2025-07-08 3:15 AM
Hi everyone,
I’m currently working on a project to detect and decode barcodes. So far, I’ve trained a st_yolox model and successfully deployed it on the board for detection.
Now, for the decoding part, I have an algorithm that works perfectly on my PC. I would like to deploy this algorithm on the board and was wondering if it’s possible to use the NPU to accelerate the decoding process.
Until now, I’ve only seen examples of deep learning models being accelerated using the NPU. Are there any examples or documentation showing how a general algorithm (non-DL based) can leverage the NPU?
Thanks.
2025-07-08 5:21 AM - edited 2025-07-08 7:02 AM
Hello @athern27,
It is a great idea but sadly it is not available, and it is also not planned.
The NPU is mainly used for CNN acceleration via the use of the ST Edge AI Core.
I will still keep your request to promote the need internally.
For your information, you can take a look at the STM32 Image Processing Library (IPL) which is a C software library of image processing and computer vision functionalities enabling to accelerate the development of vision applications on STM32 microcontrollers.
You can find all more information about our overall offer regarding AI here:
Also note that we have a partner named Irida Labs that propose off the shelf algorithms that could interest you as they have an offer for the use case you are describing.
Have a good day,
Julian