{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T22:24:26Z","timestamp":1777674266636,"version":"3.51.4"},"reference-count":37,"publisher":"MDPI AG","issue":"22","license":[{"start":{"date-parts":[[2022,11,16]],"date-time":"2022-11-16T00:00:00Z","timestamp":1668556800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Sensors"],"abstract":"<jats:p>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\u2019s 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\u2014PyTorch and TensorFlow\u2014and 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.<\/jats:p>","DOI":"10.3390\/s22228872","type":"journal-article","created":{"date-parts":[[2022,11,17]],"date-time":"2022-11-17T06:24:42Z","timestamp":1668666282000},"page":"8872","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":57,"title":["Analysis of the Application Efficiency of TensorFlow and PyTorch in Convolutional Neural Network"],"prefix":"10.3390","volume":"22","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-5472-6611","authenticated-orcid":false,"given":"Ovidiu-Constantin","family":"Novac","sequence":"first","affiliation":[{"name":"Department of Computers and Information Technology, Electrical Engineering and Information Technology Faculty, University of Oradea, 410087 Oradea, Romania"}]},{"given":"Mihai Cristian","family":"Chirodea","sequence":"additional","affiliation":[{"name":"Department of Computers and Information Technology, Electrical Engineering and Information Technology Faculty, University of Oradea, 410087 Oradea, Romania"}]},{"given":"Cornelia Mihaela","family":"Novac","sequence":"additional","affiliation":[{"name":"Department of Electrical Engineering, Electrical Engineering and Information Technology Faculty, University of Oradea, 410087 Oradea, Romania"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9311-7598","authenticated-orcid":false,"given":"Nicu","family":"Bizon","sequence":"additional","affiliation":[{"name":"Department of Electronics, Computers and Electrical Engineering, Faculty of Electronics, Telecommunication, and Computer Science, University of Pitesti, 110040 Pitesti, Romania"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0324-0846","authenticated-orcid":false,"given":"Mihai","family":"Oproescu","sequence":"additional","affiliation":[{"name":"Department of Electronics, Computers and Electrical Engineering, Faculty of Electronics, Telecommunication, and Computer Science, University of Pitesti, 110040 Pitesti, Romania"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2006-9633","authenticated-orcid":false,"given":"Ovidiu Petru","family":"Stan","sequence":"additional","affiliation":[{"name":"Department of Automation, Faculty of Automation and Computer Science, Technical University of Cluj-Napoca, 400114 Cluj-Napoca, Romania"}]},{"given":"Cornelia Emilia","family":"Gordan","sequence":"additional","affiliation":[{"name":"Department of Electronics and Telecommunications, Electrical Engineering and Information Technology Faculty, University of Oradea, 410087 Oradea, Romania"}]}],"member":"1968","published-online":{"date-parts":[[2022,11,16]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","first-page":"1347","DOI":"10.1056\/NEJMra1814259","article-title":"Machine learning in medicine","volume":"380","author":"Rajkomar","year":"2019","journal-title":"N. Engl. J. Med."},{"key":"ref_2","first-page":"1","article-title":"Applications of Artificial Intelligence in Combating COVID-19: A Systematic Review","volume":"7","author":"Enughwure","year":"2020","journal-title":"Open Access Libr. J."},{"key":"ref_3","doi-asserted-by":"crossref","first-page":"045002","DOI":"10.1103\/RevModPhys.91.045002","article-title":"Machine learning and the physical sciences","volume":"91","author":"Carleo","year":"2019","journal-title":"Rev. Mod. Phys."},{"key":"ref_4","doi-asserted-by":"crossref","first-page":"5564","DOI":"10.1080\/10106049.2021.1920635","article-title":"Evaluation efficiency of hybrid deep learning algorithms with neural network decision tree and boosting methods for predicting groundwater potential","volume":"37","author":"Chen","year":"2021","journal-title":"Geocarto Int."},{"key":"ref_5","doi-asserted-by":"crossref","first-page":"100642","DOI":"10.1016\/j.mser.2021.100642","article-title":"Machine learning for predicting thermal transport properties of solids","volume":"146","author":"Qian","year":"2021","journal-title":"Mater. Sci. Eng. R Rep."