Version mismatch between generated model and runtime in STM32N6 (1.1.3dev14 vs 1.1.3dev8)

[Rutva Patel]

Hi ST Community,

I need help regarding a version mismatch issue while deploying my AI model on STM32N6570-DK.

Current Environment

I am currently using:

• ST Edge AI Core: v2.2.0-20266 (2adc00962)
• STM32Cube.AI: 10.2.0-RC1

Problem

When I convert/generate my model using the current tools, the generated model version becomes:

• Generated model version: 1.1.3dev14

But my board/application runtime is using:

• Runtime version: 1.1.3dev8

Because of this version mismatch, I am unable to run the model properly.

My Understanding

I think I currently have two possible options:

Option 1

Install an older ST Edge AI version / STM32CubeAI version that generates a model compatible with:

1.1.3dev8

Option 2

Upgrade my runtime/environment on the board so that runtime version becomes:

1.1.3dev14

Questions

I need guidance on the following:

1. Which option is recommended by ST?
2. Where can I find the correct ST Edge AI / STM32CubeAI version that generates models for runtime 1.1.3dev8?
3. How can I upgrade the runtime on STM32N6570-DK from 1.1.3dev8 to 1.1.3dev14?
4. Is runtime upgrade enough, or do other middleware/components also need updates?
5. Is there a compatibility matrix available between:
   • ST Edge AI Core versions
   • STM32CubeAI versions
   • Runtime versions

Additional Context

I am working with the STM32N6 object detection example and trying to deploy my own custom model.

Any guidance on version alignment between model generation tools and runtime would be very helpful.

Thanks in advance.

[Julian E.]

Hello ​@Rutva Patel,

 

I think you use X Cube AI plugin for STM32Cube MX, this is deprecated.

Please use the new desktop app STM32CubeAI Studio: STM32Cube AI Studio- The next-gen stand-alone tool for embedded AI - STMicroelectronics

 

I would also suggest to update the ST Edge AI Core to the latest version.

 

have a good day,

Julian