Implementing generated STM32Cube.AI Developer Cloud model on to STM32H747i-DISCO

[DarrinR1]

Hi,

I'm working on a university project and the goal is to make a top down people system on the STM32H747i-DISCO. I used the STM32Cube.AI Developer Cloud and used one of the premade models for human detection. However, when I downloaded the project and tried to flash it on to the board I see nothing. No errors, no visuals, no feedback at all. This also occured with the firmware files.

Is there anything else I need to do to make this work? I am very new to this.

Any help would be appreciated.

Thanks,

Darrin

[DarrinR1]

To be precise, the model used is "ST_YOLO_LC_V1_192_INT8_OBJECT_DETECTION_COCO_2017.TFLITE"

[fauvarque.daniel]

The best if you want to have a prebuilt application is to look for the getting started applications in the stm32ai model zoo.

https://github.com/STMicroelectronics/stm32ai-modelzoo

The model zoo scripts will use the developer cloud for generation of the c files from the model.

Regards

Daniel

[DarrinR1]

Hi Daniel,

Thanks for the quick reply.

The main issue I'm having is that I'm unable to even figure out how to use the model zoo.

I have tried following the videos on the STM YouTube channel but am still unsure.

[Laurent FOLLIOT]

Hello,

what is your starting point in the model zoo?

You want to retrain a yoloLC? evaluate it on the ST developer cloud? Or deploy it locally?

[DarrinR1]

Hi,

I want to take a model that can accommodate top down people counting and deploy it on the H747i-DISCO board that I own.

I evaluated it on the developer cloud and generated a project. However, I have absolutely no idea where to go next.

Thanks,

Darrin

[DarrinR1]

Simply, what I would like is a program that runs exactly like the PeopleCounting program in the FP-AI-VISION1 pack. However, I would like it trained with a different model to detect people top down rather than side on.