DTMM: Deploying TinyML Models on Extremely Weak IoT Devices with Pruning
Authors:
- 20 May 2024
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1999-2008
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.Keywords
All Related Versions
This publication has 23 references indexed in Scilit:
- YONO: Modeling Multiple Heterogeneous Neural Networks on Microcontrollers2022
- IoT-based smart triage of Covid-19 suspicious cases in the Emergency Department2020
- DeepAdapter: A Collaborative Deep Learning Framework for the Mobile Web Using Context-Aware Network Pruning2020
- Push the Limit of Acoustic Gesture Recognition2020
- Channel Pruning for Accelerating Very Deep Neural Networks2017
- An implantable low-power ultrasonic platform for the Internet of Medical Things2017
- Thoreau: A subterranean wireless sensing network for agriculture and the environment2017
- Deep Residual Learning for Image Recognition2016
- You Only Look Once: Unified, Real-Time Object Detection2016
- Battery-free sensing platform for wearable devices: The synergy between two feet2016