Skip to main content
Associate II
Aug 24, 2024 8:57 PM UTC
Solved

model zoo Object detection

Hello,

I want to implement an application for detecting items in the kitchen on an STM32-H747i-DISCO board. I installed Python 3.10.2, TensorFlow 2.8, CUDA 11.7, and cuDNN v8.8.1. After installing the model zoo , I tried running the command in  Command Prompt python stm32ai_main.py , from this path " ..\stm32ai-modelzoo\object_detection\src".  But I encountered the attached error

I
This topic has been closed for replies.
Laurent FOLLIOT
Laurent FOLLIOTBest answer
ST Employee
Sep 2, 2024 8:27 AM UTC

Hello,
As this is path related issue, could you create a new virtual environment either with Conda or python?
This should avoid such issues.
Thanks & Regards,

​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.

5 replies

Laurent FOLLIOT
ST Employee
Aug 28, 2024 9:26 AM UTC

Hello,
Could you share your yaml file please?
We do not reproduce the issue as this time on last model zoo version.
Regards,

​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.
MH24Author
Associate II
Aug 28, 2024 2:17 PM UTC

Hello,

Attached is the yaml file

Thank you 

Laurent FOLLIOT
ST Employee
Aug 28, 2024 2:32 PM UTC

Thanks,
Do you confirm that you cloned the repository from GitHub, without code modification and that preprocess.py file is well cloned in src/preprocessing folder? 

​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.
MH24Author
Associate II
Sep 1, 2024 9:03 AM UTC

Hello,

yes I confirm

Laurent FOLLIOT
Laurent FOLLIOTBest answer
ST Employee
Sep 2, 2024 8:27 AM UTC

Hello,
As this is path related issue, could you create a new virtual environment either with Conda or python?
This should avoid such issues.
Thanks & Regards,

​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.