FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W3128702906> ?p ?o ?g. }

• W3128702906 endingPage "160" @default.
• W3128702906 startingPage "143" @default.
• W3128702906 abstract "Choosing the appropriate deployment strategy for any Deep Learning (DL) project in a production environment has always been the most challenging problem for industrial practitioners. There are several conflicting constraints and controversial approaches when it comes to deployment. Among these problems, the deployment on cloud versus the deployment on edge represents a common dilemma. In a nutshell, each approach provides benefits where the other would have limitations. This paper presents a real-world case study on deploying a face recognition application using MTCNN detector and FaceNet recognizer. We report the challenges faced to decide on the best deployment strategy. We propose three inference architectures for the deployment, including cloud-based, edge-based, and hybrid. Furthermore, we evaluate the performance of face recognition inference on different cloud-based and edge-based GPU platforms. We consider different models of Jetson boards for the edge (Nano, TX2, Xavier NX, Xavier AGX) and various GPUs for the cloud (GTX 1080, RTX 2080Ti, RTX 2070, and RTX 8000). We also investigate the effect of deep learning model optimization using TensorRT and TFLite compared to a standard Tensorflow GPU model, and the effect of input resolution. We provide a benchmarking study for all these devices in terms of frames per second, execution times, energy and memory usages. After conducting a total of 294 experiments, the results demonstrate that the TensorRT optimization provides the fastest execution on all cloud and edge devices, at the expense of significantly larger energy consumption (up to +40% and +35% for edge and cloud devices, respectively, compared to Tensorflow). Whereas TFLite is the most efficient framework in terms of memory and power consumption, while providing significantly less (-4% to -62%) processing acceleration than TensorRT. <italic xmlns:mml=http://www.w3.org/1998/Math/MathML xmlns:xlink=http://www.w3.org/1999/xlink>Practitioners Note:</i> The study reported in this paper presents the real-challenges that we faced during our development and deployment of a face-recognition application both on the edge and on the cloud, and the solutions we have developed to solve these problems. The code, results, and interactive analytic dashboards of this paper will be put public upon publication." @default.
• W3128702906 created "2021-02-15" @default.
• W3128702906 creator A5010117453 @default.
• W3128702906 creator A5014758459 @default.
• W3128702906 creator A5024626195 @default.
• W3128702906 creator A5050720870 @default.
• W3128702906 date "2022-01-01" @default.
• W3128702906 modified "2023-10-13" @default.
• W3128702906 title "Cloud Versus Edge Deployment Strategies of Real-Time Face Recognition Inference" @default.
• W3128702906 cites W2044168272 @default.
• W3128702906 cites W2088692353 @default.
• W3128702906 cites W2090836891 @default.
• W3128702906 cites W2097117768 @default.
• W3128702906 cites W2145287260 @default.
• W3128702906 cites W2164598857 @default.
• W3128702906 cites W2194775991 @default.
• W3128702906 cites W2395639500 @default.
• W3128702906 cites W2508388616 @default.
• W3128702906 cites W2553915786 @default.
• W3128702906 cites W2570343428 @default.
• W3128702906 cites W2659864996 @default.
• W3128702906 cites W2766823323 @default.
• W3128702906 cites W2769100446 @default.
• W3128702906 cites W2782812883 @default.
• W3128702906 cites W2791319131 @default.
• W3128702906 cites W2792220137 @default.
• W3128702906 cites W2806335431 @default.
• W3128702906 cites W2807126412 @default.
• W3128702906 cites W2807214292 @default.
• W3128702906 cites W2891209073 @default.
• W3128702906 cites W2907882680 @default.
• W3128702906 cites W2909099954 @default.
• W3128702906 cites W2917996064 @default.
• W3128702906 cites W2918891759 @default.
• W3128702906 cites W2960833983 @default.
• W3128702906 cites W2962700793 @default.
• W3128702906 cites W2962814013 @default.
• W3128702906 cites W2963150697 @default.
• W3128702906 cites W2963839617 @default.
• W3128702906 cites W2965289829 @default.
• W3128702906 cites W2971544778 @default.
• W3128702906 cites W2972714212 @default.
• W3128702906 cites W2986905306 @default.
• W3128702906 cites W3009100893 @default.
• W3128702906 cites W3015636663 @default.
• W3128702906 cites W3016493309 @default.
• W3128702906 cites W3018835489 @default.
• W3128702906 cites W3027472889 @default.
• W3128702906 cites W3041051645 @default.
• W3128702906 cites W3081838881 @default.
• W3128702906 cites W3086271189 @default.
• W3128702906 cites W3092099317 @default.
• W3128702906 cites W3098784686 @default.
• W3128702906 cites W3099206234 @default.
• W3128702906 cites W3101998545 @default.
• W3128702906 cites W4235875447 @default.
• W3128702906 cites W4236853429 @default.
• W3128702906 cites W4252642235 @default.
• W3128702906 doi "https://doi.org/10.1109/tnse.2021.3055835" @default.
• W3128702906 hasPublicationYear "2022" @default.
• W3128702906 type Work @default.
• W3128702906 sameAs 3128702906 @default.
• W3128702906 citedByCount "17" @default.
• W3128702906 countsByYear W31287029062021 @default.
• W3128702906 countsByYear W31287029062022 @default.
• W3128702906 countsByYear W31287029062023 @default.
• W3128702906 crossrefType "journal-article" @default.
• W3128702906 hasAuthorship W3128702906A5010117453 @default.
• W3128702906 hasAuthorship W3128702906A5014758459 @default.
• W3128702906 hasAuthorship W3128702906A5024626195 @default.
• W3128702906 hasAuthorship W3128702906A5050720870 @default.
• W3128702906 hasConcept C105339364 @default.
• W3128702906 hasConcept C108583219 @default.
• W3128702906 hasConcept C111919701 @default.
• W3128702906 hasConcept C115903868 @default.
• W3128702906 hasConcept C119599485 @default.
• W3128702906 hasConcept C119857082 @default.
• W3128702906 hasConcept C120314980 @default.
• W3128702906 hasConcept C127413603 @default.
• W3128702906 hasConcept C138236772 @default.
• W3128702906 hasConcept C144133560 @default.
• W3128702906 hasConcept C154945302 @default.
• W3128702906 hasConcept C162307627 @default.
• W3128702906 hasConcept C162853370 @default.
• W3128702906 hasConcept C2776214188 @default.
• W3128702906 hasConcept C2778456923 @default.
• W3128702906 hasConcept C2780165032 @default.
• W3128702906 hasConcept C41008148 @default.
• W3128702906 hasConcept C79403827 @default.
• W3128702906 hasConcept C79974875 @default.
• W3128702906 hasConcept C86251818 @default.
• W3128702906 hasConceptScore W3128702906C105339364 @default.
• W3128702906 hasConceptScore W3128702906C108583219 @default.
• W3128702906 hasConceptScore W3128702906C111919701 @default.
• W3128702906 hasConceptScore W3128702906C115903868 @default.
• W3128702906 hasConceptScore W3128702906C119599485 @default.
• W3128702906 hasConceptScore W3128702906C119857082 @default.
• W3128702906 hasConceptScore W3128702906C120314980 @default.

• next