Last edited 3 months ago

X-LINUX-AI Starter package: Difference between revisions

Visual
Registered User
m (Reverted edits by Registered User (-) to last revision by Registered User)
Tag: Rollback
Registered User
mNo edit summary
Tag: 2017 source edit
 
(28 intermediate revisions by 4 users not shown)
Line 1: Line 1:
<noinclude>{{ApplicableFor
|MPUs list=STM32MP13x, STM32MP15x, STM32MP25x
|MPUs checklist=STM32MP13x, STM32MP15x, STM32MP25x
}}</noinclude>
==Install from the OpenSTLinux AI package repository==
==Install from the OpenSTLinux AI package repository==
{{Info|The STMicroelectronics packages repository service is provided for evaluation purposes only, its content may  be updated at any time without notice and is therefore not approved for use in production.}}
{{Info|The STMicroelectronics packages repository service is provided for evaluation purposes only, its content may  be updated at any time without notice and is therefore not approved for use in production.}}
Line 9: Line 14:
You can install them individually or by package group.
You can install them individually or by package group.


===Prerequisites===
==Material needed==
To use the X-LINUX-AI OpenSTLinux Expansion Package, choose one of the following materials:
*'''{{Board | type=257F-EV1}}''' + a Sony™ IMX335 5Mpx sensor
*'''{{Board | type=257F-DK}}''' + a Sony™ IMX335 5Mpx sensor
*'''{{Board | type=157F-DK2}}''' + an UVC USB WebCam
*'''{{Board | type=157F-EV1}}''' with the built in camera module: MB1379 (OmniVision OV5640 parallel camera)
*'''{{Board | type=135F-DK}}''' with the built in camera module: MB1897 (GalaxyCore 2145 parallel camera)
 
==Prerequisites==
* Flash the Starter Package on your SDCard
* Flash the Starter Package on your SDCard
::'''For OpenSTLinux {{EcosystemRelease | revision=5.0.0}}:'''
:'''For OpenSTLinux {{EcosystemRelease | revision=6.0.0}}:'''
::::[[Getting_started/STM32MP1_boards/STM32MP157x-DK2/Let%27s_start/Populate_the_target_and_boot_the_image|STM32MP157x-DKx Starter Package procedure]]
::[[:Category:Starter_Package|Select and follow the correct Starter Package procedure based on the board used]]
::::or
:As example:
::::[[Getting_started/STM32MP1_boards/STM32MP157x-EV1/Let%27s_start/Populate_the_target_and_boot_the_image|STM32MP157x-EV1 Starter Package procedure]]
:: [[STM32MP25_Evaluation_boards_-_Starter_Package#Downloading_the_image_and_flashing_it_on_the_board|For STM32MP257x-EV, follow this Starter Package procedure]]
::::or
:: [[STM32MP15_Discovery_kits_-_Starter_Package#Downloading_the_image_and_flashing_it_on_the_board|For STM32MP157x-DK2, follow this Starter Package procedure]]
::::[[Getting_started/STM32MP1_boards/STM32MP135x-DK/Let%27s_start/Populate_the_target_and_boot_the_image|STM32MP135x-DK Starter Package procedure]]
 
* Your board has an internet connection either through the network cable or through a WiFi connection.
* Your board has an internet connection either through the network cable or through a WiFi connection.
{{Info|
{{Info|
If your internet access depends on a proxy server, you should define the http_proxy environment variable with the following command before any <code>apt-*</code> commands:
If your internet access depends on a proxy server, you should define the http_proxy environment variable with the following command before any <code>apt-*</code> commands:
  {{Board$}} export http_proxy&#x003D;'http://<proxy url>:<proxy port>/'
  {{Board$}}export http_proxy&#x003D;'http://<proxy url>:<proxy port>/'
}}
}}


===Configure the AI OpenSTLinux package repository===
==Boot the OpenSTlinux Starter Package==
Once the board is booted, execute the following command in the console in order to configure the AI OpenSTLinux package repository:
At the end of the boot sequence, the demo launcher application appears on the screen.
 
