Hello, everyone, I have encountered some problems. When I use ART runtime to analyze the uint8 model, I will report an error that the format does not match, and I can pass the analysis by using MCU runtime. Is this normal? In addition, When I run the model through NPU, the output is always NAN. I don't know what caused it and how to solve it. I have configured wake-up SRAM and NPU in RIF, and here is my code and model.
调试输出结果：
Input buffer content check:
Input[0]: -0.121942
Input[1]: 0.582246
Input[2]: -0.000011
Input[3]: -0.000012
Input[4]: -0.000015
Input[5]: -0.000007
Input[6]: 0.005214
Input[7]: -0.008049
Input[8]: -0.001116
Input[9]: 0.007997
Input[10]: 0.251979
Input[11]: -0.014175
Input[12]: 0.232821
Input[13]: 0.217874
Input[14]: 0.043446
Input[15]: 0.241517
Performing inference...
Inference finished. Printing output results:
Output[0]: nan
Output[1]: nan
Output[2]: nan
Output[3]: nan
Output[4]: nan
Output[5]: nan
Output[6]: nan
Output[7]: nan
Output[8]: nan
Output[9]: nan
Output[10]: nan
Output[11]: nan
Output[12]: nan
Output[13]: nan
Output[14]: nan
