CSCC: Convolution Split Compression Calculation Algorithm for Deep Neural Network
文献类型：期刊论文
| 作者 | Fan, Shengyu3; Yu, Hui2; Lu, Dianjie3; Liu, Zhiyong1; Liu, Fangai3; Xu, Weizhi3; Jiao, Shuai1 |
| 刊名 | IEEE ACCESS
 |
| 出版日期 | 2019 |
| 卷号 | 7页码:71607-71615 |
| 关键词 | Convolutional neural network sparse matrix vector multiplication neural networks convolution sparse matrices |
| ISSN号 | 2169-3536 |
| DOI | 10.1109/ACCESS.2019.2919554 |
| 英文摘要 | Convolutional Neural Networks (CNNs) have become one of the most successful machine learning techniques for image and video processing. The most computationally intensive part of the CNN is the convolutional layers, which have the multi-channel image and multiple kernels. However, due to the network pruning operation and the application of RELU activation function operation in the training process, numerous zero values are generated in the network. This paper proposes the convolution split compression calculation (CSCC) algorithm, which improves the performance of the convolution layer by utilizing the sparse characteristic of the feature map. In the CSCC algorithm, first, the feature map is directly converted into a sparse matrix of compressed sparse row (CSR) format, which avoids expanding feature map to an intermediate matrix and reduces the memory space consumption. Second, the convolution kernel is converted into a vector. Finally, the convolution result is obtained by the sparse matrix vector multiplication (SpMV). The experimental results show that the CSCC algorithm has a good advantage in computation speed and memory consumption compared with the other convolution algorithms. |
| 资助项目 | NNSF of China[61602285] ; NNSF of China[61602284] ; NNSF of China[61772321] ; NNSF of China[61520106005] ; National Key Research and Development Program of China[2017YFB1010000] ; Shandong Natural Science Foundation[ZR2015FQ009] ; Shandong Natural Science Foundation[ZR2016FP07] ; Shandong Natural Science Foundation[ZR2019MF017] ; Project of Shandong Province Higher Educational Science and Technology Program[J16LN05] |
| WOS研究方向 | Computer Science ; Engineering ; Telecommunications |
| 语种 | 英语 |
| WOS记录号 | WOS:000471033300001 |
| 出版者 | IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC |
| 源URL | [http://119.78.100.204/handle/2XEOYT63/4219]  |
| 专题 | 中国科学院计算技术研究所期刊论文_英文 |
| 通讯作者 | Yu, Hui; Xu, Weizhi |
| 作者单位 | 1.Chinese Acad Sci, Inst Comp Technol, Beijing 100190, Peoples R China 2.Shandong Normal Univ, Sch Business, Jinan 250358, Shandong, Peoples R China 3.Shandong Normal Univ, Sch Informat Sci & Engn, Jinan 250358, Shandong, Peoples R China |
| 推荐引用方式 GB/T 7714 | Fan, Shengyu,Yu, Hui,Lu, Dianjie,et al. CSCC: Convolution Split Compression Calculation Algorithm for Deep Neural Network[J]. IEEE ACCESS,2019,7:71607-71615. |
| APA | Fan, Shengyu.,Yu, Hui.,Lu, Dianjie.,Liu, Zhiyong.,Liu, Fangai.,...&Jiao, Shuai.(2019).CSCC: Convolution Split Compression Calculation Algorithm for Deep Neural Network.IEEE ACCESS,7,71607-71615. |
| MLA | Fan, Shengyu,et al."CSCC: Convolution Split Compression Calculation Algorithm for Deep Neural Network".IEEE ACCESS 7(2019):71607-71615. |
入库方式： OAI收割
来源：计算技术研究所
浏览0
下载0
收藏0
其他版本
除非特别说明，本系统中所有内容都受版权保护，并保留所有权利。