<div class="res-img">
[[File: STM32MP25_launcher_main_menu.png|center|link=|600px|Demo launcher appearance when X-LINUX-AI is not installed]]
</div>
 
==Install the X-LINUX-AI tool ==
Once the board is booted, execute the following command in the console in order to download X-LINUX-AI tool package from OpenSTLinux package repository:


{{InternalInfo| ST employees who would like to download X-LINUX-AI packages by being connected to the internal network will face a cache proxy issue, a workaround is available :  
{{InternalInfo| ST employees who would like to download X-LINUX-AI packages by being connected to the internal network will face a cache proxy issue, a workaround is available:
* export the http_proxy and https_proxy by replacing the @appgw.gnb.st.com by @appgw.sgp.st.com
* export the http_proxy and https_proxy by replacing the @appgw.gnb.st.com by @appgw.sgp.st.com
* modify the date of the board using : date +%y%m%d -s "yyyymmdd" and date +%T -s "hh:mm:ss" (adapt it with the local date and hours)
* modify the date of the board using: date +%y%m%d -s "yyyymmdd" and date +%T -s "hh:mm:ss" (adapt it with the local date and hours)
* get and install the debian following the wiki  below
* get and install the debian following the wiki  below
  }}
  }}
'''For {{EcosystemRelease | revision=5.0.0}}:'''
* Move to the apt archives directory :
{{Board$}} cd /var/cache/apt/archives


*Retrieve the specific package {{X-LINUXRelease/Package | version=latest | package=AI Debian package | request=name}}:
'''For {{EcosystemRelease | revision=6.0.0}}:'''
{{Board$}} wget {{X-LINUXRelease/Package | version=latest | package=AI Debian package | request=url}}{{X-LINUXRelease/Package | version=latest | package=AI Debian package | request=name}}


*Install this package:
*Synchronize the OpenSTLinux package repository.
  {{Board$}} apt-get install ./{{X-LINUXRelease/Package | version=latest | package=AI Debian package | request=name}}
  {{Board$}}apt-get update


{{warning | This command may issue the following warning message (or similar): Can't drop privileges for downloading as file '/home/root/{{X-LINUXRelease/Package | version=latest | package=AI Debian package | request=name}}' couldn't be accessed by user '_apt'. - pkgAcquire::Run (13: Permission denied)
*Install X-LINUX-AI tool package:
You can safely ignore it.}}
{{Board$}}apt-get install x-linux-ai-tool


*Then synchronize the AI OpenSTLinux package repository.
*Synchronize the X-LINUX-AI package repository.
  {{Board$}} apt-get update
  {{Board$}}apt-get update


===Install AI packages===
*Check that X-LINUX-AI is properly installed:
{{Board$}}x-linux-ai -v
X-LINUX-AI version: {{X-LINUXRelease/Revision | revision=latest | name=AI | type=release}}
 
{{info| The x-linux-ai binary (installed in the /usr/bin directory) allows to recover information on the X-LINUX-AI delivery, like version, features, supported applications. It is also used for package management, please refer to the [[ X-LINUX-AI tool suite |dedicated wiki page ]] for more information.}}
 
==Install AI packages==
{{Warning|{{SoftwareLicenseAgreement | distribution=X-LINUX-AI}}}}
{{Warning|{{SoftwareLicenseAgreement | distribution=X-LINUX-AI}}}}


====Install all X-LINUX-AI packages====
===Install X-LINUX-AI demonstration packages===
To get started with X-LINUX-AI, it is recommended to install the X-LINUX-AI demonstration package, which provides all the AI frameworks,
applications examples, tools and utilities optimized for the specific target used.
 