},{"key":"ref_6","first-page":"1","article-title":"Deep Learning on Mobile and Embedded Devices: State-of-the-Art, Challenges, and Future Directions","volume":"53","author":"Chen","year":"2020","journal-title":"ACM Comput. Surv."},{"key":"ref_7","doi-asserted-by":"crossref","unstructured":"Merone, M., Graziosi, A., Lapadula, V., Petrosino, L., D\u2019Angelis, O., and Vollero, L. (2022). A Practical Approach to the Analysis and Optimization of Neural Networks on Embedded Systems. Sensors, 22.","DOI":"10.3390\/s22207807"},{"key":"ref_8","unstructured":"David, R., Duke, J., Jain, A., Reddi, V., Jeffries, N., Li, J., Kreeger, N., Nappier, I., Natraj, M., and Regev, S. (2020). TensorFlow Lite Micro: Embedded Machine Learning on TinyML Systems. arXiv."},{"key":"ref_9","doi-asserted-by":"crossref","first-page":"16894","DOI":"10.1109\/JIOT.2021.3058587","article-title":"Emotion Recognition for Cognitive Edge Computing Using Deep Learning","volume":"8","author":"Muhammad","year":"2021","journal-title":"IEEE Internet Things J."},{"key":"ref_10","doi-asserted-by":"crossref","first-page":"1137","DOI":"10.1016\/j.jmrt.2021.07.004","article-title":"Machine learning in predicting mechanical behavior of additively manufactured parts","volume":"14","author":"Nasiri","year":"2021","journal-title":"J. Mater. Res. Technol."},{"key":"ref_11","unstructured":"Gao, G., Gao, J., Liu, Q., Wang, Q., and Wang, Y. (2020). CNN-based Density Estimation and Crowd Counting: A Survey. arXiv."},{"key":"ref_12","unstructured":"Bai, H., and Chan, S. (2020). CNN-based Single Image Crowd Counting: Network Design, Loss Function and Supervisory Signal. arXiv."},{"key":"ref_13","doi-asserted-by":"crossref","first-page":"5215","DOI":"10.1007\/s10462-022-10143-2","article-title":"The role of artificial intelligence and machine learning in wireless networks security: Principle, practice and challenges","volume":"55","author":"Waqas","year":"2022","journal-title":"Artif. Intell. Rev."},{"key":"ref_14","doi-asserted-by":"crossref","unstructured":"Jeong, J.-H., Choi, J.-H., Kim, K.-T., Lee, S.-J., Kim, D.-J., and Kim, H.-M. (2021). Multi-Domain Convolutional Neural Networks for Lower-Limb Motor Imagery Using Dry vs. Wet Electrodes. Sensors, 21.","DOI":"10.3390\/s21196672"},{"key":"ref_15","first-page":"2287","article-title":"Stereo matching by training a convolutional neural network to compare image patches","volume":"17","author":"Zbontar","year":"2016","journal-title":"J. Mach. Learn. Res."},{"key":"ref_16","doi-asserted-by":"crossref","first-page":"1231","DOI":"10.1177\/0278364913491297","article-title":"Vision meets robotics: The kitti dataset","volume":"32","author":"Geiger","year":"2013","journal-title":"Int. J. Robot. Res."},{"key":"ref_17","doi-asserted-by":"crossref","first-page":"51","DOI":"10.20544\/HORIZONS.B.04.1.17.P05","article-title":"An overview of the supervised machine learning methods","volume":"4","author":"Nasteski","year":"2017","journal-title":"HORI-ZONS.B"},{"key":"ref_18","unstructured":"Sutskever, I., Martens, J., Dahl, G., and Hinton, G. (2013, January 16\u201321). On the importance of initialization and momentum in deep learning. Proceedings of the 30th International Conference on Machine Learning, Atlanta, GA, USA."},{"key":"ref_19","doi-asserted-by":"crossref","unstructured":"Chirodea, M.C., Novac, O.C., Novac, C.M., Bizon, N., Oproescu, M., and Gordan, C.E. (2021, January 1\u20133). Comparison of TensorFlow and PyTorch in Convolutional Neural Network-based applications. Proceedings of the ECAI 13th International Conference on Electronics, Computers and Artificial Intelligence, ECAI\u20192021, Pite\u0219ti, Romania.","DOI":"10.1109\/ECAI52376.2021.9515098"},{"key":"ref_20","doi-asserted-by":"crossref","unstructured":"Gurney, K. (1997). An Introduction to Neural Networks, UCL (University College London) Press.","DOI":"10.4324\/9780203451519"},{"key":"ref_21","unstructured":"Zhu, X., Lafferty, J., and Rosenfeld, R. (2005). Semi-Supervised Learning with Graphs, Carnegie Mellon University."},{"key":"ref_22","doi-asserted-by":"crossref","first-page":"34","DOI":"10.14569\/IJARAI.2013.020206","article-title":"Comparison of Supervised and Unsupervised Learning Algorithms for Pattern Classification","volume":"2","author":"Sathya","year":"2013","journal-title":"Int. J. Adv. Res. Artif. Intell."