how to Profile memory allocation of each layer

mit-han-lab / mcunet

[NeurIPS 2020] MCUNet: Tiny Deep Learning on IoT Devices; [NeurIPS 2021] MCUNetV2: Memory-Efficient Patch-based Inference for Tiny Deep Learning

https://mcunet.mit.edu

MIT License

426 stars 79 forks source link

how to Profile memory allocation of each layer #31

Open BayRanger opened 7 months ago

BayRanger commented 7 months ago

Hey there, In the McuNet paper, it is mentioned that it decreaces the peak memory of the first serveral layers, my question would be how to profile it during the implementation of the experiments.