cancel
Showing results for 
Search instead for 
Did you mean: 

Connecting STM32n6570-DK with YOLO to train AI - Model

qrmjnn
Associate

Hi,
i'm currently working on a school project with the STM32n6570-DK and I'm pretty new into the STM scene. So my project will mainly be an object detection of different objects. The question is not directly about the STM, it's more about how to implement YOLO into STM. I heard something about the stm32-ai-model-zoo but I didn't go to deep into it yet. But is it possible to train a custom dataset with e.g. Google Colab and then implement it into STM or do I need a specific model-zoo file? And last but not least if someone has experience with STM32n6570-DK connected with YOLO, which YOLO version should I use? I heard YOLOv8n isn't that bad but I wanted to hear some more opinions. Hopefully someone can help me.

Thanks for reading!
Best Wishes


1 ACCEPTED SOLUTION

Accepted Solutions
Julian E.
ST Employee

Hi @qrmjnn,

 

I would indeed highly suggest you to look at the ST Model Zoo services: STMicroelectronics/stm32ai-modelzoo-services: AI Model Zoo services for STM32 devices

 

You will need to install it following the readme instructions.

 

This repository allows you to retrain, quantize, evaluate and deploy models easily on the stm32n6 (and some other target).

In the case of object detection, we support these kind of models: stm32ai-modelzoo/object_detection at main · STMicroelectronics/stm32ai-modelzoo

 

I would suggest you get familiar with model zoo and use a yolov2 or yolox first, as it is simplier, then look at how to use and retrain yolov8 or v11 as you will need to also use ultralytics, here is a tutorial for that:

stm32ai-modelzoo-services/object_detection/docs/tuto/How_to_deploy_yolov8_yolov5_object_detection.md at main · STMicroelectronics/stm32ai-modelzoo-services

 

You will see it, but to use model zoo, you edit a yaml file and then use the stm32ai_main.py to run what you described in the yaml.

The model zoo allows you to deploy models on real applications using display and camera. These can be found as standalone here: STM32N6-AI | Software - STMicroelectronics (the GS)

 

So without using model zoo, the task is much more complicated.

 

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.

View solution in original post

1 REPLY 1
Julian E.
ST Employee

Hi @qrmjnn,

 

I would indeed highly suggest you to look at the ST Model Zoo services: STMicroelectronics/stm32ai-modelzoo-services: AI Model Zoo services for STM32 devices

 

You will need to install it following the readme instructions.

 

This repository allows you to retrain, quantize, evaluate and deploy models easily on the stm32n6 (and some other target).

In the case of object detection, we support these kind of models: stm32ai-modelzoo/object_detection at main · STMicroelectronics/stm32ai-modelzoo

 

I would suggest you get familiar with model zoo and use a yolov2 or yolox first, as it is simplier, then look at how to use and retrain yolov8 or v11 as you will need to also use ultralytics, here is a tutorial for that:

stm32ai-modelzoo-services/object_detection/docs/tuto/How_to_deploy_yolov8_yolov5_object_detection.md at main · STMicroelectronics/stm32ai-modelzoo-services

 

You will see it, but to use model zoo, you edit a yaml file and then use the stm32ai_main.py to run what you described in the yaml.

The model zoo allows you to deploy models on real applications using display and camera. These can be found as standalone here: STM32N6-AI | Software - STMicroelectronics (the GS)

 

So without using model zoo, the task is much more complicated.

 

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.