Abstract：The Residual Network（ResNet)is widely used for its excellent performance in image classification and object detection.However,due to the high degree of irregularity and complexity of the model structure,deploying the ResNet on mobile terminals is still a challenging task.In this paper,a ResNet accelerator based on Field Programmable Gate Array（FPGA)is designed.Firstly,the k-means clustering algorithm is used to quantify the network parameters in order to reduce the storage requirements of the parameters.Secondly,each computing unit is implemented through pipeline and parallel computing.And reusing the unit of residual calculation reduces the requirement of computing resources.The proposed hardware accelerator can efficiently deploye the ResNet on Zynq-ZCU102 FPGA with 300MHz of clock frequency and 26.43ms of latency.The occupancy rates of the DSP and LUTRAM are 60.4% and 4%,respectively.
林秀男,钱慧. 面向移动终端的残差网络加速器设计[J]. 小型微型计算机系统, 2020, 41(8): 1713-1717.
LIN Xiu-nan,QIAN Hui. Design of Residual Network Accelerator for Mobile Terminals. Journal of Chinese Computer Systems, 2020, 41(8): 1713-1717.
2020, Vol. 41 
