Please use this identifier to cite or link to this item: https://hdl.handle.net/20.500.11851/8612
Full metadata record
DC FieldValueLanguage
dc.contributor.authorSever M.-
dc.contributor.authorOgut S.-
dc.date.accessioned2022-07-30T16:43:34Z-
dc.date.available2022-07-30T16:43:34Z-
dc.date.issued2021-
dc.identifier.citationSever, M., & Öğüt, S. (2021, November). A Performance Study Depending on Execution Times of Various Frameworks in Machine Learning Inference. In 2021 15th Turkish National Software Engineering Symposium (UYMS) (pp. 1-5). IEEE.en_US
dc.identifier.isbn9781665410700-
dc.identifier.urihttps://doi.org/10.1109/UYMS54260.2021.9659677-
dc.identifier.urihttps://hdl.handle.net/20.500.11851/8612-
dc.description15th Turkish National Software Engineering Symposium, UYMS 2021 -- 17 November 2021 through 19 November 2021 -- -- 176220en_US
dc.description.abstractThis work is intended to compare the latency of various frameworks in machine learning inference through an average power calculation model. This model is created in terms of a 2-layer neural network with PyTorch, in Python. Then, it is converted to a traced Torch Script module and also to ONNX file format. Afterwards, the C++ front-end is used for the inference process. The traced model is run with Libtorch on CPU and GPU, the ONNX file is run with ONNX Runtime on both CPU and GPU and it is also run with TensorRT on GPU. The inference execution times for 100 trials are averaged for all cases and it is realized that TensorRT with ONNX file format significantly outperforms its counterparts as expected. Hence, this work highlights the performance of TensorRT in machine learning inference and sheds light into the future by proposing several extensions. © 2021 IEEE.en_US
dc.language.isoenen_US
dc.publisherInstitute of Electrical and Electronics Engineers Inc.en_US
dc.relation.ispartof2021 Turkish National Software Engineering Symposium, UYMS 2021 - Proceedingsen_US
dc.rightsinfo:eu-repo/semantics/closedAccessen_US
dc.subjectinferenceen_US
dc.subjectmachine learningen_US
dc.subjectONNX Runtimeen_US
dc.subjectoptimizationen_US
dc.subjectTensorRTen_US
dc.subjectAverage poweren_US
dc.subjectFile formatsen_US
dc.subjectInferenceen_US
dc.subjectMachine-learningen_US
dc.subjectONNX runtimeen_US
dc.subjectOptimisationsen_US
dc.subjectPerformance studyen_US
dc.subjectPower calculationen_US
dc.subjectRuntimesen_US
dc.subjectTensorrten_US
dc.subjectMachine learningen_US
dc.titleA Performance Study Depending on Execution Times of Various Frameworks in Machine Learning Inferenceen_US
dc.typeConference Objecten_US
dc.departmentFakülteler, Mühendislik Fakültesi, Bilgisayar Mühendisliği Bölümüen_US
dc.departmentFaculties, Faculty of Engineering, Department of Computer Engineeringen_US
dc.identifier.wosWOS:000813101100003en_US
dc.identifier.scopus2-s2.0-85124794100en_US
dc.institutionauthorSever, Murat-
dc.identifier.doi10.1109/UYMS54260.2021.9659677-
dc.authorscopusid56763681600-
dc.authorscopusid57456912400-
dc.relation.publicationcategoryKonferans Öğesi - Uluslararası - İdari Personel ve Öğrencien_US
item.openairecristypehttp://purl.org/coar/resource_type/c_18cf-
item.grantfulltextnone-
item.fulltextNo Fulltext-
item.openairetypeConference Object-
item.cerifentitytypePublications-
item.languageiso639-1en-
Appears in Collections:Bilgisayar Mühendisliği Bölümü / Department of Computer Engineering
Scopus İndeksli Yayınlar Koleksiyonu / Scopus Indexed Publications Collection
WoS İndeksli Yayınlar Koleksiyonu / WoS Indexed Publications Collection
Show simple item record



CORE Recommender

WEB OF SCIENCETM
Citations

1
checked on Mar 23, 2024

Page view(s)

90
checked on Mar 25, 2024

Google ScholarTM

Check




Altmetric


Items in GCRIS Repository are protected by copyright, with all rights reserved, unless otherwise indicated.