TedNet: A Pytorch toolkit for tensor decomposition networks

被引：8
|
作者：
Pan, Yu [1 ]
Wang, Maolin [3 ]
Xu, Zenglin [1 ,2 ]
机构：
[1] Harbin Inst Technol Shenzhen, Shenzhen, Peoples R China
[2] Peng Cheng Natl Lab, Shenzhen, Peoples R China
[3] Univ Elect Sci & Technol China, Chengdu, Peoples R China
来源：
NEUROCOMPUTING | 2022年 / 469卷
关键词：
Tensor decomposition networks; Deep neural networks; Tensor networks; Network compression;
D O I：
10.1016/j.neucom.2021.10.064
中图分类号：
TP18 [人工智能理论];
学科分类号：
081104 ; 0812 ; 0835 ; 1405 ;
摘要：
Tensor Decomposition Networks (TDNs) prevail for their inherent compact architectures. To give more researchers a flexible way to exploit TDNs, we present a Pytorch toolkit named TedNet. TedNet implements 5 kinds of tensor decomposition (i.e., CANDECOMP/PARAFAC (CP), Block-Term Tucker (BTT), Tucker-2, Tensor Train (TT) and Tensor Ring (TR)) on traditional deep neural layers, the convolutional layer and the fully-connected layer.By utilizing the basic layers, it is simple to construct a variety of TDNs. TedNet is available at https://github.com/tnbar/tednet. (c) 2021 Elsevier B.V. All rights reserved.
引用
收藏
页码：234 / 238
页数：5
相关论文
共 50 条
  • [1] Performance Evaluation of a Toolkit for Sparse Tensor Decomposition
    Tan, Yiyu
    Imamura, Toshiyuki
    HPDC '18: PROCEEDINGS OF THE 27TH INTERNATIONAL SYMPOSIUM ON HIGH-PERFORMANCE PARALLEL AND DISTRIBUTED COMPUTING: POSTERS/DOCTORAL CONSORTIUM, 2018, : 5 - 6
  • [2] THE PYTORCH-KALDI SPEECH RECOGNITION TOOLKIT
    Ravanelli, Mirco
    Parcollet, Titouan
    Bengio, Yoshua
    2019 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH AND SIGNAL PROCESSING (ICASSP), 2019, : 6465 - 6469
  • [3] tntorch: Tensor Network Learning with PyTorch
    Usvyatsov, Mikhail
    Ballester-Ripoll, Rafael
    Schindler, Konrad
    Journal of Machine Learning Research, 2022, 23
  • [4] TENSOR DECOMPOSITION VIA CORE TENSOR NETWORKS
    Zhang, Jianfu
    Tao, Zerui
    Zhang, Liqing
    Zhao, Qibin
    2021 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH AND SIGNAL PROCESSING (ICASSP 2021), 2021, : 2130 - 2134
  • [5] tntorch: Tensor Network Learning with PyTorch
    Usvyatsov, Mikhail
    Ballester-Ripoll, Rafael
    Schindler, Konrad
    JOURNAL OF MACHINE LEARNING RESEARCH, 2022, 23
  • [6] MobileStyleGAN.pytorch: PyTorch-based toolkit to compress StyleGAN2 model
    Belousov, Sergei
    SOFTWARE IMPACTS, 2021, 10
  • [7] Tensor Decomposition for Multilayer Networks Clustering
    Chen, Zitai
    Chen, Chuan
    Zheng, Zibin
    Zhu, Yi
    THIRTY-THIRD AAAI CONFERENCE ON ARTIFICIAL INTELLIGENCE / THIRTY-FIRST INNOVATIVE APPLICATIONS OF ARTIFICIAL INTELLIGENCE CONFERENCE / NINTH AAAI SYMPOSIUM ON EDUCATIONAL ADVANCES IN ARTIFICIAL INTELLIGENCE, 2019, : 3371 - 3378
  • [8] PyAnomaly: A Pytorch-based Toolkit for Video Anomaly Detection
    Cheng, Yuhao
    Liu, Wu
    Duan, Pengrui
    Liu, Jingen
    Mei, Tao
    MM '20: PROCEEDINGS OF THE 28TH ACM INTERNATIONAL CONFERENCE ON MULTIMEDIA, 2020, : 4473 - 4476
  • [9] Leveraging Features and Networks for Probabilistic Tensor Decomposition
    Rai, Piyush
    Wang, Yingjian
    Carin, Lawrence
    PROCEEDINGS OF THE TWENTY-NINTH AAAI CONFERENCE ON ARTIFICIAL INTELLIGENCE, 2015, : 2942 - 2948
  • [10] Second-Order Networks in PyTorch
    Brooks, Daniel
    Schwander, Olivier
    Barbaresco, Frederic
    Schneider, Jean-Yves
    Cord, Matthieu
    GEOMETRIC SCIENCE OF INFORMATION, 2019, 11712 : 751 - 758
12345