Difference between revisions of "Edge AI SDK/User Guide 300"

From ESS-WIKI
Jump to: navigation, search
(change "not using" to "do not use")
Line 1: Line 1:
 +
<h1>Installation</h1>
  
−
= Installation =
+
<h2>System Requirements</h2>
  
 +
<ul>
 +
<li>The installation of RTX-A5000 on Intel x86_64 requires 30 GB of Disk Space.</li>
 +
<li>The installation of GenAI on Intel 12~13th CPU requires 30 GB of Disk Space and 16 GB physical Memory.</li>
 +
<li>The installation of GenAI on Jetson AGX Orin requires 25 GB of Disk Space and 16 GB physical Memory.</li>
 +
</ul>
  
 +
<p>&nbsp;</p>
  
 +
<h2>Install</h2>
  
−
== System Requirements ==
+
<p><b><span style="color:#e74c3c;"><span style="font-size:larger;">NOTE:</span></span></b></p>
  
−
*The installation of RTX-A5000 on Intel x86_64 requires 30 GB of Disk Space.
+
<p><span style="color:#e74c3c;"><b>* Do NOT&nbsp;Use&nbsp;(sudo su or sudo ) to install</b></span></p>
−
*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.
 
  
−
&nbsp;
+
<p><span style="color:#e74c3c;"><b>* An active Internet connection is required</b>.</span></p>
  
−
== Install ==
+
<p><b><span style="color:#e74c3c;">* Don&#39;t &quot;apt upgrade&quot; before installation</span></b></p>
  
−
'''<span style="color:#e74c3c;"><span style="font-size:larger;">NOTE:</span></span>'''
+
<pre>
 +
$tar zxvf Edge_AI_SDK-installer-&lt;version&gt;.tar.gz
 +
$./Edge_AI_SDK-installer.run
 +
</pre>
  
−
<span style="color:#e74c3c;">'''* Not Using (sudo su or sudo ) to install'''</span>
+
<p><img _fck_mw_filename="EAS-installer-run-s1.png" _fck_mw_origimgheight="533" _fck_mw_origimgwidth="786" alt="EAS-installer-run-s1.png" src="/wiki/images/7/79/EAS-installer-run-s1.png" style="vertical-align:middle;" title="EAS-installer-run-s1.png" width="600" /></p>
  
−
<span style="color:#e74c3c;">'''* An active Internet connection is required'''.</span>
+
<ul>
 +
<li>License Aggreement</li>
 +
</ul>
  
−
'''<span style="color:#e74c3c;">* Don't "apt upgrade" before installation</span>'''
+
<pre class="_fck_mw_lspace">
−
<pre>$tar zxvf Edge_AI_SDK-installer-<version>.tar.gz
+
<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" />
−
$./Edge_AI_SDK-installer.run
 
 
</pre>
 
</pre>
  
−
[[File:EAS-installer-run-s1.png|600px|EAS-installer-run-s1.png]]
+
<ul>
 +
<li>System Information ( by target platform )</li>
 +
</ul>
  
−
*License Aggreement
+
<pre class="_fck_mw_lspace">
 +
<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" />
 +
</pre>
  
−
[[File:EAS Install s2.png|600px|EAS Install s2.png]]
+
<ul>
 +
<li>Select AI Accelerator SDK&nbsp;</li>
 +
</ul>
  
−
*System Information ( by target platform )
+
<p><img _fck_mw_filename="Installer-3.0.0-p2.png" _fck_mw_origimgheight="533" _fck_mw_origimgwidth="786" alt="Installer-3.0.0-p2.png" src="/wiki/images/d/da/Installer-3.0.0-p2.png" style="vertical-align:middle;" title="Installer-3.0.0-p2.png" width="600" /></p>
  
−
[[File:Installer-3.0.0-p1.png|600px|Installer-3.0.0-p1.png]]
+
<ul>
 +
<li>Select GenAI SDK&nbsp;</li>
 +
</ul>
  
