다양한 컴퓨팅 환경에서 YOLOv7 모델의 추론 시간 복잡도 분석

YOLOv7 Model Inference Time Complexity Analysis in Different Computing Environments

  • 박천수 (성균관대학교 컴퓨터교육과)
  • 투고 : 2022.07.31
  • 심사 : 2022.09.06
  • 발행 : 2022.09.30

초록

Object detection technology is one of the main research topics in the field of computer vision and has established itself as an essential base technology for implementing various vision systems. Recent DNN (Deep Neural Networks)-based algorithms achieve much higher recognition accuracy than traditional algorithms. However, it is well-known that the DNN model inference operation requires a relatively high computational power. In this paper, we analyze the inference time complexity of the state-of-the-art object detection architecture Yolov7 in various environments. Specifically, we compare and analyze the time complexity of four types of the Yolov7 model, YOLOv7-tiny, YOLOv7, YOLOv7-X, and YOLOv7-E6 when performing inference operations using CPU and GPU. Furthermore, we analyze the time complexity variation when inferring the same models using the Pytorch framework and the Onnxruntime engine.

키워드

과제정보

본 연구는 중소벤처기업부의 연구비지원(S3147433)에 의해 수행되었습니다.

참고문헌

  1. Liu, Yang et al., "A survey and performance evaluation of deep learning methods for small object detection," Expert Systems with Applications, vol. 172, no. 15, pp. 114602-1-14, 2021. https://doi.org/10.1016/j.eswa.2021.114602
  2. S. S. AbbasZaidi, M. S. Ansari, A. Aslam, N. Kanwal, M. Asghar, and B. Lee, "Velasco-Montero, Delia, et al. "A survey of modern deep learning based object detection models." Real-Time Image and Video Processing, vol. 10670, no. 30, pp. 103514-1-9, 2022.
  3. S. Jha, C. Seo, F. Yang, and G. P. Joshi, "Real time object detection and tracking system for video surveillance system." Multimedia Tools and Applications, vol. 80, no. 3, pp. 3981-3996, 2021. https://doi.org/10.1007/s11042-020-09749-x
  4. R. Chandrakar, R. Raja, R. Miri, U. Sinha, A. K. S. Kushwaha, and H. Raja, "Enhanced the moving object detection and object tracking for traffic surveillance using RBF-FDLNN and CBF algorithm." Expert Systems with Applications, vol. 191, pp. 116306-1-15, 2022. https://doi.org/10.1016/j.eswa.2021.116306
  5. E. Arnold, O. Y. Al-Jarrah, M. Dianati, S. Fallah, D. Oxtoby, and A. Mouzakitis, "A survey on 3d object detection methods for autonomous driving applications." IEEE Transactions on Intelligent Transportation Systems, vol. 20, no. 10, pp. 3782-3795, 2019 https://doi.org/10.1109/tits.2019.2892405
  6. E. H. Nguyen, H. Yang, R. Deng, Y. Lu, Z. Zhu, J. T. Roland, and Y. Huo, "Circle Representation for Medical Object Detection." IEEE transactions on medical imaging, vol. 41, no. 3, 746-754. 2021.
  7. D. Pestana, et al. "A full featured configurable accelerator for object detection with YOLO." IEEE Access, vol. 9, pp. 75864-75877, 2021. https://doi.org/10.1109/ACCESS.2021.3081818
  8. R. Girshick, J. Donahue, T. Darrell, and J. Malik, "Rich feature hierarchies for accurate object detection and semantic segmentation," in Proc. IEEE Conf. Comput. Vis. Pattern Recognit., pp. 580-587, Jun. 2014.
  9. R. Girshick, "Fast R-CNN," in Proc. IEEE Int. Conf. Comput. Vis. (ICCV), pp. 1440-1448, Dec. 2015.
  10. J. Dai, Y. Li, K. He, and J. Sun, "R-FCN: Object detection via region based fully convolutional networks," in Proc. 30th Int. Conf. Neural Inf. Process. Syst. (NIPS). Red Hook, NY, USA: Curran Associates, pp. 379-387, 2016.
  11. S. Ren, K. He, R. Girshick, and J. Sun, "Faster R-CNN: Towards real-time object detection with region proposal networks," IEEE Trans. Pattern Anal. Mach. Intell., vol. 39, no. 6, pp. 1137-1149, Jun. 2017. https://doi.org/10.1109/TPAMI.2016.2577031
  12. K. He, G. Gkioxari, P. Dollar, and R. B. Girshick, "Mask R-CNN," in Proc. IEEE Int. Conf. Comput. Vis. (ICCV), pp. 2980-2988, Oct. 2017.
  13. W. Liu, et al. "Ssd: Single shot multibox detector." European conference on computer vision. Cham, pp. 21-37, 2016.
  14. P. Jiang, D. Ergu, F. Liu, Y. Cai, and B. Ma. "A Review of Yolo Algorithm Developments." Procedia Computer Science, pp. 1066-1073, 2022.
  15. J. Redmon, and A. Farhadi, "YOLO9000: better, faster, stronger." In Proceedings of the IEEE conference on computer vision and pattern recognition, pp. 7263-7271, 2017.
  16. Ali Farhadi and Joseph Redmon. "Yolov3: An incremental improvement." Computer Vision and Pattern Recognition, vol. 1804, pp. 1-6, 2018.
  17. Bochkovskiy, Alexey, Chien-Yao Wang, and HongYuan Mark Liao. "Yolov4: Optimal speed and accuracy of object detection." arXiv preprint arXiv:2004.10934, 2020.
  18. C. Y. Wang, A. Bochkovskiy, and H. Y. H. Liao. "Scaled-yolov4: Scaling cross stage partial network." In Proceedings of the IEEE/cvf conference on computer vision and pattern recognition. pp. 13029-13038, 2021.
  19. W. Wu, et al. "Application of local fully Convolutional Neural Network combined with YOLO v5 algorithm in small target detection of remote sensing image." PloS one, vol. 16, no. 10, pp. e0259283. 2021. https://doi.org/10.1371/journal.pone.0259283
  20. https://github.com/meituan/YOLOv6
  21. C. Y. Wang, A. Bochkovskiy, and H. Y. M. Liao, "YOLOv7: Trainable bag-of-freebies sets new state-of-the-art for real-time object detectors." arXiv preprint arXiv:2207.02696.
  22. C. S. Park, "Performance Analysis of DNN inference using OpenCV Built in CPU and GPU Functions." Journal of the Semiconductor & Display Technology, vol. 21. no. 1. pp. 75-78, 2022.