FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W3173381570> ?p ?o ?g. }

• W3173381570 abstract "One of the purposes of HPC benchmarks is to identify limitations and bottlenecks in hardware. This functionality is particularly influential when assessing performance on emerging tasks, the nature and requirements of which may not yet be fully understood. In this setting, a proper benchmark can steer the design of next generation hardware by properly identifying said requirements, and quicken the deployment of novel solutions. With the increasing popularity of deep learning workloads, benchmarks for this family of tasks have been gaining popularity. Particularly for image based tasks, which rely on the most well established family of deep learning models: Convolutional Neural Networks. Significantly, most benchmarks for CNN use low-resolution and fixed-shape (LR&FS) images. While this sort of inputs have been very successful for certain purposes, they are insufficient for some domains of special interest (e.g., medical image diagnosis or autonomous driving) where one requires higher resolutions and variable-shape (HR&VS) images to avoid loss of information and deformation. As of today, it is still unclear how does image resolution and shape variability affect the nature of the problem from a computational perspective. In this paper we assess the differences between training with LR&FS and HR&VS, as means to justify the importance of building benchmarks specific for the latter. Our results on three different HPC clusters show significant variations in time, resources and memory management, highlighting the differences between LR&FS and HR&VS image deep learning." @default.
• W3173381570 created "2021-07-05" @default.
• W3173381570 creator A5000504787 @default.
• W3173381570 creator A5010831226 @default.
• W3173381570 creator A5035035680 @default.
• W3173381570 creator A5075478782 @default.
• W3173381570 creator A5075755125 @default.
• W3173381570 creator A5082933794 @default.
• W3173381570 date "2021-03-01" @default.
• W3173381570 modified "2023-10-18" @default.
• W3173381570 title "Size & Shape Matters: The Need of HPC Benchmarks of High Resolution Image Training for Deep Learning" @default.
• W3173381570 cites W1527148394 @default.
• W3173381570 cites W1557692423 @default.
• W3173381570 cites W2133564696 @default.
• W3173381570 cites W2168231600 @default.
• W3173381570 cites W2194775991 @default.
• W3173381570 cites W2338908902 @default.
• W3173381570 cites W2555618208 @default.
• W3173381570 cites W2736374171 @default.
• W3173381570 cites W2907965334 @default.
• W3173381570 cites W2913323966 @default.
• W3173381570 cites W2937048311 @default.
• W3173381570 cites W2949507647 @default.
• W3173381570 cites W2952046647 @default.
• W3173381570 cites W2964121744 @default.
• W3173381570 cites W2980030301 @default.
• W3173381570 cites W2981122607 @default.
• W3173381570 cites W2981237538 @default.
• W3173381570 cites W2999032020 @default.
• W3173381570 cites W3036039597 @default.
• W3173381570 cites W3038942628 @default.
• W3173381570 cites W3041159379 @default.
• W3173381570 cites W3045363250 @default.
• W3173381570 cites W3094714191 @default.
• W3173381570 cites W3097751213 @default.
• W3173381570 cites W3130650642 @default.
• W3173381570 cites W3169135813 @default.
• W3173381570 doi "https://doi.org/10.14529/jsfi210103" @default.
• W3173381570 hasPublicationYear "2021" @default.
• W3173381570 type Work @default.
• W3173381570 sameAs 3173381570 @default.
• W3173381570 citedByCount "1" @default.
• W3173381570 countsByYear W31733815702023 @default.
• W3173381570 crossrefType "journal-article" @default.
• W3173381570 hasAuthorship W3173381570A5000504787 @default.
• W3173381570 hasAuthorship W3173381570A5010831226 @default.
• W3173381570 hasAuthorship W3173381570A5035035680 @default.
• W3173381570 hasAuthorship W3173381570A5075478782 @default.
• W3173381570 hasAuthorship W3173381570A5075755125 @default.
• W3173381570 hasAuthorship W3173381570A5082933794 @default.
• W3173381570 hasBestOaLocation W31733815701 @default.
• W3173381570 hasConcept C105339364 @default.
• W3173381570 hasConcept C108583219 @default.
• W3173381570 hasConcept C113775141 @default.
• W3173381570 hasConcept C115903868 @default.
• W3173381570 hasConcept C115961682 @default.
• W3173381570 hasConcept C119857082 @default.
• W3173381570 hasConcept C12713177 @default.
• W3173381570 hasConcept C13280743 @default.
• W3173381570 hasConcept C154945302 @default.
• W3173381570 hasConcept C15744967 @default.
• W3173381570 hasConcept C185798385 @default.
• W3173381570 hasConcept C205649164 @default.
• W3173381570 hasConcept C2780586970 @default.
• W3173381570 hasConcept C41008148 @default.
• W3173381570 hasConcept C77088390 @default.
• W3173381570 hasConcept C77805123 @default.
• W3173381570 hasConcept C81363708 @default.
• W3173381570 hasConcept C88548561 @default.
• W3173381570 hasConceptScore W3173381570C105339364 @default.
• W3173381570 hasConceptScore W3173381570C108583219 @default.
• W3173381570 hasConceptScore W3173381570C113775141 @default.
• W3173381570 hasConceptScore W3173381570C115903868 @default.
• W3173381570 hasConceptScore W3173381570C115961682 @default.
• W3173381570 hasConceptScore W3173381570C119857082 @default.
• W3173381570 hasConceptScore W3173381570C12713177 @default.
• W3173381570 hasConceptScore W3173381570C13280743 @default.
• W3173381570 hasConceptScore W3173381570C154945302 @default.
• W3173381570 hasConceptScore W3173381570C15744967 @default.
• W3173381570 hasConceptScore W3173381570C185798385 @default.
• W3173381570 hasConceptScore W3173381570C205649164 @default.
• W3173381570 hasConceptScore W3173381570C2780586970 @default.
• W3173381570 hasConceptScore W3173381570C41008148 @default.
• W3173381570 hasConceptScore W3173381570C77088390 @default.
• W3173381570 hasConceptScore W3173381570C77805123 @default.
• W3173381570 hasConceptScore W3173381570C81363708 @default.
• W3173381570 hasConceptScore W3173381570C88548561 @default.
• W3173381570 hasIssue "1" @default.
• W3173381570 hasLocation W31733815701 @default.
• W3173381570 hasLocation W31733815702 @default.
• W3173381570 hasOpenAccess W3173381570 @default.
• W3173381570 hasPrimaryLocation W31733815701 @default.
• W3173381570 hasRelatedWork W2337926734 @default.
• W3173381570 hasRelatedWork W2731899572 @default.
• W3173381570 hasRelatedWork W3018421652 @default.
• W3173381570 hasRelatedWork W3133861977 @default.
• W3173381570 hasRelatedWork W4312417841 @default.
• W3173381570 hasRelatedWork W4320802194 @default.
• W3173381570 hasRelatedWork W4321369474 @default.
• W3173381570 hasRelatedWork W4366224123 @default.

• next