−
*Select AI Accelerator SDK&nbsp;  
+
<p><img _fck_mw_filename="Installer-3.0.0-p3.png" _fck_mw_origimgheight="533" _fck_mw_origimgwidth="786" alt="Installer-3.0.0-p3.png" src="/wiki/images/b/b0/Installer-3.0.0-p3.png" style="vertical-align:middle;" title="Installer-3.0.0-p3.png" width="600" /></p>
  
−
[[File:Installer-3.0.0-p2.png|600px|Installer-3.0.0-p2.png]]
+
<p>&nbsp;</p>
  
−
*Select GenAI SDK&nbsp;
+
<h2>Activation</h2>
  
−
[[File:Installer-3.0.0-p3.png|600px|Installer-3.0.0-p3.png]]
+
<ul>
 +
<li>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.&nbsp;</li>
 +
</ul>
  
−
&nbsp;
+
<p><img _fck_mw_filename="EAS-Activataion-S1.png" _fck_mw_origimgheight="655" _fck_mw_origimgwidth="1120" alt="EAS-Activataion-S1.png" src="/wiki/images/7/79/EAS-Activataion-S1.png" style="vertical-align:middle;" title="EAS-Activataion-S1.png" width="600" /></p>
  
−
== Activation ==
+
<p><br />
 +
&nbsp;</p>
  
−
*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.&nbsp;
+
<ul>
 +
<li>License agreement.&nbsp;Please review EULA and then press the Activation button if the content is agreed.</li>
 +
</ul>
  
−
[[File:EAS-Activataion-S1.png|600px|EAS-Activataion-S1.png]]
+
<p><img _fck_mw_filename="EAS-Activataion-S2.png" _fck_mw_origimgheight="655" _fck_mw_origimgwidth="1120" alt="EAS-Activataion-S2.png" src="/wiki/images/8/8f/EAS-Activataion-S2.png" style="vertical-align:middle;" title="EAS-Activataion-S2.png" width="600" /></p>
  
−
<br/> &nbsp;
+
<p><br />
 +
* Activation&nbsp;Code: If it&rsquo;s available to access internet, a dialog will pop up to ask you to enter a token for activation.</p>
  
−
*License agreement.&nbsp;Please review EULA and then press the Activation button if the content is agreed.  
+
<p><img _fck_mw_filename="EAS-Activataion-S3.png" _fck_mw_origimgheight="655" _fck_mw_origimgwidth="1120" alt="EAS-Activataion-S3.png" src="/wiki/images/7/7d/EAS-Activataion-S3.png" style="vertical-align:middle;" title="EAS-Activataion-S3.png" width="600" /></p>
  
−
[[File:EAS-Activataion-S2.png|600px|EAS-Activataion-S2.png]]
+
<p><br />
 +
&nbsp;</p>
  
−
<br/> * Activation&nbsp;Code: If it’s available to access internet, a dialog will pop up to ask you to enter a token for activation.
+
<h2>Uninstall</h2>
  
−
[[File:EAS-Activataion-S3.png|600px|EAS-Activataion-S3.png]]
+
<pre>
−
 
+
cd /opt/Advantech/EdgeAISuite
−
<br/> &nbsp;
 
−
 
 
−
== Uninstall ==
 
−
<pre>cd /opt/Advantech/EdgeAISuite
 
  
 
./unInstall.sh</pre>
 
./unInstall.sh</pre>
  
−
&nbsp;
+
<p>&nbsp;</p>
  
−
= Quick Guide =
+
<h1>Quick Guide</h1>
  
−
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&nbsp;GPU, and provides runtime results inferenced with ML.
+
<p>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&nbsp;GPU, and provides runtime results inferenced with ML.</p>
  
−
Dduble click the icon ( in the red box )&nbsp;on the Destop to start the Edge AI SDK App.
+
<p>Dduble click the icon ( in the red box )&nbsp;on the Destop to start the Edge AI SDK App.</p>
  
