Zobrazeno 1 - 4
of 4
pro vyhledávání: '"Alexandr Rokovyi"'
Autor:
Sergii Stirenko, Vlad Taran, Yuriy Kochura, Oleg Alienin, Yuri Gordienko, Nikita Gordienko, Alexandr Rokovyi
Publikováno v:
Deep Learning: Concepts and Architectures ISBN: 9783030317553
Specialized tensor processing architectures (TPA) targeted for neural network processing has attracted a lot of attention in recent years. The computing complexity of the algorithmically different components of some deep neural networks (DNNs) was co
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::09c62c328b37b7efe5fff65255ea68b9
https://doi.org/10.1007/978-3-030-31756-0_3
https://doi.org/10.1007/978-3-030-31756-0_3
Autor:
Nikita Gordienko, Alexandr Rokovyi, Yuriy Kochura, Yuri Gordienko, Sergii Stirenko, Vlad Taran, Oleg Alienin
Publikováno v:
Advances in Computer Science for Engineering and Education II ISBN: 9783030166205
The impact of the maximally possible batch size (for the better runtime) on performance of graphic processing units (GPU) and tensor processing units (TPU) during training and inference phases is investigated. The numerous runs of the selected deep n
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::781f908c32bd67640f2a3f2eaa3121dd
https://doi.org/10.1007/978-3-030-16621-2_61
https://doi.org/10.1007/978-3-030-16621-2_61
Publikováno v:
Advances in Computer Science for Engineering and Education II ISBN: 9783030166205
Preparation of high-quality datasets for the urban scene understanding is a labor-intensive task, especially, for datasets designed for the autonomous driving applications. The application of the coarse ground truth (GT) annotations of these datasets
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::c4334f1134dac3fe3e69abebfcd607b6
https://doi.org/10.1007/978-3-030-16621-2_17
https://doi.org/10.1007/978-3-030-16621-2_17
Autor:
Alexandr Rokovyi, Yuriy Kochura, Nikita Gordienko, Oleg Alienin, Sergii Stirenko, Vlad Taran, Yuri Gordienko
Publikováno v:
CompSysTech
Semantic image segmentation is one the most demanding task, especially for analysis of traffic conditions for self-driving cars. Here the results of application of several deep learning architectures (PSPNet and ICNet) for semantic image segmentation
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::e389540c9da65a392056b194d15c51ff
http://arxiv.org/abs/1806.01896
http://arxiv.org/abs/1806.01896