InstantNet: Automated Generation and Deployment of Instantaneously Switchable-Precision Networks
TimeWednesday, December 8th1:30pm - 1:52pm PST
Event Type
Research Manuscript
Virtual Programs
Presented In-Person
AI/ML System Design
DescriptionThe promise of Deep Neural Network (DNN) powered Internet of Thing (IoT) devices has motivated a tremendous demand for automated solutions to enable fast development and deployment of efficient (1) DNNs equipped with instantaneous accuracy-efficiency trade-off capability to accommodate the time-varying resources at IoT devices and (2) dataflows to optimize the execution efficiency of DNNs on different devices. Therefore, we propose InstantNet to automatically generate and deploy instantaneously switchable-precision networks which can operate at variable bit-widths. Extensive experiments show that the proposed InstantNet consistently outperforms state-of-the-art designs. All codes will be released upon acceptance.