Analysis of the Application Efficiency of TensorFlow and PyTorch in Convolutional Neural Network

被引：28

作者：

Novac, Ovidiu-Constantin ^{[1
]}

Chirodea, Mihai Cristian ^{[1
]}

Novac, Cornelia Mihaela ^{[2
]}

Bizon, Nicu ^{[3
]}

Oproescu, Mihai ^{[3
]}

Stan, Ovidiu Petru ^{[4
]}

Gordan, Cornelia Emilia ^{[5
]}

机构：

[1] Univ Oradea, Elect Engn & Informat Technol Fac, Dept Comp & Informat Technol, Oradea 410087, Romania

[2] Univ Oradea, Elect Engn & Informat Technol Fac, Dept Elect Engn, Oradea 410087, Romania

[3] Univ Pitesti, Fac Elect Telecommun & Comp Sci, Dept Elect Comp & Elect Engn, Pitesti 110040, Romania

[4] Tech Univ Cluj Napoca, Fac Automat & Comp Sci, Dept Automat, Cluj Napoca 400114, Romania

[5] Univ Oradea, Elect Engn & Informat Technol Fac, Dept Elect & Telecommun, Oradea 410087, Romania

来源：

SENSORS | 2022年 / 22卷 / 22期

关键词：

convolutional neural network; TensorFlow; PyTorch; network training; network design;

D O I：

10.3390/s22228872

中图分类号：

O65 [分析化学];

学科分类号：

070302 ; 081704 ;

摘要：

In this paper, we present an analysis of important aspects that arise during the development of neural network applications. Our aim is to determine if the choice of library can impact the system's overall performance, either during training or design, and to extract a set of criteria that could be used to highlight the advantages and disadvantages of each library under consideration. To do so, we first extracted the previously mentioned aspects by comparing two of the most popular neural network libraries-PyTorch and TensorFlow-and then we performed an analysis on the obtained results, with the intent of determining if our initial hypothesis was correct. In the end, the results of the analysis are gathered, and an overall picture of what tasks are better suited for what library is presented.

引用

页数：23

共 37 条

[1]

Abadi M, 2016, PROCEEDINGS OF OSDI'16: 12TH USENIX SYMPOSIUM ON OPERATING SYSTEMS DESIGN AND IMPLEMENTATION, P265

[2] Detection of a Potato Disease (Early Blight) Using Artificial Intelligence [J].

Afzaal, Hassan ;

Farooque, Aitazaz A. ;

Schumann, Arnold W. ;

Hussain, Nazar ;

McKenzie-Gopsill, Andrew ;

Esau, Travis ;

Abbas, Farhat ;

Acharya, Bishnu .

REMOTE SENSING, 2021, 13 (03) :1-17

[3]

Bai Haoli, 2020, ARXIV

[4]

Burwick T.T., 1994, STANFORD PDP RES M, P1

[5] Machine learning and the physical sciences [J].

Carleo, Giuseppe ;

Cirac, Ignacio ;

Cranmer, Kyle ;

Daudet, Laurent ;

Schuld, Maria ;

Tishby, Naftali ;

Vogt-Maranto, Leslie ;

Zdeborova, Lenka .

REVIEWS OF MODERN PHYSICS, 2019, 91 (04)

[6] Deep Learning on Mobile and Embedded Devices: State-of-the-art, Challenges, and Future Directions [J].

Chen, Yanjiao ;

Zheng, Baolin ;

Zhang, Zihan ;

Wang, Qian ;

Shen, Chao ;

Zhang, Qian .

ACM COMPUTING SURVEYS, 2020, 53 (04)

[7] Evaluation efficiency of hybrid deep learning algorithms with neural network decision tree and boosting methods for predicting groundwater potential [J].

Chen, Yunzhi ;

Chen, Wei ;

Pal, Subodh Chandra ;

Saha, Asish ;

Chowdhuri, Indrajit ;

Adeli, Behzad ;

Janizadeh, Saeid ;

Dineva, Adrienn A. ;

Wang, Xiaojing ;

Mosavi, Amirhosein .

GEOCARTO INTERNATIONAL, 2022, 37 (19) :5564-5584

[8]

Chirodea Mihai Cristian, 2021, 2021 13th International Conference on Electronics, Computers and Artificial Intelligence (ECAI), DOI 10.1109/ECAI52376.2021.9515098

[9] How to Use Machine Learning to Improve the Discrimination between Signal and Background at Particle Colliders [J].

Cid Vidal, Xabier ;

Dieste Maronas, Lorena ;

Dosil Suarez, Alvaro .

APPLIED SCIENCES-BASEL, 2021, 11 (22)

[10]

David R., 2020, ARXIV201008678

← 1 2 3 4 →