Stm32n657-dk board with Zoo models

[Kumar123]

Dear Team

How can I implement Zoo models on the STM32N657-DK board?

[Julian E.]

Hello @Kumar123,

You have the ST Model Zoo: GitHub - STMicroelectronics/stm32ai-modelzoo: AI Model Zoo for STM32 devices

That contains model that you can use with the ST Model Zoo Services or with the Standalone getting started

ST Model Zoo Services: GitHub - STMicroelectronics/stm32ai-modelzoo-services: AI Model Zoo services for STM32 devices

Standalone getting started: STM32N6-AI | Software - STMicroelectronics

With the ST Model Zoo Services, you can find documentation to retrain a model, quantize a model, evaluate a model, deploy a model etc. You need to edit the user_config.yaml and run the stm32_main.py script.

With the Standalone getting started, you can replace the default model with models from the model zoo. See the doc in /Doc (you will mainly need to convert the model to c and edit the postprocessing).

Have a good day,

Julian

[Kumar123]

Dear Julian

Thank you for your response. I’ve installed the packages, but I’m not familiar with the Model Zoo. I’ve chosen the image_classification example—how do I implement it? Please guide me step by step

GitHub - STMicroelectronics/stm32ai-modelzoo: AI Model Zoo for STM32 devices

GitHub - STMicroelectronics/stm32ai-modelzoo-services: AI Model Zoo services for STM32

 STM32N6-AI | Software - STMicroelectronics

[Julian E.]

Hello @Kumar123,

For image classification, everything is explained in the different readme:

stm32ai-modelzoo-services/image_classification at main · STMicroelectronics/stm32ai-modelzoo-services · GitHub

You will find a link for each operation modes (training, quantization, deployement ect) with step by step guide.

Keep in mind that the way it works is similar. It is always:

1. Edit the user_config.yaml
2. Run stm32ai_main.py

Have a good day,

Julian

[Kumar123]

Dear Julian

Why do we need to edit the user_config.yaml file? If we run the script directly without editing it, will it still work?

[Julian E.]

Hello @Kumar123,

You can edit the yaml to configure what you want to do:

• Select which model to use
• Which operation mode (training, deployment ...)
• other options

Depending on what you do, you will also need to set your path to cubeIDE, ST Edge AI Core etc

Please read the documentation.

Have a good day,

Julian

[Kumar123]

Dear Julian

I run script getting errors in image classification example.

  File "d:\Pavan\AI Software packages\stm32ai-modelzoo-services-main\stm32ai-modelzoo-services-main\image_classification\stm32ai_main.py", line 11, in <module>
    from hydra.core.hydra_config import HydraConfig
ModuleNotFoundError: No module named 'hydra'
PS D:\Pavan\AI Software packages\stm32ai-modelzoo-services-main\stm32ai-modelzoo-services-main\image_classification> 

[avburmel]

Hello. Here is a helpful guide AI:How to use Teachable Machine to create an image classification application on STM32 - stm32mcu

Different board should not be a big problem. I guess you need the stage "3. Porting to a target".

Try to install correct python version(3.9 or 3.10) and correct requirements from requirements.txt.

[Kumar123]

Hi Avburmel

I think the next step is Stage 3: Porting to a target. How do I port to a target? I installed the ModelZoo services and the required packages. I tried the image classification example, but when I run stm32ai_main.py, I get errors. Please check.

PS D:\Micro\stm32ai-modelzoo-services-main\stm32ai-modelzoo-services-main\image_classification> & C:/Users/User/AppData/Local/Programs/Python/Python39/python.exe d:/Micro/stm32ai-modelzoo-services-main/stm32ai-modelzoo-services-main/image_classification/stm32ai_main.py
[INFO] : Setting upper limit of usable GPU memory to 24GBytes.
[INFO] : Running `chain_tqeb` operation mode
Error executing job with overrides: []
Traceback (most recent call last):
  File "C:\Users\User\AppData\Local\Programs\Python\Python39\lib\site-packages\clearml\binding\hydra_bind.py", line 230, in _patched_task_function
    return task_function(a_config, *a_args, **a_kwargs)
  File "d:\Micro\stm32ai-modelzoo-services-main\stm32ai-modelzoo-services-main\image_classification\stm32ai_main.py", line 374, in main
    cfg = get_config(cfg)
  File "d:\Micro\stm32ai-modelzoo-services-main\stm32ai-modelzoo-services-main\image_classification\src\utils\parse_config.py", line 327, in get_config
    parse_dataset_section(cfg.dataset,
  File "d:\Micro\stm32ai-modelzoo-services-main\stm32ai-modelzoo-services-main\image_classification\src\utils\parse_config.py", line 84, in parse_dataset_section
    _check_dataset_paths_and_contents(cfg, mode=mode, mode_groups=mode_groups)
  File "d:\Micro\stm32ai-modelzoo-services-main\stm32ai-modelzoo-services-main\image_classification\src\utils\parse_config.py", line 42, in _check_dataset_paths_and_contents     
    raise FileNotFoundError(f"\nUnable to find the root directory of the {name[:-5]} set\n"
FileNotFoundError:
Unable to find the root directory of the training set
Received path: ./datasets/flower_photos
Please check the 'dataset' section of your configuration file.

Set the environment variable HYDRA_FULL_ERROR=1 for a complete stack trace.

[avburmel]

Hi. I guess you need to download and unzip to "./datasets/flower_photos" flower_photos dataset to train your model.
https://storage.googleapis.com/download.tensorflow.org/example_images/flower_photos.tgz