−
[[File:EdgeAISDK StartApp.jpg|600px|Step1.png]]
+
<p><img _fck_mw_filename="EdgeAISDK StartApp.jpg" _fck_mw_origimgheight="649" _fck_mw_origimgwidth="1150" alt="Step1.png" src="/wiki/images/5/5d/EdgeAISDK_StartApp.jpg" style="vertical-align:middle;" title="Step1.png" width="600" /></p>
  
−
== How to Quickly Start Vision AI ==
+
<h2>How to Quickly Start Vision AI</h2>
  
−
Step 1. Go to the “Quick Start (Vision)”&nbsp;page, as shown below.
+
<p>Step 1. Go to the &ldquo;Quick Start (Vision)&rdquo;&nbsp;page, as shown below.</p>
  
−
[[File:EAS-UserGuide-Vision-1.png|600px|EAS-UserGuide-Vision-1.png]]
+
<pre class="_fck_mw_lspace">
 +
<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" />
 +
</pre>
  
−
&nbsp;
+
<p>&nbsp;</p>
  
−
Step 2. Choose one application you want to activate and then confirm inference info, as shown below.
+
<p>Step 2. Choose one application you want to activate and then confirm inference info, as shown below.</p>
  
−
( 1. Object detection, 2. Face detection, 3. Person detection, 4. Pose estimation )
+
<p>( 1. Object detection, 2. Face detection, 3. Person detection, 4. Pose estimation )</p>
  
−
[[File:EAS-UserGuide-Vision-2.png|600px|EAS-UserGuide-Vision-2.png]]
+
<pre class="_fck_mw_lspace">
 +
<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" />
 +
</pre>
  
−
&nbsp;
+
<p>&nbsp;</p>
  
−
Step 3. Choose your video source which could be video clips or the USB Camera, as shown below.
+
<p>Step 3. Choose your video source which could be video clips or the USB Camera, as shown below.</p>
  
−
'''Video&nbsp;'''<span style="color:#c0392b;">( Note: .MP4 only )</span>
+
<p><b>Video&nbsp;</b><span style="color:#c0392b;">( Note: .MP4 only )</span></p>
  
−
[[File:EAS-UserGuide-Vision-3.png|600px|EAS-UserGuide-Vision-3.png]] &nbsp;
+
<p><img _fck_mw_filename="EAS-UserGuide-Vision-3.png" _fck_mw_origimgheight="655" _fck_mw_origimgwidth="1120" alt="EAS-UserGuide-Vision-3.png" src="/wiki/images/7/7a/EAS-UserGuide-Vision-3.png" style="vertical-align:middle;" title="EAS-UserGuide-Vision-3.png" width="600" /> &nbsp;</p>
  
−
'''or USB Camera&nbsp;'''
+
<p><b>or USB Camera&nbsp;</b></p>
  
−
[[File:EAS-UserGuide-Vision-4.png|600px|EAS-UserGuide-Vision-4.png]]
+
<p><img _fck_mw_filename="EAS-UserGuide-Vision-4.png" _fck_mw_origimgheight="655" _fck_mw_origimgwidth="1120" alt="EAS-UserGuide-Vision-4.png" src="/wiki/images/7/72/EAS-UserGuide-Vision-4.png" style="vertical-align:middle;" title="EAS-UserGuide-Vision-4.png" width="600" /></p>
  
−
&nbsp;
+
<p>&nbsp;</p>
  
−
Step 4. Choose one of the acceleration chipsets to execute selected inference application, as shown below.
+
<p>Step 4. Choose one of the acceleration chipsets to execute selected inference application, as shown below.</p>
  
−
( <span style="color:#c0392b;">Note:&nbsp; The available accelerator chipsets&nbsp;depend on your AI system&nbsp;and accelerator card.</span> )
+
<p>( <span style="color:#c0392b;">Note:&nbsp; The available accelerator chipsets&nbsp;depend on your AI system&nbsp;and accelerator card.</span> )</p>
  
