FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W2947845658> ?p ?o ?g. }

• W2947845658 endingPage "395" @default.
• W2947845658 startingPage "385" @default.
• W2947845658 abstract "We benchmark several widely-used deep learning frameworks and investigate the field programmable gate array (FPGA) deployment for performing traffic sign classification and detection. We evaluate the training speed and inference accuracy of these frameworks on the graphics processing unit (GPU) by training FPGA-deployment-suitable models with various input sizes on German Traffic Sign Recognition Benchmark (GTSRB), a traffic sign classification dataset. Then, selected trained classification models and various object detection models that we train on GTSRB's detection counterpart (i.e., German Traffic Sign Detection Benchmark) are evaluated with inference speed, accuracy, and FPGA power efficiency by varying different parameters such as floating-point precisions, batch sizes, etc. We discover that Neon and MXNet deliver the best training speed and classification accuracy on the GPU in general for all test cases, while TensorFlow is always among the frameworks with the highest inference accuracies. We observe that with the current OpenVINO release, the performance of lightweight models (e.g., MobileNet-v1-SSD, etc.) usually exceeds the requirement of real-time detection without losing much accuracy, while other models (e.g., VGG-SSD, ResNet-50-SSD) generally fail to do so. We also demonstrate that we can adjust the precision of bitstreams and the batch sizes to balance inference speed and accuracy of the applications deployed on the FPGA. Finally, we show that for all test cases, the FPGA always achieves higher power efficiency than the GPU." @default.
• W2947845658 created "2019-06-07" @default.
• W2947845658 creator A5028111265 @default.
• W2947845658 creator A5028662746 @default.
• W2947845658 creator A5033194035 @default.
• W2947845658 creator A5043168123 @default.
• W2947845658 creator A5082748769 @default.
• W2947845658 date "2019-09-01" @default.
• W2947845658 modified "2023-09-24" @default.
• W2947845658 title "Benchmarking Deep Learning Frameworks and Investigating FPGA Deployment for Traffic Sign Classification and Detection" @default.
• W2947845658 cites W1677182931 @default.
• W2947845658 cites W2001412060 @default.
• W2947845658 cites W2067713319 @default.
• W2947845658 cites W2152417180 @default.
• W2947845658 cites W2294282016 @default.
• W2947845658 cites W2800066735 @default.
• W2947845658 cites W2963674387 @default.
• W2947845658 doi "https://doi.org/10.1109/tiv.2019.2919458" @default.
• W2947845658 hasPublicationYear "2019" @default.
• W2947845658 type Work @default.
• W2947845658 sameAs 2947845658 @default.
• W2947845658 citedByCount "18" @default.
• W2947845658 countsByYear W29478456582019 @default.
• W2947845658 countsByYear W29478456582020 @default.
• W2947845658 countsByYear W29478456582021 @default.
• W2947845658 countsByYear W29478456582022 @default.
• W2947845658 countsByYear W29478456582023 @default.
• W2947845658 crossrefType "journal-article" @default.
• W2947845658 hasAuthorship W2947845658A5028111265 @default.
• W2947845658 hasAuthorship W2947845658A5028662746 @default.
• W2947845658 hasAuthorship W2947845658A5033194035 @default.
• W2947845658 hasAuthorship W2947845658A5043168123 @default.
• W2947845658 hasAuthorship W2947845658A5082748769 @default.
• W2947845658 hasBestOaLocation W29478456582 @default.
• W2947845658 hasConcept C105339364 @default.
• W2947845658 hasConcept C108583219 @default.
• W2947845658 hasConcept C111919701 @default.
• W2947845658 hasConcept C115961682 @default.
• W2947845658 hasConcept C119857082 @default.
• W2947845658 hasConcept C13280743 @default.
• W2947845658 hasConcept C134306372 @default.
• W2947845658 hasConcept C139676723 @default.
• W2947845658 hasConcept C144133560 @default.
• W2947845658 hasConcept C153180895 @default.
• W2947845658 hasConcept C154945302 @default.
• W2947845658 hasConcept C162853370 @default.
• W2947845658 hasConcept C185798385 @default.
• W2947845658 hasConcept C191178318 @default.
• W2947845658 hasConcept C205649164 @default.
• W2947845658 hasConcept C2776151529 @default.
• W2947845658 hasConcept C2776214188 @default.
• W2947845658 hasConcept C2983860417 @default.
• W2947845658 hasConcept C33923547 @default.
• W2947845658 hasConcept C41008148 @default.
• W2947845658 hasConcept C42935608 @default.
• W2947845658 hasConcept C6528762 @default.
• W2947845658 hasConcept C86251818 @default.
• W2947845658 hasConcept C9390403 @default.
• W2947845658 hasConceptScore W2947845658C105339364 @default.
• W2947845658 hasConceptScore W2947845658C108583219 @default.
• W2947845658 hasConceptScore W2947845658C111919701 @default.
• W2947845658 hasConceptScore W2947845658C115961682 @default.
• W2947845658 hasConceptScore W2947845658C119857082 @default.
• W2947845658 hasConceptScore W2947845658C13280743 @default.
• W2947845658 hasConceptScore W2947845658C134306372 @default.
• W2947845658 hasConceptScore W2947845658C139676723 @default.
• W2947845658 hasConceptScore W2947845658C144133560 @default.
• W2947845658 hasConceptScore W2947845658C153180895 @default.
• W2947845658 hasConceptScore W2947845658C154945302 @default.
• W2947845658 hasConceptScore W2947845658C162853370 @default.
• W2947845658 hasConceptScore W2947845658C185798385 @default.
• W2947845658 hasConceptScore W2947845658C191178318 @default.
• W2947845658 hasConceptScore W2947845658C205649164 @default.
• W2947845658 hasConceptScore W2947845658C2776151529 @default.
• W2947845658 hasConceptScore W2947845658C2776214188 @default.
• W2947845658 hasConceptScore W2947845658C2983860417 @default.
• W2947845658 hasConceptScore W2947845658C33923547 @default.
• W2947845658 hasConceptScore W2947845658C41008148 @default.
• W2947845658 hasConceptScore W2947845658C42935608 @default.
• W2947845658 hasConceptScore W2947845658C6528762 @default.
• W2947845658 hasConceptScore W2947845658C86251818 @default.
• W2947845658 hasConceptScore W2947845658C9390403 @default.
• W2947845658 hasIssue "3" @default.
• W2947845658 hasLocation W29478456581 @default.
• W2947845658 hasLocation W29478456582 @default.
• W2947845658 hasOpenAccess W2947845658 @default.
• W2947845658 hasPrimaryLocation W29478456581 @default.
• W2947845658 hasRelatedWork W2215983828 @default.
• W2947845658 hasRelatedWork W2582851122 @default.
• W2947845658 hasRelatedWork W2766975872 @default.
• W2947845658 hasRelatedWork W2800066735 @default.
• W2947845658 hasRelatedWork W2800387905 @default.
• W2947845658 hasRelatedWork W2883921424 @default.
• W2947845658 hasRelatedWork W2883987240 @default.
• W2947845658 hasRelatedWork W2900129920 @default.
• W2947845658 hasRelatedWork W2906549808 @default.
• W2947845658 hasRelatedWork W2948969300 @default.
• W2947845658 hasRelatedWork W2975722160 @default.

• next