Regarding the Validation of AI Models in ST Cloud

[creeper]

I tried to validate my Keras model on ST Cloud, but there seems to be '' stedgeai analyze --model emotion_model.h5 --st-neural-art custom@/tmp/stm32ai_service/5afbcf71-db0d-4f0d-81a1-3cd5102933d8/profile-2fb440ba-ebb2-486b-b795-d7287b8d6307.json --target stm32n6 --optimize.export_hybrid True --name network --workspace workspace --output output
ST Edge AI Core v2.1.0-20182 a437ed3c9
WARNING: Unsupported keys in the current profile custom are ignored: memory_desc
> memory_desc is not a valid key anymore, use machine_desc instead
E102(CliArgumentError): Cannot use 'keras_dump'-type input files when using Neural Art compiler'' The error.

I hope to verify the STM32N6570DK development board in the cloud, but if I choose the MCU platform, it seems that I cannot choose this development board. If I choose NPU, it seems that there will be the above errors again.

[hamitiya]

Hello @creeper 

STM32N6570-DK with ST Neural-ART accelerator does not support .h5 file, you need to quantize it first or to use another model (.tflite or .onnx).

And yes you are right, actually, only STM32N6570-DK with ST Neural ART is supported. You cannot benchmark STM32N6570-DK + Cortex M55 with ST Edge AI Developer Cloud.

 

Hope it helps.

Best regards,

Yanis

[creeper]

In other words, I can still bechmark .h5 files on Cubemx by connecting to the development board?

[hamitiya]

It should be possible yes, as a regular STM32 MCU (using ARM Cortex-M55 without ST Neural-ART Accelerator)