−
[[File:EAS-UserGuide-Vision-5.png|600px|EAS-UserGuide-Vision-5.png]] &nbsp;
+
<p><img _fck_mw_filename="EAS-UserGuide-Vision-5.png" _fck_mw_origimgheight="655" _fck_mw_origimgwidth="1120" alt="EAS-UserGuide-Vision-5.png" src="/wiki/images/e/e7/EAS-UserGuide-Vision-5.png" style="vertical-align:middle;" title="EAS-UserGuide-Vision-5.png" width="600" /> &nbsp;</p>
  
−
Step 5. Another window will pop up to show the AI inference, as shown below.
+
<p>Step 5. Another window will pop up to show the AI inference, as shown below.</p>
  
−
[[File:Objection Detect.png|600px|Objection Detect.png]]
+
<p><img _fck_mw_filename="Objection Detect.png" _fck_mw_origimgheight="1071" _fck_mw_origimgwidth="1866" alt="Objection Detect.png" src="/wiki/images/7/73/Objection_Detect.png" style="vertical-align:middle;" title="Objection Detect.png" width="600" /></p>
  
−
=== Object Detection ===
+
<h3>Object Detection</h3>
  
−
'''Object Detection'''&nbsp;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.
+
<p><b>Object Detection</b>&nbsp;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.</p>
  
−
&nbsp;
+
<p>&nbsp;</p>
  
−
[[File:Objection Detect.png|600px|Objection Detect.png]]
+
<p><img _fck_mw_filename="Objection Detect.png" _fck_mw_origimgheight="1071" _fck_mw_origimgwidth="1866" alt="Objection Detect.png" src="/wiki/images/7/73/Objection_Detect.png" style="vertical-align:middle;" title="Objection Detect.png" width="600" /></p>
  
−
=== Person Detection ===
+
<h3>Person Detection</h3>
  
−
Person Detection is based on&nbsp;'''object detection&nbsp;'''systems that can "detect human classification," i.e., have the data and training to classify the detected object as human. Person detection&nbsp;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.
+
<p>Person Detection is based on&nbsp;<b>object detection&nbsp;</b>systems that can &quot;detect human classification,&quot; i.e., have the data and training to classify the detected object as human. Person detection&nbsp;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.</p>
  
−
[[File:Person Detect.png|600px|Person Detect.png]]
+
<p><img _fck_mw_filename="Person Detect.png" _fck_mw_origimgheight="1071" _fck_mw_origimgwidth="1866" alt="Person Detect.png" src="/wiki/images/9/9d/Person_Detect.png" style="vertical-align:middle;" title="Person Detect.png" width="600" /></p>
  
−
=== Face Detection ===
+
<h3>Face Detection</h3>
  
−
'''Facial Detection&nbsp;'''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.
+
<p><b>Facial Detection&nbsp;</b>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.</p>
  
−
[[File:Face Detect.png|600px|Face Detect.png]]
+
<p><img _fck_mw_filename="Face Detect.png" _fck_mw_origimgheight="1071" _fck_mw_origimgwidth="1866" alt="Face Detect.png" src="/wiki/images/3/36/Face_Detect.png" style="vertical-align:middle;" title="Face Detect.png" width="600" /></p>
  
−
=== Pose Estimation ===
+
<h3>Pose Estimation</h3>
  
−
'''Pose Estimation'''&nbsp;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.
+
<p><b>Pose Estimation</b>&nbsp;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.</p>
  
−
[[File:Pose Detect.png|600px|Pose Detect.png]]
+
<p><img _fck_mw_filename="Pose Detect.png" _fck_mw_origimgheight="1071" _fck_mw_origimgwidth="1866" alt="Pose Detect.png" src="/wiki/images/3/39/Pose_Detect.png" style="vertical-align:middle;" title="Pose Detect.png" width="600" /></p>
  
−
== How to Quickly Start GenAI ==
+
<h2>How to Quickly Start GenAI</h2>
  
−
Step 1. Go to the “Quick Start (GenAI)”&nbsp;page, as shown below.
+
<p>Step 1. Go to the &ldquo;Quick Start (GenAI)&rdquo;&nbsp;page, as shown below.</p>
  
