Latency and Throughput Characterization of Convolutional Neural Networks for Mobile Computer Vision

03/26/2018
by   Jussi Hanhirova, et al.
0

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.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
09/27/2017

Modeling the Resource Requirements of Convolutional Neural Networks on Mobile Devices

Convolutional Neural Networks (CNNs) have revolutionized the research in...
research
12/21/2015

Quantized Convolutional Neural Networks for Mobile Devices

Recently, convolutional neural networks (CNN) have demonstrated impressi...
research
03/17/2017

Towards Closing the Energy Gap Between HOG and CNN Features for Embedded Vision

Computer vision enables a wide range of applications in robotics/drones,...
research
08/26/2022

Hardware-aware mobile building block evaluation for computer vision

In this work we propose a methodology to accurately evaluate and compare...
research
06/02/2022

EfficientFormer: Vision Transformers at MobileNet Speed

Vision Transformers (ViT) have shown rapid progress in computer vision t...
research
06/08/2020

Making Convolutions Resilient via Algorithm-Based Error Detection Techniques

The ability of Convolutional Neural Networks (CNNs) to accurately proces...
research
10/21/2021

Improving the Deployment of Recycling Classification through Efficient Hyper-Parameter Analysis

The paradigm of automated waste classification has recently seen a shift...

Please sign up or login with your details

Forgot password? Click here to reset