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
792 stars 130 forks source link

Uint8 model #11

Closed waquey closed 1 year ago

waquey commented 1 year ago

Thanks for the great work. As the tutorial described, the input and output are all of "int8" type.

Is uint8 model supported or we should just convert into int8 instead? Thanks

meenchen commented 1 year ago

Hi @waquey thanks for your interest in our work. Our current implementation only supports int8 models. Please convert your models to int8 in order to use Tinyengine.

meenchen commented 1 year ago

Close due to inactivity. Feel free to reopen.