OpenCV 내장 CPU 및 GPU 함수를 이용한 DNN 추론 시간 복잡도 분석 = Performance Analysis of DNN inference using OpenCV Built in CPU and GPU Functions

다국어 초록 (Multilingual Abstract)

Deep Neural Networks (DNN) has become an essential data processing architecture for the implementation of multiple computer vision tasks. Recently, DNN-based algorithms achieve much higher recognition accuracy than traditional algorithms based on shallow learning. However, training and inference DNNs require huge computational capabilities than daily usage purposes of computers. Moreover, with increased size and depth of DNNs, CPUs may be unsatisfactory since they use serial processing by default. GPUs are the solution that come up with greater speed compared to CPUs because of their Parallel Processing/Computation nature. In this paper, we analyze the inference time complexity of DNNs using well-known computer vision library, OpenCV. We measure and analyze inference time complexity for three cases, CPU, GPU-Float32, and GPU-Float16.

참고문헌 (Reference)

1 "https://learnopencv.com/deep-learning-with-opencvs-dnn-module-a-definitive-guide/"

2 "https://github.com/AlexeyAB/darknet"

3 "https://en.wikipedia.org/wiki/OpenCV"

4 Bochkovskiy, Alexey, "Yolov4: Optimal speed and accuracy of object detection" 2020

5 Ali Farhadi, "Yolov3: An incremental improvement" 1804 : 1-6, 2018

6 C. Y. Wang, "Scaled-yolov4: Scaling cross stage partial network" 13029-13038, 2021

7 Xiang, Yecheng, "Pipelined data-parallel CPU/GPU scheduling for multi-DNN real-time inference" 392-405, 2019

8 Hangün, Batuhan, "Performance comparison between OpenCV built in CPU and GPU functions on image processing operations" 1 (1): 34-41, 2017

9 Velasco-Montero, Delia, "Performance analysis of real-time DNN inference on Raspberry Pi" 10670 : 10670F-, 2018

10 Adrian Kaehler, "Learning OpenCV 3: computer vision in C++ with the OpenCV library" O'Reilly Media, Inc 2016

11 Shalini, K., "Comparative analysis on Deep Convolution Neural Network models using Pytorch and OpenCV DNN frameworks for identifying optimum fruit detection solution on RISC-V architecture" 738-743, 2021

12 Xiaoyun Wang, "Accelerating DNN Inference with GraphBLAS and the GPU" 1-6, 2019

13 P. Jiang, "A Review of Yolo Algorithm Developments" 1066-1073, 2022