基于Vitis AI的语义分割网络加速器研究与实现  

Research and Implementation of Semantic Segmentation Network Accelerator Based on Vitis AI

作　　者：李慧琳 柴志雷 Li Huilin;Chai Zhilei(School of Artificial Intelligence and Computer Science,Jiangnan University,Wuxi 214122,China;Jiangsu Provincial Engineering Laboratory of Pattern Recognition and Computational Intelligence)

机构地区：[1]江南大学人工智能与计算机学院,无锡214122 [2]江苏省模式识别与计算智能工程实验室

出　　处：《单片机与嵌入式系统应用》2022年第7期17-20,25,共5页Microcontrollers & Embedded Systems

基　　金：国家自然科学基金资助项目(61972180)。

摘　　要：本文基于Xilinx Vitis AI对语义分割网络U Net进行网络定点化、深度学习处理单元DPU定制、软硬件协同优化等加速方法,最终在Xilinx ZCU102异构平台上实现了语义分割加速器的设计,在较低的精度损失下降低硬件资源消耗,完成了整个U Net网络的软硬件系统开发。实验结果表明,整个U Net网络硬件加速器的处理帧率可达42 fps,证明了该神经网络加速方案的有效性。In the paper,based on Xilinx Vitis AI,the semantic segmentation network U Net is implemented with network fixed point,deep learning processing unit DPU customization,software and hardware collaborative optimization and other acceleration methods.Finally,the design of the semantic segmentation accelerator is implemented on the Xilinx ZCU102 heterogeneous platform.The hardware resource consumption is reduced with low precision loss,and the software and hardware system development of the entire U Net network is completed.The experimental results show that the processing frame rate of the entire U Net network hardware accelerator can reach 42 fps,which shows the effectiveness of the neural network acceleration scheme.

关 键 词：现场可编程门阵列 深度学习处理单元 语义分割 Vitis AI 卷积神经网络 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]