Abstract
This paper benchmarks 16 combinations of popular Deep Neural Networks for 1000-category image recognition and Deep Learning frameworks on an embedded platform. A Figure of Merit based on high-level specifications is introduced. By sweeping the relative weight of accuracy, throughput and power consumption on global performance, we demonstrate that only a reduced set of the analyzed combinations must actually be considered for real deployment. We also report the optimum network/framework selection for all possible application scenarios defined in those terms, i.e. weighted balance of the aforementioned parameters. Our approach can be extended to other networks, frameworks and performance parameters, thus supporting system-level design decisions in the ever-changing ecosystem of Deep Learning technology.
This is a preview of subscription content, log in via an institution.
Buying options
Tax calculation will be finalised at checkout
Purchases are for personal use only
Learn about institutional subscriptionsReferences
Abadi, M. et al.: TensorFlow: a system for large-scale machine learning. In: 12th USENIX Symposium on Operating Systems Design and Implementation (OSDI), pp. 265–283 (2016)
DeftWork: a docker image for Tensorflow (2018). https://github.com/DeftWork/rpi-tensorflow. Accessed July 2018
Facebook Open Source: Caffe2 (2018). https://caffe2.ai/. Accessed July 2018
Howard, A. et al.: MobileNets: efficient convolutional neural networks for mobile vision applications. arXiv:1704.04861 (2017)
Iandola, F. et al.: SqueezeNet: AlexNet-level accuracy with 50x fewer parameters and \(<\)1 MB model size. arXiv:1602.07360 (2016)
Jia, Y., et al.: Caffe: convolutional architecture for fast feature embedding. arXiv:1408.5093 (2014)
LeCun, Y., Bengio, Y., Hinton, G.: Deep learning. Nature 521(7553), 436–444 (2015)
Lin, M., Chen, Q., Yan, S.: Network in network. arXiv:1312.4400 (2013)
OpenCV Team: OpenCV (2018). https://opencv.org/. Accessed July 2018
Russakovsky, O., et al.: ImageNet large scale visual recognition challenge. Int. J. Comput. Vis. (IJCV) 115(3), 211–252 (2015)
Sze, V., et al.: Efficient processing of deep neural networks: a tutorial and survey. Proc. IEEE 105(12), 2295–2329 (2017)
Szegedy, C. et al.: Going deeper with convolutions. arXiv:1409.4842 (2014)
Velasco-Montero, D. et al.: Performance analysis of real-time DNN inference on Raspberry Pi. In: SPIE Commercial + Scientific Sensing and Imaging, April 2018
Verhelst, M., Moons, B.: Embedded deep neural network processing. IEEE Solid-State Circ. Mag. 9(4), 55–65 (2017)
Xianyi, Z.: OpenBLAS, optimized BLAS library based on GotoBLAS2 1.13 BSD version (2018). https://github.com/xianyi/OpenBLAS. Accessed July 2018
Acknowledgments
This work was supported by Spanish Government MINECO (European Region Development Fund, ERDF/FEDER) through Project TEC2015-66878-C3-1-R, by Junta de Andalucía CEICE through Project TIC 2338-2013 and by EU H2020 MSCA ACHIEVE-ITN, Grant No. 765866.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2018 Springer Nature Switzerland AG
About this paper
Cite this paper
Velasco-Montero, D., Fernández-Berni, J., Carmona-Galán, R., Rodríguez-Vázquez, Á. (2018). Optimum Network/Framework Selection from High-Level Specifications in Embedded Deep Learning Vision Applications. In: Blanc-Talon, J., Helbert, D., Philips, W., Popescu, D., Scheunders, P. (eds) Advanced Concepts for Intelligent Vision Systems. ACIVS 2018. Lecture Notes in Computer Science(), vol 11182. Springer, Cham. https://doi.org/10.1007/978-3-030-01449-0_31
Download citation
DOI: https://doi.org/10.1007/978-3-030-01449-0_31
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-01448-3
Online ISBN: 978-3-030-01449-0
eBook Packages: Computer ScienceComputer Science (R0)