{|
{|
!width="80%"| Command
!width="50%"| Command
!width="20%"| Description
!width="50%"| Description
|-
|-
| <pre>apt-get install packagegroup-x-linux-ai</pre>
| <pre> x-linux-ai -i packagegroup-x-linux-ai-demo </pre>
| Install all the X-LINUX-AI packages (TensorFlow™ Lite, Edge TPU™, application samples and tools)
| Install the X-LINUX-AI demonstration packages which provide AI frameworks, application examples and tools dedicated to the board used.
|}
|}
After having [[#Install the X-LINUX-AI tool|installed the x-linux-ai-tool]] you can install the X-LINUX-AI demonstration packages.
{{Board$}}x-linux-ai -i packagegroup-x-linux-ai-demo
And restart the demo launcher:
{{Board$}}systemctl restart weston-graphical-session.service


<div class="mw-collapsible mw-collapsed">
<div class="mw-collapsible mw-collapsed">
====Install AI framework related packages====
===[OPTIONAL] Going further with X-LINUX-AI package management===
<div class="mw-collapsible-content">
<div class="mw-collapsible-content">
{|
====Install X-LINUX-AI package-group ====
!width="80%"| Command
 
!width="20%"| Description
In addition with the X-LINUX-AI demonstration package, there are also other groups of packages dedicated to providing all the necessary packages and tools for a specific artificial intelligence functionality named "packagegroup".
|-
| <pre>apt-get install packagegroup-x-linux-ai-tflite</pre>
| Install X-LINUX-AI packages related to TensorFlow™ Lite framework (including application samples)
|-
| <pre>apt-get install packagegroup-x-linux-ai-tflite-edgetpu</pre>
| Install X-LINUX-AI packages related to the Coral Edge TPU™ framework (including application samples)
|-
| <pre>apt-get install packagegroup-x-linux-ai-onnxruntime</pre>
| Install X-LINUX-AI packages related to ONNX Runtime™ (including application samples)
|}
</div>
</div>


<div class="mw-collapsible mw-collapsed">
The available packagegroups are the following:
* packagegroup-x-linux-ai-demo: Default packagegroup provinding for X-LINUX-AI expansion package evaluation.
* packagegroup-x-linux-ai-npu: Provide minimal packages to address NN hardware acceleration on NPU for {{Board | type=MP2}}.
* packagegroup-x-linux-ai-<tflite/onnxruntime>: Provide packages and tools dedicated to a specific AI frameworks like TensorFlow Lite and ONNX.
* packagegroup-x-linux-ai: Packagegroup used to install all the packages available in X-LINUX-AI for the target used.


