How to run "validate on target" in with cube-x-ai
- Mark as New
- Bookmark
- Subscribe
- Mute
- Subscribe to RSS Feed
- Permalink
- Email to a Friend
- Report Inappropriate Content
‎2021-10-08 6:55 AM
I am using a Nucleo-F676ZI and trying to run a dnn on the mcu.
I can run the NN using the "application template" but I want to use the "validate on target" in order to obtain runtime without developing the data transfer from the host system to the mcu myself.
Steps to reprocude:
1: MCU selector
2: Use x-cube-ai package with the validation application
3: Add USART communication. Im using ST-Link so the virtual com port should be connected to USART3.
4: Add the network and run analyze / validate on desktop. (works fine)
5: Run validate on target:
Which results in the following error:
Is there anything I am missing ? in order to run "validate on target"
Or any steps to get a detailed error message?
- Labels:
-
X-CUBE-AI
- Mark as New
- Bookmark
- Subscribe
- Mute
- Subscribe to RSS Feed
- Permalink
- Email to a Friend
- Report Inappropriate Content
‎2021-10-12 9:19 AM
There is a bug in X-CUBE-AI 7.0.0 when you try to do automatic validation on the target and you are using STM32CubeMX inside STM32CubeIDE.
2 solutions here:
- Perform automatic validation on the target using the standalone STM32CubeMX
- or Inside STM32CubeIDE, generate the project, compile and flash on the target and then go back to X-CUBE-AI and perform validation on the target without the automatic compilation as you have already done it
Regards
Daniel
In order to give better visibility on the answered topics, please click on 'Accept as Solution' on the reply which solved your issue or answered your question.
- Mark as New
- Bookmark
- Subscribe
- Mute
- Subscribe to RSS Feed
- Permalink
- Email to a Friend
- Report Inappropriate Content
‎2021-10-22 7:28 AM
Thanks for the reply!
I did test both solutions. Unfortunately, both did not work.
Furthermore, I did test other x-cube-ai releases.
It is possible to use the COM port that is directly connected to the ST-Link correct? (USART 3)
Is there any way to get more debug information?
- Mark as New
- Bookmark
- Subscribe
- Mute
- Subscribe to RSS Feed
- Permalink
- Email to a Friend
- Report Inappropriate Content
‎2021-10-22 8:16 AM
You'll find more information in ~/.stm32cubemx/STM32CubeMX.log (in your home directory)
If MX can't launch STM32CubeIDE or in the log it complains about missing .project or .cproject file you can verify that in your standalone STM32CubeMX installation (on Windows C:\Program Files\STMicroelectronics\STM32Cube\STM32CubeMX) you have a third_parties_plugins directory with a jar file named com.st.stm32cube.ide.services,mx.... in it
You can also try to select "Validation" as the application (and not template), and let X-CUBE-AI configure automatically the USART for you.
I've just tried on the same board and it works out of the box with X-CUBE-AI 7.0
In order to give better visibility on the answered topics, please click on 'Accept as Solution' on the reply which solved your issue or answered your question.
- Mark as New
- Bookmark
- Subscribe
- Mute
- Subscribe to RSS Feed
- Permalink
- Email to a Friend
- Report Inappropriate Content
‎2021-10-29 7:27 AM
> You can also try to select "Validation" as the application (and not template), and let X-CUBE-AI configure automatically the USART for you.
How can I set "validation" as the application?
I did only find how to set it in the selection of the x-cube-ai package (image 2)
