cancel
Showing results for 
Search instead for 
Did you mean: 

Error deploying deeplab_v3_mobilenetv2_05_16_320_asppv2_qdq_int8.onnx to STM32N6570-DK.

dev8
Associate

Hi @everyone, 

I’m deploying an AI model on the STM32N6570-DK. The deployment process seems fine — in the command line I see the message:

“Your model deployed. Turn both boot switches to the left and cycle the power.”

However, the issue is that the model is not building in cmd and as well as on STM32CubeIDE. I’ve tried this with 5–10 different models, but every time I get a model build failed error, and the .bin file is not generated.

Any help or suggestions would be greatly appreciated!
Thanks in advance! 


Details:

  • Board: STM32N6570-DK

  • Tools: STM32CubeIDE, STM32Cube.AI, STM32CubeProgrammer.

 

3 REPLIES 3
Julian E.
ST Employee

Hello @dev8,

 

Could you please share an example user_config.yaml you are using and also the output in the CMD that you get.

 

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.

Hello @Julian E. 

I have attached zip file below containing yaml file.

For now the error is this:

"

[INFO] : Setting upper limit of usable GPU memory to 12GBytes.
[INFO] : Running `deployment` operation mode
Error executing job with overrides: []
Traceback (most recent call last):
File "D:\Stm32-AI-Model-Zoo\stm32ai-modelzoo-services\st_zoo\lib\site-packages\mlflow\tracking\registry.py", line 77, in get_store_builder
store_builder = self._registry[scheme]
KeyError: 'd'

During handling of the above exception, another exception occurred:

Traceback (most recent call last):
File "D:\Stm32-AI-Model-Zoo\stm32ai-modelzoo-services\st_zoo\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:\Stm32-AI-Model-Zoo\stm32ai-modelzoo-services\semantic_segmentation\stm32ai_main.py", line 379, in main
mlflow_ini(cfg)
File "D:\Stm32-AI-Model-Zoo\stm32ai-modelzoo-services\common\utils\logs_utils.py", line 67, in mlflow_ini
mlflow.set_experiment(experiment_name)
File "D:\Stm32-AI-Model-Zoo\stm32ai-modelzoo-services\st_zoo\lib\site-packages\mlflow\tracking\fluent.py", line 111, in set_experiment
client = MlflowClient()
File "D:\Stm32-AI-Model-Zoo\stm32ai-modelzoo-services\st_zoo\lib\site-packages\mlflow\tracking\client.py", line 74, in __init__
self._tracking_client = TrackingServiceClient(final_tracking_uri)
File "D:\Stm32-AI-Model-Zoo\stm32ai-modelzoo-services\st_zoo\lib\site-packages\mlflow\tracking\_tracking_service\client.py", line 51, in __init__
self.store
File "D:\Stm32-AI-Model-Zoo\stm32ai-modelzoo-services\st_zoo\lib\site-packages\mlflow\tracking\_tracking_service\client.py", line 55, in store
return utils._get_store(self.tracking_uri)
File "D:\Stm32-AI-Model-Zoo\stm32ai-modelzoo-services\st_zoo\lib\site-packages\mlflow\tracking\_tracking_service\utils.py", line 217, in _get_store
return _tracking_store_registry.get_store(store_uri, artifact_uri)
File "D:\Stm32-AI-Model-Zoo\stm32ai-modelzoo-services\st_zoo\lib\site-packages\mlflow\tracking\_tracking_service\registry.py", line 39, in get_store
return self._get_store_with_resolved_uri(resolved_store_uri, artifact_uri)
File "D:\Stm32-AI-Model-Zoo\stm32ai-modelzoo-services\st_zoo\lib\site-packages\mlflow\tracking\_tracking_service\registry.py", line 48, in _get_store_with_resolved_uri
builder = self.get_store_builder(resolved_store_uri)
File "D:\Stm32-AI-Model-Zoo\stm32ai-modelzoo-services\st_zoo\lib\site-packages\mlflow\tracking\registry.py", line 79, in get_store_builder
raise UnsupportedModelRegistryStoreURIException(
mlflow.tracking.registry.UnsupportedModelRegistryStoreURIException: Model registry functionality is unavailable; got unsupported URI 'D:/Stm32-AI-Model-Zoo/stm32ai-modelzoo-services/semantic_segmentation/src/experiments_outputs/mlruns' for model registry data storage. Supported URI schemes are: ['', 'file', 'databricks', 'databricks-uc', 'http', 'https', 'postgresql', 'mysql', 'sqlite', 'mssql']. See https://www.mlflow.org/docs/latest/tracking.html#storage for how to run an MLflow server against one of the supported backend storage locations.

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

"

Hello @dev8,

 

Did you follow the instructions on how to setup model zoo?

You can find it here:

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

Please make sure to follow exactly what is described in here, especially the version of python being 3.10.

 

You issue seems to be an installation issue. 

 

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.