====Install individual packages====
<div class="mw-collapsible-content">
{|
{|
!width="80%"| Command
!width="50%"| Command
!width="20%"| Description
!width="50%"| Description
|-
|-
| <pre>apt-get install libedgetpu2</pre>
| <pre>x-linux-ai -i packagegroup-x-linux-ai-demo</pre>
| Install libedgetpu for Coral Edge TPU™
| Install X-LINUX-AI demonstration packages which provide AI frameworks, application examples and tools dedicated to the board used.
|-
|-
| <pre>apt-get install libcoral2</pre>
| <pre>x-linux-ai -i packagegroup-x-linux-ai-npu</pre>
| Install libcoral API for Coral Edge TPU™
| Install X-LINUX-AI packages allowing to use OpenVX stack for the NPU hardware acceleration (including application samples)
|-
|-
| <pre>apt-get install libtensorflow-lite-tools</pre>
| <pre>x-linux-ai -i packagegroup-x-linux-ai-tflite</pre>
| Install Tensorflow™ Lite utilities
| Install X-LINUX-AI packages related to TensorFlow™ Lite framework (including application samples)
|-
|-
| <pre>apt-get install libtensorflow-lite2</pre>
| <pre>x-linux-ai -i packagegroup-x-linux-ai-onnxruntime</pre>
| Install Tensorflow™ Lite runtime
| Install X-LINUX-AI packages related to ONNX Runtime™ (including application samples)
|-
| <pre>apt-get install python3-libtensorflow-lite</pre>
| Install Python TensorFlow™ Lite inference engine
|-
| <pre>apt-get install python3-pycoral</pre>
| Install Python PyCoral API for Coral Edge TPU™
|-
| <pre>apt-get install tflite-cv-apps-edgetpu-image-classification-c++</pre>
| Install C++ image classification example using Coral Edge TPU™ TensorFlow™ Lite API
|-
| <pre>apt-get install tflite-cv-apps-edgetpu-image-classification-python</pre>
| Install Python image classification example using Coral Edge TPU™ TensorFlow™ Lite API
|-
| <pre>apt-get install tflite-cv-apps-edgetpu-object-detection-c++</pre>
| Install C++  object detection example using Coral Edge TPU™ TensorFlow™ Lite API
|-
|-
| <pre>apt-get install tflite-cv-apps-edgetpu-object-detection-python</pre>
| <pre>x-linux-ai -i packagegroup-x-linux-ai</pre>
| Install Python object detection example using Coral Edge TPU™ TensorFlow™ Lite API
| Install all X-LINUX-AI packages available for the target
|-
| <pre>apt-get install tflite-cv-apps-image-classification-c++</pre>
| Install C++ image classification using TensorFlow™ Lite
|-
| <pre>apt-get install tflite-cv-apps-image-classification-python</pre>
| Install Python image classification example using TensorFlow™ Lite
|-
| <pre>apt-get install tflite-cv-apps-object-detection-c++</pre>
| Install C++ object detection example using TensorFlow™ Lite
|-
| <pre>apt-get install tflite-cv-apps-object-detection-python</pre>
| Install Python object detection example using TensorFlow™ Lite
|-
| <pre>apt-get install tflite-edgetpu-benchmark</pre>
| Install benchmark application for Coral Edge TPU™ models
|-
| <pre>apt-get install tflite-models-coco-ssd-mobilenetv1</pre>
| Install TensorFlow™ Lite COCO SSD Mobilenetv1 model
|-
| <pre>apt-get install tflite-models-coco-ssd-mobilenetv1-edgetpu</pre>
| Install TensorFlow™ Lite COCO SSD Mobilenetv1 model for Coral Edge TPU™
|-
| <pre>apt-get install tflite-models-mobilenetv1</pre>
| Install TensorFlow™ Lite Mobilenetv1 model
|-
| <pre>apt-get install tflite-models-mobilenetv1-edgetpu</pre>
| Install TensorFlow™ Lite Mobilenetv1 model for Coral Edge TPU™
|-
| <pre>apt-get install onnxruntime</pre>
| Install ONNX Runtime™
|-
| <pre>apt-get install onnxruntime-tools</pre>
| Install ONNX Runtime™ utilities
|-
| <pre>apt-get install python3-onnxruntime</pre>
| Install ONNX Runtime™ python API
|-
| <pre>apt-get install onnx-models-coco-ssd-mobilenetv1</pre>
| Install ONNX Runtime™ COCO SSD Mobilenetv1 model
|-
| <pre>apt-get install onnx-models-mobilenet</pre>
| Install ONNX Runtime™ Mobilenetv1 model
|-
| <pre>apt-get install onnx-cv-apps-image-classification-python</pre>
| Install Python image classification example using ONNX Runtime™
|-
| <pre>apt-get install onnx-cv-apps-object-detection-c++</pre>
| Install C++ object detection example using ONNX Runtime™
|-
| <pre>apt-get install onnx-cv-apps-object-detection-python</pre>
| Install Python object detection example using ONNX Runtime™
|}
|}
====Install X-LINUX-AI individual packages ====
To be able to list or manage all the X-LINUX-AI individual packages available please refer to the dedicated [[X-LINUX-AI tool suite]] article
</div>
</div>
</div>
</div>


{{Info|If you need more information about how to use apt-* utilities check the [[Package repository for OpenSTLinux distribution]] article.}}
==Launch an AI application sample==
 
Once the demo launcher is restarted, notice that it is slightly different because new AI application samples have been installed.<br>
==How to use the X-LINUX-AI Expansion Package ==
The demo launcher has the following appearance, and you can navigate into the different screens by using the '''NEXT''' or '''BACK''' buttons.
===Material needed===
To use the X-LINUX-AI OpenSTLinux Expansion Package, choose one of the following materials:
*'''{{Board | type=157F-DK2}}''' + an UVC USB WebCam
*'''{{Board | type=157F-EV1}}''' with the built in camera module : MB1379 (OmniVision OV5640 parallel camera)
*'''{{Board | type=135F-DK}}''' with the built in camera module :  MB1897 (GalaxyCore 2145 parallel camera)
 
Optional:
* '''Coral USB Edge TPU™'''<ref name=edgetpu_url>[https://coral.ai/ Coral Edge TPU]</ref> accelerator
 
===Boot the OpenSTlinux Starter Package===
At the end of the boot sequence, the demo launcher application appears on the screen.


