Issues of combining and using two neural network models on the H747I-DISCO board

[HanYi]

Hello,

I am currently working on a project to recognize and classify pet dogs using the H747I-DISCO board. So far, I have successfully deployed both an object detection model and an image classification model on the board using the resources from the stm32aimodelzoo on GitHub, and they are working well individually. However, to improve the accuracy of the model, I would like to combine the two models.

The specific method I am considering involves first using the object detection model to process the detected image information. Then, based on the output of the object detection model, I will crop and resize the image. Finally, the processed image will be handled by the image classification model.

I have the IDE files for both models, and they both run correctly. However, I am unsure how to merge them. Should I simply copy some files from the object detection model to the image classification model? Do I need to adjust any additional parameters, such as the addresses where the model weights are stored? Are there any examples I can follow to learn how to do this?

Thank you very much!

[fauvarque.daniel]

The easiest way is to use STM32CubeMX to create a template for the 2 models.

Basically when you want to integrate 2 models you'll have to pass a different name in the UI or in the command line (--name option) and it will generate files and functions with the name of the network in it.

Regards