摘要
Channel pruning can reduce memory consumption and running time with least performance damage,and is one of the most important techniques in network compression.However,existing channel pruning methods mainly focus on the pruning of standard convolutional networks,and they rely intensively on time-consuming fine-tuning to achieve the performance improvement.To this end,we present a novel efficient probability-based channel pruning method for depthwise separable convolutional networks.Our method leverages a new simple yet effective probability-based channel pruning criterion by taking the scaling and shifting factors of batch normalization layers into consideration.A novel shifting factor fusion technique is further developed to improve the performance of the pruned networks without requiring extra time-consuming fine-tuning.We apply the proposed method to five representative deep learning networks,namely MobileNetV1,MobileNetV2,ShuffleNetV1,ShuffleNetV2,and GhostNet,to demonstrate the efficiency of our pruning method.Extensive experimental results and comparisons on publicly available CIFAR10,CIFAR100,and ImageNet datasets validate the feasibility of the proposed method.
作者
Han-Li Zhao
Kai-Jie Shi
Xiao-Gang Jin
Ming-Liang Xu
Hui Huang
Wang-Long Lu
Ying Liu
赵汉理;史开杰;金小刚;徐明亮;黄辉;卢望龙;刘影(College of Computer Science and Artificial Intelligence,Wenzhou University,Wenzhou 325035,China;State Key Laboratory of CAD&CG,Zhejiang University,Hangzhou 310058,China;School of Information Engineering,Zhengzhou University,Zhengzhou 450000,China;Department of Computer Science,Memorial University of Newfoundland,St.John's A1B 3X5,Canada)
基金
the National Natural Science Foundation of China under Grant Nos.62036010 and 62072340
the Zhejiang Provincial Natural Science Foundation of China under Grant Nos.LZ21F020001 and LSZ19F020001
the Open Project Program of the State Key Laboratory of CAD&CG,Zhejiang University under Grant No.A2220.
