stm32ai-modelzoo-services-main benchmarking error!

[fanronghua0123456]

[INFO] : Quantization complete.
[INFO] : Evaluating the quantized model using validation_set...
INFO: Created TensorFlow Lite XNNPACK delegate for CPU.
100%|██████████| 36/36 [05:01<00:00, 8.37s/it]
[INFO] : Accuracy of quantized model on validation_set = 98.17%
[INFO] : Evaluation complete.
[INFO] : Using the local download of STM32Cube.AI. Link to download https://www.st.com/en/embedded-software/x-cube-ai.html
[INFO] : Starting the model memory footprints estimation...
[WARN] : STM32Cube.AI installed version 2.1.0 does not match the version specified in user_config.yaml file 10.1.0 !
[INFO] : STM32Cube.AI version 2.1.0 used.
Error executing job with overrides: []
Traceback (most recent call last):
File "C:\st\stm32ai-modelzoo-services-main\.venv\lib\site-packages\clearml\binding\hydra_bind.py", line 230, in _patched_task_function
return task_function(a_config, *a_args, **a_kwargs)
File "C:\st\stm32ai-modelzoo-services-main\image_classification\stm32ai_main.py", line 399, in main
process_mode(mode=mode, configs=cfg, train_ds=train_ds, valid_ds=valid_ds, quantization_ds=quantization_ds,
File "C:\st\stm32ai-modelzoo-services-main\image_classification\stm32ai_main.py", line 315, in process_mode
chain_tqeb(cfg=configs, train_ds=train_ds, valid_ds=valid_ds, quantization_ds=quantization_ds, test_ds=test_ds)
File "C:\st\stm32ai-modelzoo-services-main\image_classification\stm32ai_main.py", line 233, in chain_tqeb
benchmark(cfg=cfg, model_path_to_benchmark=quantized_model_path, credentials=credentials)
File "C:\st\stm32ai-modelzoo-services-main\common\benchmarking\common_benchmark.py", line 58, in benchmark
_stm32ai_benchmark(footprints_on_target=board,
File "C:\st\stm32ai-modelzoo-services-main\common\benchmarking\common_benchmark.py", line 549, in _stm32ai_benchmark
_analyze_footprints(offline=offline, results=cloud_res, stm32ai_output=stm32ai_output, inference_res=inference_res, target_mcu=target_mcu)
File "C:\st\stm32ai-modelzoo-services-main\common\benchmarking\common_benchmark.py", line 80, in _analyze_footprints
with open(os.path.join(stm32ai_output, 'network_report.json'), 'r') as f:
FileNotFoundError: [Errno 2] No such file or directory: 'C:\\st\\stm32ai-modelzoo-services-main\\image_classification\\src\\experiments_outputs\\2025_07_25_09_01_04/stm32ai_files\\network_report.json'

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

进程已结束，退出代码为 1

[fanronghua0123456]

network_report.json file  have not been  created!

[fanronghua0123456]

i append some log in common_benchmark.py.

 # Run generate command locally
 command = f"{path_to_stm32ai} generate --target stm32 -m {model_path} -v 0 --output {stm32ai_output} --workspace {stm32ai_output} --optimization {optimization}"
 # command = f"{path_to_stm32ai} generate --target stm32n6 -m {model_path} --st-neural-art user_neuralart.json"
 print("command00 = {}".format(command))
 args = shlex.split(command, posix="win" not in sys.platform)
 print("command01 = {}".format(command))
 subprocess.run(args, env=new_env, check=True)
 print("command02 = {}".format(command))
except subprocess.CalledProcessError as e:
 raise TypeError(
 f"Received: stm32ai.path_to_stm32ai={path_to_stm32ai}. Please specify a correct path to STM32Cube.AI!") from e