−
[[File:EAS-UserGuide-GenAI-1.png|600px|EAS-UserGuide-GenAI-1.png]]
+
<p><img _fck_mw_filename="EAS-UserGuide-GenAI-1.png" _fck_mw_origimgheight="655" _fck_mw_origimgwidth="1120" alt="EAS-UserGuide-GenAI-1.png" src="/wiki/images/3/37/EAS-UserGuide-GenAI-1.png" style="vertical-align:middle;" title="EAS-UserGuide-GenAI-1.png" width="600" /></p>
  
−
&nbsp; Step 2. Choose application (chatbot) , as shown below.
+
<p>&nbsp; Step 2. Choose application (chatbot) , as shown below.</p>
  
−
[[File:EAS-UserGuide-GenAI-2.png|600px|EAS-UserGuide-GenAI-2.png]]
+
<p><img _fck_mw_filename="EAS-UserGuide-GenAI-2.png" _fck_mw_origimgheight="655" _fck_mw_origimgwidth="1120" alt="EAS-UserGuide-GenAI-2.png" src="/wiki/images/a/a3/EAS-UserGuide-GenAI-2.png" style="vertical-align:middle;" title="EAS-UserGuide-GenAI-2.png" width="600" /></p>
  
−
&nbsp; Step 3. Choose one of the acceleration chipsets to execute selected chatbot application, as shown below.
+
<p>&nbsp; Step 3. Choose one of the acceleration chipsets to execute selected chatbot application, as shown below.</p>
  
−
[[File:EAS-UserGuide-GenAI-4.png|600px|EAS-UserGuide-GenAI-4.png]]
+
<p><img _fck_mw_filename="EAS-UserGuide-GenAI-4.png" _fck_mw_origimgheight="655" _fck_mw_origimgwidth="1120" alt="EAS-UserGuide-GenAI-4.png" src="/wiki/images/2/2f/EAS-UserGuide-GenAI-4.png" style="vertical-align:middle;" title="EAS-UserGuide-GenAI-4.png" width="600" /></p>
  
−
&nbsp; Step 4. Another window will pop up to show the chatbot , as shown below.
+
<p>&nbsp; Step 4. Another window will pop up to show the chatbot , as shown below.</p>
  
−
[[File:EAS-UserGuide-GenAI-5.png|600px|EAS-UserGuide-GenAI-5.png]]
+
<p><img _fck_mw_filename="EAS-UserGuide-GenAI-5.png" _fck_mw_origimgheight="812" _fck_mw_origimgwidth="910" alt="EAS-UserGuide-GenAI-5.png" src="/wiki/images/5/5b/EAS-UserGuide-GenAI-5.png" style="vertical-align:middle;" title="EAS-UserGuide-GenAI-5.png" width="600" /></p>
  
−
&nbsp;
+
<p>&nbsp;</p>
  
−
== Monitor AI System Performance ==
+
<h2>Monitor AI System Performance</h2>
  
−
Go to the “System Monitoring” page. This page shows payload and temperature for each chipset, as shown below.
+
<p>Go to the &ldquo;System Monitoring&rdquo; page. This page shows payload and temperature for each chipset, as shown below.</p>
  
−
[[File:System-info-1.png|600px|System-info-1.png]]
+
<pre class="_fck_mw_lspace">
 +
<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" />
 +
</pre>
  
 +
<p>&nbsp;</p>
  
−
== Evaluate the Benchmark Performance ==
+
<h2>Evaluate the Benchmark Performance</h2>
  
−
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.
+
<p>Go to the &ldquo;System Monitoring&rdquo; page and select Visoin. Click the &ldquo;Run&rdquo; button to evaluate each chipset performance and wait for a few seconds to get FPS results, as shown below.</p>
  
−
[[File:Benchmark-vison.png|600px|Benchmark-vison.png]]
+
<p><img _fck_mw_filename="Benchmark-vison.png" _fck_mw_origimgheight="655" _fck_mw_origimgwidth="1120" alt="Benchmark-vison.png" src="/wiki/images/c/cb/Benchmark-vison.png" style="vertical-align:middle;" title="Benchmark-vison.png" width="600" /></p>
  
