Edge AI DC custom model with ModelZoo CubeIDE application code

[temilola]

When I generate a model's C code with Edge AI DC, what files do I need to replace in this application code example: https://github.com/STMicroelectronics/stm32ai-modelzoo-services/tree/main/application_code/image_classification/STM32N6 to get the model running? Also do I need to still follow steps 1 & 2 since the model is already generated with Edge AI DC? 

[Julian E.]

Hello @temilola,

 

I am not sure to understand what are the steps 1 & 2 that you are talking about.

You can read this document (for the DK, there is another one for the nucleo).

stm32ai-modelzoo-services/application_code/image_classification/STM32N6/Doc/Deploy-your-tflite-Model-STM32N6570-DK.md at main · STMicroelectronics/stm32ai-modelzoo-services · GitHub

 

In here, the model you got from the Edge AI DC should be equivalent to the first thing done in the first step, the "generate". I am not sure that the default@user_neuralart.json is the same that in the dev cloud. So, I would still suggest to re do this step.

 

If you used the dev cloud to quantize your model, you can download it and start following the steps of the tutorial from there.

 

Have a good day,

Julian.