* Do NOT Use (sudo su or sudo ) to install

* An active Internet connection is required.

* Don't "apt upgrade" before installation

$tar zxvf Edge_AI_SDK-installer-<version>.tar.gz
$./Edge_AI_SDK-installer.run

License Aggreement

<img _fck_mw_filename="EAS Install s2.png" _fck_mw_origimgheight="482" _fck_mw_origimgwidth="738" alt="EAS Install s2.png" src="/wiki/images/9/97/EAS_Install_s2.png" style="vertical-align:middle;" title="EAS Install s2.png" width="600" />

System Information ( by target platform )

<img _fck_mw_filename="Installer-3.0.0-p1.png" _fck_mw_origimgheight="533" _fck_mw_origimgwidth="786" alt="Installer-3.0.0-p1.png" src="/wiki/images/8/84/Installer-3.0.0-p1.png" style="vertical-align:middle;" title="Installer-3.0.0-p1.png" width="600" />

Select AI Accelerator SDK

Select GenAI SDK

Activation

User Information. Please fill in the required information one by one, especially a correct email. The following activation will need an available email. Then press the Next button to proceed.

License agreement. Please review EULA and then press the Activation button if the content is agreed.

Activation Code: If it’s available to access internet, a dialog will pop up to ask you to enter a token for activation.

Uninstall

cd /opt/Advantech/EdgeAISuite

./unInstall.sh

Quick Guide

Edge AI SDK caters to users who are comfortable with the machine learning (ML) experience. It can quickly evaluate computing performance for the CPU or GPU, and provides runtime results inferenced with ML.

Dduble click the icon ( in the red box ) on the Destop to start the Edge AI SDK App.

How to Quickly Start Vision AI

Step 1. Go to the “Quick Start (Vision)” page, as shown below.

<img _fck_mw_filename="EAS-UserGuide-Vision-1.png" _fck_mw_origimgheight="655" _fck_mw_origimgwidth="1120" alt="EAS-UserGuide-Vision-1.png" src="/wiki/images/5/5d/EAS-UserGuide-Vision-1.png" style="vertical-align:middle;" title="EAS-UserGuide-Vision-1.png" width="600" />

Step 2. Choose one application you want to activate and then confirm inference info, as shown below.

( 1. Object detection, 2. Face detection, 3. Person detection, 4. Pose estimation )

<img _fck_mw_filename="EAS-UserGuide-Vision-2.png" _fck_mw_origimgheight="655" _fck_mw_origimgwidth="1120" alt="EAS-UserGuide-Vision-2.png" src="/wiki/images/a/ac/EAS-UserGuide-Vision-2.png" style="vertical-align:middle;" title="EAS-UserGuide-Vision-2.png" width="600" />

Step 3. Choose your video source which could be video clips or the USB Camera, as shown below.

Video ( Note: .MP4 only )

or USB Camera

Step 4. Choose one of the acceleration chipsets to execute selected inference application, as shown below.

( Note: The available accelerator chipsets depend on your AI system and accelerator card. )

Step 5. Another window will pop up to show the AI inference, as shown below.

Object Detection

Object Detection is a computer vision task in which the goal is to detect and locate objects of interest in an image or video. The task involves identifying the position and boundaries of objects in an image, and classifying the objects into different categories. It forms a crucial part of vision recognition, alongside image classification and retrieval.

Person Detection

Person Detection is based on object detection systems that can "detect human classification," i.e., have the data and training to classify the detected object as human. Person detection is used in many different sectors. These can be listed as security, insurance, nursing, health, and production. Technologies offer opportunities that can significantly increase customer satisfaction.

Face Detection

Facial Detection is the task of making a positive identification of a face in a photo or video image against a pre-existing database of faces. It begins with detection - distinguishing human faces from other objects in the image - and then works on identification of those detected faces.

Pose Estimation

Pose Estimation is a computer vision task where the goal is to detect the position and orientation of a person or an object. Usually, this is done by predicting the location of specific keypoints like hands, head, elbows, etc. in case of Human Pose Estimation.

How to Quickly Start GenAI

Step 1. Go to the “Quick Start (GenAI)” page, as shown below.

Step 2. Choose application (chatbot) , as shown below.

Step 3. Choose one of the acceleration chipsets to execute selected chatbot application, as shown below.

Step 4. Another window will pop up to show the chatbot , as shown below.

Monitor AI System Performance

Go to the “System Monitoring” page. This page shows payload and temperature for each chipset, as shown below.

<img _fck_mw_filename="System-info-1.png" _fck_mw_origimgheight="655" _fck_mw_origimgwidth="1120" alt="System-info-1.png" src="/wiki/images/c/c0/System-info-1.png" style="vertical-align:middle;" title="System-info-1.png" width="600" />

Evaluate the Benchmark Performance

Go to the “System Monitoring” page and select Visoin. Click the “Run” button to evaluate each chipset performance and wait for a few seconds to get FPS results, as shown below.

Go to the “System Monitoring” page and select GenAI. Click the “Run” button to evaluate each chipset performance and wait for a few seconds to get tokens results, as shown below.

Edge AI SDK/User Guide 300

Contents

Installation

System Requirements

Install

Activation

Uninstall

Quick Guide

How to Quickly Start Vision AI

Object Detection

Person Detection

Face Detection

Pose Estimation

How to Quickly Start GenAI

Monitor AI System Performance

Evaluate the Benchmark Performance

Navigation menu

Personal tools

Namespaces

Variants

Views

More

Search

Navigation

Tools