−
&nbsp; 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.
+
<p>&nbsp; Go to the &ldquo;System Monitoring&rdquo; page and select GenAI. Click the &ldquo;Run&rdquo; button to evaluate each chipset performance and wait for a few seconds to get tokens results, as shown below.</p>
  
−
[[File:Benchmark-genai.png|600px|Benchmark-genai.png]]
+
<p><img _fck_mw_filename="Benchmark-genai.png" _fck_mw_origimgheight="655" _fck_mw_origimgwidth="1120" alt="Benchmark-genai.png" src="/wiki/images/a/a2/Benchmark-genai.png" style="vertical-align:middle;" title="Benchmark-genai.png" width="600" /></p>

Revision as of 06:49, 20 August 2024

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

<img _fck_mw_filename="EAS-installer-run-s1.png" _fck_mw_origimgheight="533" _fck_mw_origimgwidth="786" alt="EAS-installer-run-s1.png" src="/wiki/images/7/79/EAS-installer-run-s1.png" style="vertical-align:middle;" title="EAS-installer-run-s1.png" width="600" />

  • 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 

<img _fck_mw_filename="Installer-3.0.0-p2.png" _fck_mw_origimgheight="533" _fck_mw_origimgwidth="786" alt="Installer-3.0.0-p2.png" src="/wiki/images/d/da/Installer-3.0.0-p2.png" style="vertical-align:middle;" title="Installer-3.0.0-p2.png" width="600" />

  • Select GenAI SDK 

<img _fck_mw_filename="Installer-3.0.0-p3.png" _fck_mw_origimgheight="533" _fck_mw_origimgwidth="786" alt="Installer-3.0.0-p3.png" src="/wiki/images/b/b0/Installer-3.0.0-p3.png" style="vertical-align:middle;" title="Installer-3.0.0-p3.png" width="600" />

 

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. 

<img _fck_mw_filename="EAS-Activataion-S1.png" _fck_mw_origimgheight="655" _fck_mw_origimgwidth="1120" alt="EAS-Activataion-S1.png" src="/wiki/images/7/79/EAS-Activataion-S1.png" style="vertical-align:middle;" title="EAS-Activataion-S1.png" width="600" />


 

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

<img _fck_mw_filename="EAS-Activataion-S2.png" _fck_mw_origimgheight="655" _fck_mw_origimgwidth="1120" alt="EAS-Activataion-S2.png" src="/wiki/images/8/8f/EAS-Activataion-S2.png" style="vertical-align:middle;" title="EAS-Activataion-S2.png" width="600" />


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

<img _fck_mw_filename="EAS-Activataion-S3.png" _fck_mw_origimgheight="655" _fck_mw_origimgwidth="1120" alt="EAS-Activataion-S3.png" src="/wiki/images/7/7d/EAS-Activataion-S3.png" style="vertical-align:middle;" title="EAS-Activataion-S3.png" width="600" />


 

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.

<img _fck_mw_filename="EdgeAISDK StartApp.jpg" _fck_mw_origimgheight="649" _fck_mw_origimgwidth="1150" alt="Step1.png" src="/wiki/images/5/5d/EdgeAISDK_StartApp.jpg" style="vertical-align:middle;" title="Step1.png" width="600" />

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 )

<img _fck_mw_filename="EAS-UserGuide-Vision-3.png" _fck_mw_origimgheight="655" _fck_mw_origimgwidth="1120" alt="EAS-UserGuide-Vision-3.png" src="/wiki/images/7/7a/EAS-UserGuide-Vision-3.png" style="vertical-align:middle;" title="EAS-UserGuide-Vision-3.png" width="600" />  

or USB Camera 

<img _fck_mw_filename="EAS-UserGuide-Vision-4.png" _fck_mw_origimgheight="655" _fck_mw_origimgwidth="1120" alt="EAS-UserGuide-Vision-4.png" src="/wiki/images/7/72/EAS-UserGuide-Vision-4.png" style="vertical-align:middle;" title="EAS-UserGuide-Vision-4.png" width="600" />

 

