search

mit-han-lab / tinyengine

[NeurIPS 2020] MCUNet: Tiny Deep Learning on IoT Devices; [NeurIPS 2021] MCUNetV2: Memory-Efficient Patch-based Inference for Tiny Deep Learning; [NeurIPS 2022] MCUNetV3: On-Device Training Under 256KB Memory
https://mcunet.mit.edu
MIT License
810 stars 131 forks source link

IDE Compilation Error #31

Closed Zerkclown closed 1 year ago

Zerkclown commented 1 year ago

Currently following the inference tutorial and attempting to build the the VWW demo (step 3 of the tutorial). STM32CubeIDE seems to be unable to fully compile the project. Any suggestions to where the source of the error might lie?

Is it in the Makefile? or could the error have been caused all the way back during the CodeGeneration step? Am I including the wrong version of MCUNet?

image

Zerkclown commented 1 year ago

The issue seems to be caused by incongruence of patchpadding_convolve_s8_kernel3_inputch3_stride2 declaration's and implementation's parameters. An additional parameter (q15_t *kbuf) can be found in the declaration:

https://github.com/mit-han-lab/tinyengine/blob/3e6292e7ab5c24b3011856fac2830863164f2fea/TinyEngine/include/tinyengine_function.h#L154

meenchen commented 1 year ago

Hi @Zerkclown,

Thanks for fixing the issue. I will close this issue since the fix has been merged.