Deploying the image classification model on the STM32N6570-DK got stuck, seeking help.

[oet]

Hello everyone,

I followed the following tutorial to deploy, but the compilation got stuck and didn't progress for a long time. I interrupted the process with Ctrl+C, and the window log is as follows. Can anyone help me figure out what's going on?

https://github.com/STMicroelectronics/stm32ai-modelzoo-services/blob/main/image_classification/deployment/README_STM32N6.md

logs：

Windows PowerShell
版权所有（C） Microsoft Corporation。保留所有权利。

安装最新的 PowerShell，了解新功能和改进！https://aka.ms/PSWindows

PS D:\TEST\stm32ai-modelzoo-services\image_classification\src> python stm32ai_main.py
[INFO] : Setting upper limit of usable GPU memory to 24GBytes.
[INFO] : Running `deployment` operation mode
[INFO] : ClearML config check
[INFO] : The random seed for this simulation is 123
INFO: Created TensorFlow Lite XNNPACK delegate for CPU.
[INFO] : Generating C header file for Getting Started...
loading model.. model_path="../../../stm32ai-modelzoo/image_classification/mobilenetv2/ST_pretrainedmodel_public_dataset/flowers/mobilenet_v2_0.35_128_fft/mobilenet_v2_0.35_128_fft_int8.tflite"
loading conf file.. "../../application_code/image_classification/STM32N6/stmaic_STM32N6570-DK.conf" config="None"
"n6 release" configuration is used
[INFO] : Selected board : "STM32N6570-DK Getting Started Image Classification (STM32CubeIDE)" (stm32_cube_ide/n6 release/stm32n6)
[INFO] : Compiling the model and generating optimized C code + Lib/Inc files: ../../../stm32ai-modelzoo/image_classification/mobilenetv2/ST_pretrainedmodel_public_dataset/flowers/mobilenet_v2_0.35_128_fft/mobilenet_v2_0.35_128_fft_int8.tflite
setting STM.AI tools.. root_dir="", req_version=""
Cube AI Path: "C:\Users\OET\STM32Cube\Repository\Packs\STMicroelectronics\X-CUBE-AI\10.0.0\Utilities\windows\stedgeai.exe".
[INFO] : Offline CubeAI used; Selected tools: 10.0.0 (x-cube-ai pack)
loading conf file.. "../../application_code/image_classification/STM32N6/stmaic_STM32N6570-DK.conf" config="None"
"n6 release" configuration is used
compiling... "mobilenet_v2_0_35_128_fft_int8_tflite" session
model_path : ['../../../stm32ai-modelzoo/image_classification/mobilenetv2/ST_pretrainedmodel_public_dataset/flowers/mobilenet_v2_0.35_128_fft/mobilenet_v2_0.35_128_fft_int8.tflite']
tools : 10.0.0 (x-cube-ai pack)
target : "STM32N6570-DK Getting Started Image Classification (STM32CubeIDE)" (stm32_cube_ide/n6 release/stm32n6)
options : --st-neural-art default@../../application_code/image_classification/STM32N6/Model/user_neuralart.json --input-data-type uint8 --inputs-ch-position chlast --output-data-type float32
Traceback (most recent call last):
File "D:\TEST\stm32ai-modelzoo-services\image_classification\src\stm32ai_main.py", line 421, in <module>
main()
File "C:\Users\OET\AppData\Roaming\Python\Python310\site-packages\hydra\main.py", line 94, in decorated_main
_run_hydra(
File "C:\Users\OET\AppData\Roaming\Python\Python310\site-packages\hydra\_internal\utils.py", line 394, in _run_hydra
_run_app(
File "C:\Users\OET\AppData\Roaming\Python\Python310\site-packages\hydra\_internal\utils.py", line 457, in _run_app
run_and_report(
File "C:\Users\OET\AppData\Roaming\Python\Python310\site-packages\hydra\_internal\utils.py", line 220, in run_and_report
return func()
File "C:\Users\OET\AppData\Roaming\Python\Python310\site-packages\hydra\_internal\utils.py", line 458, in <lambda>
lambda: hydra.run(
File "C:\Users\OET\AppData\Roaming\Python\Python310\site-packages\clearml\binding\hydra_bind.py", line 91, in _patched_hydra_run
return PatchHydra._original_hydra_run(self, config_name, task_function, overrides, *args, **kwargs)
File "C:\Users\OET\AppData\Roaming\Python\Python310\site-packages\hydra\_internal\hydra.py", line 119, in run
ret = run_job(
File "C:\Users\OET\AppData\Roaming\Python\Python310\site-packages\clearml\binding\hydra_bind.py", line 195, in _patched_run_job
result = PatchHydra._original_run_job(*args, **kwargs)
File "C:\Users\OET\AppData\Roaming\Python\Python310\site-packages\hydra\core\utils.py", line 186, in run_job
ret.return_value = task_function(task_cfg)
File "C:\Users\OET\AppData\Roaming\Python\Python310\site-packages\clearml\binding\hydra_bind.py", line 230, in _patched_task_function
return task_function(a_config, *a_args, **a_kwargs)
File "D:\TEST\stm32ai-modelzoo-services\image_classification\src\stm32ai_main.py", line 407, in main
process_mode(mode=mode, configs=cfg, train_ds=train_ds, valid_ds=valid_ds, quantization_ds=quantization_ds,
File "D:\TEST\stm32ai-modelzoo-services\image_classification\src\stm32ai_main.py", line 302, in process_mode
deploy(cfg=configs)
File "D:\TEST\stm32ai-modelzoo-services\image_classification\src\../deployment\deploy.py", line 90, in deploy
stm32ai_deploy_stm32n6(target=board, stlink_serial_number=stlink_serial_number, stm32ai_version=stm32ai_version, c_project_path=c_project_path,
File "D:\TEST\stm32ai-modelzoo-services\image_classification\src\../../common/deployment\common_deploy.py", line 469, in stm32ai_deploy_stm32n6
stmaic_local_call(session)
File "D:\TEST\stm32ai-modelzoo-services\image_classification\src\../../common/deployment\common_deploy.py", line 443, in stmaic_local_call
stmaic.compile(session=session, options=opt, target=session._board_config)
File "D:\TEST\stm32ai-modelzoo-services\image_classification\src\../../common\stm32ai_local\compile.py", line 203, in cmd_compile
err, errorList = run_shell_cmd(cmd_line, logger=logger)
File "D:\TEST\stm32ai-modelzoo-services\image_classification\src\../../common\stm32ai_local\utils.py", line 278, in run_shell_cmd
line = process.stdout.readline() if process.stdout is not None else ''
KeyboardInterrupt
PS D:\TEST\stm32ai-modelzoo-services\image_classification\src>

Any guidance would be greatly appreciated!

Thanks in advance!

[Julian E. · Accepted solution]

Hello @oet ,

I think I know the cause. 

The first time the st edge ai core is used (it is called by model zoo to convert your model to C code), it asks if you agree to share or not information and waits for you tipping y for yes or n for no. But when used inside model zoo, you don't see it.

Please locate "stedgeai" in your pc, open a terminal and run the following command:

./stedgeai generate --model MY_MODEL --target stm32n6 --st-neural-art

And at the end of it, when running the ST Edge AI Core the first time, it asks:

Do you allow statistics to improve the command line ? (y)es / (n)

After saying yes or no, the message never appears again, and model zoo should work.

Similar issue here if you need:

Solved: Re: Deploy an image classification model in STM32N... - STMicroelectronics Community

Let me know if it worked,

Have a good day,

Julian