Need Help with FCNN Model: Unable to Get Output from Input Data
- Mark as New
- Bookmark
- Subscribe
- Mute
- Subscribe to RSS Feed
- Permalink
- Email to a Friend
- Report Inappropriate Content
‎2025-04-20 7:44 AM
Hello STM Community,
I have a question regarding my FCNN model. My goal is to feed input data into the model and obtain the corresponding output, but I haven’t been successful so far. Could you please assist me with this? Any guidance would be greatly appreciated!
Model Layer Information:
Stm32 Anlyze Show Graph:
- Labels:
-
STM32CubeMX
-
STM32F4 Series
- Mark as New
- Bookmark
- Subscribe
- Mute
- Subscribe to RSS Feed
- Permalink
- Email to a Friend
- Report Inappropriate Content
‎2025-04-22 7:33 AM
Hello @AI_I,
What is your issue exactly? you get an error using cubeAI or stedgeai core CLI?
Can you provide your model (in .zip) or source code please.
Have a good day,
Julian
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
‎2025-04-22 11:38 AM
Hello,
I'm new to CubeAI and would like to use it in one of my projects. I created a simple model (attached as a zip), but when running it on an STM32F4 series processor, I’m not getting any output. I’m not sure if my code is correct. I’d really appreciate it if I could get a basic output from this simple model.
Thank you in advance!
- Mark as New
- Bookmark
- Subscribe
- Mute
- Subscribe to RSS Feed
- Permalink
- Email to a Friend
- Report Inappropriate Content
‎2025-04-23 7:45 AM
Hello @AI_I,
First, your model is correct.
Then, here is what I suggest you to do.
- Open STM32CubeMX
- Select your board
- Activate X Cube AI and select the systemPerformance template.
- Generate the code, build and flash
- Open tera term and you should see an output with some metrics.
For there, you can look at the code.
In the main() you will see a function called cubemx_ai_run or something close to that.
Use the debug option to understand what is being done. Basically, you just need to manage the inputs and outputs, X Cube AI does the rest.
You can also use the application template instead of the systemPerformace.
You will have to once again manage how you collect input and what you want to do with the outputs with functions template already in place.
Here is some documentation that should help you:
https://stedgeai-dc.st.com/assets/embedded-docs/embedded_client_api_legacy.html
The function names may be different, but the idea it the same.
Have a good day,
Julian
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.