},{"key":"ref_23","doi-asserted-by":"crossref","unstructured":"Kaya, V., Tuncer, S., and Baran, A. (2022). Detection and Classification of Different Weapon Types Using Deep Learning. Appl. Sci., 11.","DOI":"10.3390\/app11167535"},{"key":"ref_24","unstructured":"Krishna Sai, B.N., and Sasikala, T. (2019, January 27\u201329). Object Detection and Count of Objects in Image using Tensor Flow Object Detection API. Proceedings of the International Conference on Smart Systems and Inventive Technology, Tirunelveli, India."},{"key":"ref_25","doi-asserted-by":"crossref","unstructured":"Varga, D. (2021). No-Reference Image Quality Assessment with Convolutional Neural Networks and Decision Fusion. Appl. Sci., 12.","DOI":"10.3390\/app12010101"},{"key":"ref_26","doi-asserted-by":"crossref","unstructured":"Stephen, O., Maduh, U.J., and Sain, M. (2022). A Machine Learning Method for Detection of Surface Defects on Ceramic Tiles Using Convolutional Neural Networks. Electronics, 11.","DOI":"10.3390\/electronics11010055"},{"key":"ref_27","doi-asserted-by":"crossref","unstructured":"Li, Y., Zhao, Z., Luo, Y., and Qiu, Z. (2020). Real-Time Pattern-Recognition of GPR Images with YOLO v3 Implemented by Tensorflow. Sensors, 20.","DOI":"10.3390\/s20226476"},{"key":"ref_28","doi-asserted-by":"crossref","unstructured":"Vidal, X.C., Maro\u00f1as, L.D., and Su\u00e1rez, A.D. (2021). How to Use Machine Learning to Improve the Discrimination between Signal and Background at Particle Colliders. Appl. Sci., 11.","DOI":"10.3390\/app112211076"},{"key":"ref_29","doi-asserted-by":"crossref","unstructured":"Yang, B., Ma, J., Yao, X., Cao, W., and Zhu, Y. (2021). Estimation of Leaf Nitrogen Content in Wheat Based on Fusion of Spectral Features and Deep Features from Near Infrared Hyperspectral Imagery. Sensors, 21.","DOI":"10.3390\/s21020613"},{"key":"ref_30","doi-asserted-by":"crossref","unstructured":"Afzaal, H., Farooque, A., Schumann, A., Hussain, N., McKenzie-Gopsill, A., Esau, T., Abbas, F., and Acharya, B. (2021). Detection of a Potato Disease (Early Blight) Using Artificial Intelligence. Remote Sens., 13.","DOI":"10.3390\/rs13030411"},{"key":"ref_31","unstructured":"Gurucharan, M.K. (2022, March 25). TensorFlow vs PyTorch-Convolutional Neural Networks (CNN). Available online: https:\/\/towardsdatascience.com\/tensorflow-vs-pytorch-convolutional-neural-networks-cnn-dd9ca6ddafce."},{"key":"ref_32","first-page":"8024","article-title":"Pytorch: An Imperative Style, High-Performance Deep Learning Library","volume":"Volume 32","author":"Paszke","year":"2019","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref_33","unstructured":"Abadi, M., Barham, P., Chen, J., Chen, Z., Davis, A., Dean, J., Devin, M., Ghemawat, S., Irving, G., and Isard, M. (2016, January 2\u20134). Tensorflow: A system for large-scale machine learning. Proceedings of the 12th USENIX Conference on Operating Systems Design and Implementation, Savannah, GA, USA."},{"key":"ref_34","unstructured":"TensorFlow (2022, May 23). What\u2019s Coming in TensorFlow 2.0. Available online: https:\/\/medium.com\/tensorflow\/whats-coming-in-tensorflow-2-0-d3663832e9b8."},{"key":"ref_35","first-page":"9","article-title":"On Loss Functions for Deep Neural Networks in Classification","volume":"25","author":"Janocha","year":"2017","journal-title":"Schedae Inform."},{"key":"ref_36","unstructured":"Burwick, T.T. Neural Network Construction via Back-Propagation. Talk Presented at Stanford PDP Research Meeting, 23 June 1994, Stanford University."},{"key":"ref_37","unstructured":"Kinghorn, D. (2022, October 13). TitanXp vs GTX1080Ti for Machine Learning. Puget Systems. Available online: https:\/\/www.pugetsystems.com\/labs\/hpc\/TitanXp-vs-GTX1080Ti-for-Machine-Learning-937\/."}],"container-title":["Sensors"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/1424-8220\/22\/22\/8872\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,11]],"date-time":"2025-10-11T01:19:39Z","timestamp":1760145579000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/1424-8220\/22\/22\/8872"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,11,16]]},"references-count":37,"journal-issue":{"issue":"22","published-online":{"date-parts":[[2022,11]]}},"alternative-id":["s22228872"],"URL":"https:\/\/doi.org\/10.3390\/s22228872","relation":{},"ISSN":["1424-8220"],"issn-type":[{"value":"1424-8220","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022,11,16]]}}}