return stm32ai_output

[INFO] : STM32Cube.AI version 2.1.0 used.
command00 = C:/Users/Administrator/STM32Cube/Repository/Packs/STMicroelectronics/X-CUBE-AI/10.1.0/Utilities/windows/stedgeai.exe generate --target stm32 -m ./pretrained_models/best_model.h5 -v 0 --output C:\st\stm32ai-modelzoo-services-main_bak\stm32ai-modelzoo-services-main\image_classification\src\experiments_outputs\2025_07_25_14_33_22/stm32ai_files --workspace C:\st\stm32ai-modelzoo-services-main_bak\stm32ai-modelzoo-services-main\image_classification\src\experiments_outputs\2025_07_25_14_33_22/stm32ai_files --optimization balanced
command01 = C:/Users/Administrator/STM32Cube/Repository/Packs/STMicroelectronics/X-CUBE-AI/10.1.0/Utilities/windows/stedgeai.exe generate --target stm32 -m ./pretrained_models/best_model.h5 -v 0 --output C:\st\stm32ai-modelzoo-services-main_bak\stm32ai-modelzoo-services-main\image_classification\src\experiments_outputs\2025_07_25_14_33_22/stm32ai_files --workspace C:\st\stm32ai-modelzoo-services-main_bak\stm32ai-modelzoo-services-main\image_classification\src\experiments_outputs\2025_07_25_14_33_22/stm32ai_files --optimization balanced
command02 = C:/Users/Administrator/STM32Cube/Repository/Packs/STMicroelectronics/X-CUBE-AI/10.1.0/Utilities/windows/stedgeai.exe generate --target stm32 -m ./pretrained_models/best_model.h5 -v 0 --output C:\st\stm32ai-modelzoo-services-main_bak\stm32ai-modelzoo-services-main\image_classification\src\experiments_outputs\2025_07_25_14_33_22/stm32ai_files --workspace C:\st\stm32ai-modelzoo-services-main_bak\stm32ai-modelzoo-services-main\image_classification\src\experiments_outputs\2025_07_25_14_33_22/stm32ai_files --optimization balanced
Error executing job with overrides: []
Traceback (most recent call last):
File "C:\st\stm32ai-modelzoo-services-main\.venv\lib\site-packages\clearml\binding\hydra_bind.py", line 230, in _patched_task_function
return task_function(a_config, *a_args, **a_kwargs)
File "C:\st\stm32ai-modelzoo-services-main_bak\stm32ai-modelzoo-services-main\image_classification\stm32ai_main.py", line 399, in main
process_mode(mode=mode, configs=cfg, train_ds=train_ds, valid_ds=valid_ds, quantization_ds=quantization_ds,
File "C:\st\stm32ai-modelzoo-services-main_bak\stm32ai-modelzoo-services-main\image_classification\stm32ai_main.py", line 309, in process_mode
benchmark(cfg=configs)
File "C:\st\stm32ai-modelzoo-services-main_bak\stm32ai-modelzoo-services-main\common\benchmarking\common_benchmark.py", line 58, in benchmark
_stm32ai_benchmark(footprints_on_target=board,
File "C:\st\stm32ai-modelzoo-services-main_bak\stm32ai-modelzoo-services-main\common\benchmarking\common_benchmark.py", line 551, in _stm32ai_benchmark
_analyze_footprints(offline=offline, results=cloud_res, stm32ai_output=stm32ai_output, inference_res=inference_res, target_mcu=target_mcu)
File "C:\st\stm32ai-modelzoo-services-main_bak\stm32ai-modelzoo-services-main\common\benchmarking\common_benchmark.py", line 80, in _analyze_footprints
with open(os.path.join(stm32ai_output, 'network_report.json'), 'r') as f:
FileNotFoundError: [Errno 2] No such file or directory: 'C:\\st\\stm32ai-modelzoo-services-main_bak\\stm32ai-modelzoo-services-main\\image_classification\\src\\experiments_outputs\\2025_07_25_14_33_22/stm32ai_files\\network_report.json'

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

[Julian E.]

Hello @fanronghua0123456,

 

Can you share the yaml you used? And the model if possible?

Else, do you see this issue with other models?

 

Have a good day,

Julian

[fanronghua0123456]

Julian E.

Thanks  for your reply,  and  The attachment is my configuration file .I think this is not a model issue, but rather a configuration issue that has caused the absence of the output file "network_report.json"