I had problem when I use x-cube-ai from stm32 ai model zoo.

[jeidi]

Hello,

I am using the model from 'STM32 AI Model Zoo' located at 'stm32ai-modelzoo/image_classification/pretrained_models/mobilenetv2/ST_pretrainedmodel_public_dataset/flowers/mobilenet_v2_0.35_128_tl' for image classification.

I have installed and tested the Device Application using the Template Application in X-CUBE-AI 9.0.0.

I verified that the input data is correctly received, and I understand that the output should be quantized integer values according to the quantization results.

However, I have found that all the output values in the first tensor of the model's data_outs are 0.

- 1. Can this happen if I don't use the stm32h747i board?

- 2. Did I misunderstand and write the post process function incorrectly?

Thanks

[MCHTO.1 · Accepted solution]

Hello,

Please note that the model you are using is indeed quantized, but it has float32 output.

In the C code, you need to make sure to handle the output data as float32.

Best Regards.