=== For STM32MP25x lines ===
<div class="res-img">
<div class="res-img">
[[File: X-LINUX-AI_demo_launcher_noAI.png|center|link=|600px|Demo launcher appearance when X-LINUX-AI is not installed]]
[[File: X-LINUX-AI_demo_launcher_AI_mp2.png|center|Demo launcher appearance when X-LINUX-AI is installed on MP25x |link=]]
</div>
</div>


===Install the X-LINUX-AI===
=== For STM32MP1 series ===
{{Warning|{{SoftwareLicenseAgreement | distribution=X-LINUX-AI}}}}
After having [[#Configure the AI OpenSTLinux package repository|configured the AI OpenSTLinux package]] you can install the X-LINUX-AI  components.
{{Board$}} apt-get install packagegroup-x-linux-ai
And restart the demo launcher:
{{Board$}} systemctl restart weston-graphical-session.service
 
Check that X-LINUX-AI is properly installed:
{{Board$}} x-linux-ai -v
X-LINUX-AI version: {{X-LINUXRelease/Revision | revision=5.0.0 | name=AI | type=tag}}
 
{{info| With the x-linux-ai binary it is possible to check the X-LINUX-AI version and the supported frameworks/applications. Use x-linux-ai --help for more information.}}
 
===Launch an AI application sample===
Once the demo launcher is restarted, notice that it is slightly different because new AI application samples have been installed.<br>
The demo launcher has the following appearance, and you can navigate into the different screens by using the '''NEXT''' or '''BACK''' buttons.
 
<div class="res-img">
<div class="res-img">
[[File: X-LINUX-AI_demo_launcher_AI.png|center|Demo launcher appearance when X-LINUX-AI is installed |link=]]
[[File: X-LINUX-AI_demo_launcher_AI.png|center|Demo launcher appearance when X-LINUX-AI is installed on MP25x |link=]]
</div>
</div>


The demo launcher now contain AI application samples that are described within dedicated article available in the [[X-LINUX-AI application samples zoo]] page.
The demo launcher now contain AI application samples that are described within dedicated article available in the [[:Category:AI - Application examples | X-LINUX-AI application samples]] page.


===Enjoy running your own NN models===
===Enjoy running your own NN models===
The above examples provide application samples to demonstrate how to execute models easily on the STM32MP1.
The above examples provide application samples to demonstrate how to execute models easily on the STM32MPUs.


You are free to update the C/C++ application or Python scripts for your own purposes, using your own NN models.
You are free to update the C/C++ application or Python scripts for your own purposes, using your own NN models.
Line 220: Line 150:
Source code locations are provided in application sample pages.
Source code locations are provided in application sample pages.


===References===
==References==
<noinclude>
<noinclude>
[[Category:X-LINUX-AI expansion package|01]]
[[Category:X-LINUX-AI expansion package|01]]
{{PublicationRequestId |25195| 2022-11-07 | Page extracted from [[X-LINUX-AI OpenSTLinux Expansion Package]] which was reviewed by TW }}
{{PublicationRequestId |25195| 2022-11-07 | Page extracted from [[X-LINUX-AI OpenSTLinux Expansion Package]] which was reviewed by TW }}
</noinclude>
</noinclude>

Latest revision as of 13:17, 6 December 2024↑

Applicable for STM32MP13x lines, STM32MP15x lines, STM32MP25x lines

1. Install from the OpenSTLinux AI package repository↑

Info white.png Information
The STMicroelectronics packages repository service is provided for evaluation purposes only, its content may be updated at any time without notice and is therefore not approved for use in production.

All the generated X-LINUX-AI packages are available from the OpenSTLinux AI package repository service hosted at the non-browsable URL http://extra.packages.openstlinux.st.com/AI.

This repository contains AI packages that can be simply installed using apt-* utilities, which the same as those used on a Debian system:

  • the main group contains the selection of AI packages whose installation is automatically tested by STMicroelectronics
  • the updates group is reserved for future uses such as package revision update.

You can install them individually or by package group.

