DTMM: Deploying TinyML Models on Extremely Weak IoT Devices with Pruning

TL;DR

DTMM is a library that enables efficient deployment of pruned TinyML models on extremely weak IoT devices like microcontrollers, addressing the challenge of model compression and runtime efficiency.

Contribution

The paper introduces DTMM, a comprehensive system with pruning and optimization techniques tailored for deploying TinyML models on low-end IoT devices, filling a gap in existing solutions.

Findings

Significant reduction in model size with minimal accuracy loss.

Improved runtime performance on microcontroller units.

Compatibility with commercial ML frameworks.

Abstract

DTMM is a library designed for efficient deployment and execution of machine learning models on weak IoT devices such as microcontroller units (MCUs). The motivation for designing DTMM comes from the emerging field of tiny machine learning (TinyML), which explores extending the reach of machine learning to many low-end IoT devices to achieve ubiquitous intelligence. Due to the weak capability of embedded devices, it is necessary to compress models by pruning enough weights before deploying. Although pruning has been studied extensively on many computing platforms, two key issues with pruning methods are exacerbated on MCUs: models need to be deeply compressed without significantly compromising accuracy, and they should perform efficiently after pruning. Current solutions only achieve one of these objectives, but not both. In this paper, we find that pruned models have great potential for efficient deployment and execution on MCUs. Therefore, we propose DTMM with pruning unit selection, pre-execution pruning optimizations, runtime acceleration, and post-execution low-cost storage to fill the gap for efficient deployment and execution of pruned models. It can be integrated into commercial ML frameworks for practical deployment, and a prototype system has been developed. Extensive experiments on various models show promising gains compared to state-of-the-art methods.