Neural networks on microcontrollers: saving memory at inference via operator reordering
This addresses memory limitations for edge devices using microcontrollers, but it is incremental as it builds on existing compression methods.
The paper tackles the problem of deploying neural networks on memory-constrained microcontrollers by proposing operator reordering to save memory at inference, demonstrating a reduction that enables deployment on an MCU with 512KB SRAM.
Designing deep learning models for highly-constrained hardware would allow imbuing many edge devices with intelligence. Microcontrollers (MCUs) are an attractive platform for building smart devices due to their low cost, wide availability, and modest power usage. However, they lack the computational resources to run neural networks as straightforwardly as mobile or server platforms, which necessitates changes to the network architecture and the inference software. In this work, we discuss the deployment and memory concerns of neural networks on MCUs and present a way of saving memory by changing the execution order of the network's operators, which is orthogonal to other compression methods. We publish a tool for reordering operators of TensorFlow Lite models and demonstrate its utility by sufficiently reducing the memory footprint of a CNN to deploy it on an MCU with 512KB SRAM.