DAPart: An Online DRL-based Adaptive Partition Framework for DNN Inference Acceleration and Energy Conservation in Edge Computing
An online Deep Reinforcement Learning (DRL) based adaptive partition method to dynamically determine optimal partitioning decision so as to jointly accelerate DNN inference and mitigate energy consumption is developed.
Shu-Bin Zhang, Junrong Ma, Kai-Kai Chi et al.
· ACM transactions on sensor n... · 0 citations