Latency and throughput characterization of convolutional neural networks for mobile computer vision

Research output: Chapter in Book/Report/Conference proceedingConference contributionScientificpeer-review

13 Citations (Scopus)

Abstract

We study performance characteristics of convolutional neural networks (CNN) for mobile computer vision systems. CNNs have proven to be a powerful and efficient approach to implement such systems. However, the system performance depends largely on the utilization of hardware accelerators, which are able to speed up the execution of the underlying mathematical operations tremendously through massive parallelism. Our contribution is performance characterization of multiple CNN-based models for object recognition and detection with several different hardware platforms and software frameworks, using both local (on-device) and remote (network-side server) computation. The measurements are conducted using real workloads and real processing platforms. On the platform side, we concentrate especially on TensorFlow and TensorRT. Our measurements include embedded processors found on mobile devices and high-performance processors that can be used on the network side of mobile systems. We show that there exists significant latency-throughput trade-offs but the behavior is very complex. We demonstrate and discuss several factors that affect the performance and yield this complex behavior.

Original languageEnglish
Title of host publicationProceedings of the 9th ACM Multimedia Systems Conference, MMSys 2018
PublisherACM
Pages204-215
Number of pages12
ISBN (Electronic)9781450351928
DOIs
Publication statusPublished - 12 Jun 2018
MoE publication typeA4 Article in a conference publication
EventACM Multimedia Systems Conference - Amsterdam, Netherlands
Duration: 12 Jun 201815 Jun 2018
Conference number: 9

Conference

ConferenceACM Multimedia Systems Conference
Abbreviated titleMMSys
CountryNetherlands
CityAmsterdam
Period12/06/201815/06/2018

Fingerprint Dive into the research topics of 'Latency and throughput characterization of convolutional neural networks for mobile computer vision'. Together they form a unique fingerprint.

  • Cite this