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. )

<img _fck_mw_filename="EAS-UserGuide-Vision-5.png" _fck_mw_origimgheight="655" _fck_mw_origimgwidth="1120" alt="EAS-UserGuide-Vision-5.png" src="/wiki/images/e/e7/EAS-UserGuide-Vision-5.png" style="vertical-align:middle;" title="EAS-UserGuide-Vision-5.png" width="600" />  

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

<img _fck_mw_filename="Objection Detect.png" _fck_mw_origimgheight="1071" _fck_mw_origimgwidth="1866" alt="Objection Detect.png" src="/wiki/images/7/73/Objection_Detect.png" style="vertical-align:middle;" title="Objection Detect.png" width="600" />

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.

 

<img _fck_mw_filename="Objection Detect.png" _fck_mw_origimgheight="1071" _fck_mw_origimgwidth="1866" alt="Objection Detect.png" src="/wiki/images/7/73/Objection_Detect.png" style="vertical-align:middle;" title="Objection Detect.png" width="600" />

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.

<img _fck_mw_filename="Person Detect.png" _fck_mw_origimgheight="1071" _fck_mw_origimgwidth="1866" alt="Person Detect.png" src="/wiki/images/9/9d/Person_Detect.png" style="vertical-align:middle;" title="Person Detect.png" width="600" />

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.

<img _fck_mw_filename="Face Detect.png" _fck_mw_origimgheight="1071" _fck_mw_origimgwidth="1866" alt="Face Detect.png" src="/wiki/images/3/36/Face_Detect.png" style="vertical-align:middle;" title="Face Detect.png" width="600" />

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.

<img _fck_mw_filename="Pose Detect.png" _fck_mw_origimgheight="1071" _fck_mw_origimgwidth="1866" alt="Pose Detect.png" src="/wiki/images/3/39/Pose_Detect.png" style="vertical-align:middle;" title="Pose Detect.png" width="600" />

How to Quickly Start GenAI

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

<img _fck_mw_filename="EAS-UserGuide-GenAI-1.png" _fck_mw_origimgheight="655" _fck_mw_origimgwidth="1120" alt="EAS-UserGuide-GenAI-1.png" src="/wiki/images/3/37/EAS-UserGuide-GenAI-1.png" style="vertical-align:middle;" title="EAS-UserGuide-GenAI-1.png" width="600" />

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

<img _fck_mw_filename="EAS-UserGuide-GenAI-2.png" _fck_mw_origimgheight="655" _fck_mw_origimgwidth="1120" alt="EAS-UserGuide-GenAI-2.png" src="/wiki/images/a/a3/EAS-UserGuide-GenAI-2.png" style="vertical-align:middle;" title="EAS-UserGuide-GenAI-2.png" width="600" />

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

<img _fck_mw_filename="EAS-UserGuide-GenAI-4.png" _fck_mw_origimgheight="655" _fck_mw_origimgwidth="1120" alt="EAS-UserGuide-GenAI-4.png" src="/wiki/images/2/2f/EAS-UserGuide-GenAI-4.png" style="vertical-align:middle;" title="EAS-UserGuide-GenAI-4.png" width="600" />

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

<img _fck_mw_filename="EAS-UserGuide-GenAI-5.png" _fck_mw_origimgheight="812" _fck_mw_origimgwidth="910" alt="EAS-UserGuide-GenAI-5.png" src="/wiki/images/5/5b/EAS-UserGuide-GenAI-5.png" style="vertical-align:middle;" title="EAS-UserGuide-GenAI-5.png" width="600" />

 

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.

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

  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.

<img _fck_mw_filename="Benchmark-genai.png" _fck_mw_origimgheight="655" _fck_mw_origimgwidth="1120" alt="Benchmark-genai.png" src="/wiki/images/a/a2/Benchmark-genai.png" style="vertical-align:middle;" title="Benchmark-genai.png" width="600" />

Retrieved from "https://ess-wiki.advantech.com.tw/wiki/index.php?title=Edge_AI_SDK/User_Guide_300&oldid=36697"