2. Material needed↑

To use the X-LINUX-AI OpenSTLinux Expansion Package, choose one of the following materials:

  •  unknown board type identifier + a Sony™ IMX335 5Mpx sensor
  •  unknown board type identifier + a Sony™ IMX335 5Mpx sensor
  • STM32MP157F-DK2 Discovery kit More info green.png + an UVC USB WebCam
  • STM32MP157F-EV1 Evaluation board More info green.png with the built in camera module: MB1379 (OmniVision OV5640 parallel camera)
  • STM32MP135F-DK Discovery kit More info green.png with the built in camera module: MB1897 (GalaxyCore 2145 parallel camera)

3. Prerequisites↑

  • Flash the Starter Package on your SDCard
For OpenSTLinux ecosystem release unknown revision 6.0.0 Warning.png :
Select and follow the correct Starter Package procedure based on the board used
As example:
For STM32MP257x-EV, follow this Starter Package procedure
For STM32MP157x-DK2, follow this Starter Package procedure
  • Your board has an internet connection either through the network cable or through a WiFi connection.
Info white.png Information

If your internet access depends on a proxy server, you should define the http_proxy environment variable with the following command before any apt-* commands: 

export http_proxy='http://<proxy url>:<proxy port>/'

4. Boot the OpenSTlinux Starter Package↑

At the end of the boot sequence, the demo launcher application appears on the screen.

Demo launcher appearance when X-LINUX-AI is not installed

5. Install the X-LINUX-AI tool↑

Once the board is booted, execute the following command in the console in order to download X-LINUX-AI tool package from OpenSTLinux package repository:


For ecosystem release unknown revision 6.0.0 Warning.png :

  • Synchronize the OpenSTLinux package repository.
apt-get update
  • Install X-LINUX-AI tool package:
apt-get install x-linux-ai-tool
  • Synchronize the X-LINUX-AI package repository.
apt-get update
  • Check that X-LINUX-AI is properly installed:
x-linux-ai -v
X-LINUX-AI version: 5.0.0
Info white.png Information
The x-linux-ai binary (installed in the /usr/bin directory) allows to recover information on the X-LINUX-AI delivery, like version, features, supported applications. It is also used for package management, please refer to the dedicated wiki page for more information.

6. Install AI packages↑

Warning white.png Warning
The software package is provided AS IS, and by downloading it, you agree to be bound to the terms of the software license agreement (SLA). The detailed content licenses can be found here.

6.1. Install X-LINUX-AI demonstration packages↑

To get started with X-LINUX-AI, it is recommended to install the X-LINUX-AI demonstration package, which provides all the AI frameworks, applications examples, tools and utilities optimized for the specific target used.

Command Description 
 x-linux-ai -i packagegroup-x-linux-ai-demo
Install the X-LINUX-AI demonstration packages which provide AI frameworks, application examples and tools dedicated to the board used.

After having installed the x-linux-ai-tool you can install the X-LINUX-AI demonstration packages. 

x-linux-ai -i packagegroup-x-linux-ai-demo

And restart the demo launcher: 

systemctl restart weston-graphical-session.service

6.2. [OPTIONAL] Going further with X-LINUX-AI package management↑

7. Launch an AI application sample↑

Once the demo launcher is restarted, notice that it is slightly different because new AI application samples have been installed.
The demo launcher has the following appearance, and you can navigate into the different screens by using the NEXT or BACK buttons.

7.1. For STM32MP25x lines↑

Demo launcher appearance when X-LINUX-AI is installed on MP25x

7.2. For STM32MP1 series↑

Demo launcher appearance when X-LINUX-AI is installed on MP25x

The demo launcher now contain AI application samples that are described within dedicated article available in the X-LINUX-AI application samples page.

7.3. Enjoy running your own NN models↑

The above examples provide application samples to demonstrate how to execute models easily on the STM32MPUs.

You are free to update the C/C++ application or Python scripts for your own purposes, using your own NN models.

Source code locations are provided in application sample pages.

8. References↑


Retrieved from "https://wiki.stmicroelectronics.cn/stm32mpu/index.php?title=X-LINUX-AI_Starter_package&oldid=113783"