DOI QR코드

DOI QR Code

Pedestrian Inference Convolution Neural Network Using GP-GPU

GP-GPU를 이용한 보행자 추론 CNN

  • Jeong, Junmo (Dept. of Electronics Engineering, Seokyeong University)
  • Received : 2017.09.13
  • Accepted : 2017.09.20
  • Published : 2017.09.30

Abstract

In this paper, we implemented a convolution neural network using GP-GPU. After defining the structure, CNN performed inferencing using the GP-GPU with 256 threads, which was the previous study, using the weight obtained from the training. Training used Intel i7-4470 CPU and Matlab. Dataset used Daimler Pedestrian Dataset. The GP-GPU is controlled by the PC using PCIe and operates as an FPGA. We assigned a thread according to the depth and size of each layer. In the case of the pooling layer, we used over warpping pooling to perform additional operations on the horizontal and vertical regions. One inferencing takes about 12 ms.

본 논문에서는 GP-GPU를 활용한 보행자 추론 컨볼루션 뉴럴 네트워크를 구현했다. CNN은 구조를 정한 후, 학습에서 얻은 가중치를 이용해 기존 연구인 256개의 스레드를 가지는 GP-GPU를 활용해 추론을 수행했다. 학습에는 Inter i7-4470 CPU와 Matlab을 사용했다. Dataset은 Daimler Pedestrian Dataset을 사용했다. GP-GPU는 PCIe를 이용해 PC로부터 제어를 받으며, FPGA로 동작한다. 각 레이어의 depth와 size에 따라 스레드를 할당했다. 풀링 레이어의 경우는 over warpping pooling을 사용했기 때문에 횡영역과 종영역에 추가적인 연산을 수행했다. 한 번의 추론에는 약 12ms가 걸린다.

Keywords

References

  1. P. Dollar, C. Wojek, B. Schiele, and P. Perona, "Pedestrian detection: An evaluation of the state of the art," IEEE Trans. on PAMI, 2012. DOI : 10.1109/TPAMI.2011.155
  2. http://darkpgmr.tistory.com/
  3. http://www.gavrila.net/Research/Pedestrian_Detection/Daimler_Pedestrian_Benchmark_D/Daimler_Mono_Ped_Detection_Be/daimler_mono_ped_detection_be.html
  4. Dohyun Kim, Chi-yong Kim, "Design of a SIMT architecture GP-GPU using Tile based on graphic pipeline structure", j.inst.Korean.electr.electron.eng, Vol 20. No 1. DOI : 10.7471/ikeee.2016.20.1.075
  5. Kwanho Lee, Chi-yong Kim, "A Design of a High Performance Stream Processor without Superscalar Architecture", j.inst.Korean.electr.electron.eng, Vol 21. No 1.
  6. https://www.xilinx.com
  7. Farabet, Clément, Cyril Poulet, Jefferson Y. Han, and Yann LeCun. "Cnp: An fpga-based processor for convolutional networks." In 2009 International Conference on Field Programmable Logic and Applications, pp. 32-37. IEEE, 200 DOI : 10.1109/FPL.2009.5272559
  8. Chakradhar, Srimat, et al. "A dynamically configurable coprocessor for convolutional neural networks." ACM SIGARCH Computer Architecture News. Vol. 38. No. 3.ACM, 2010. DOI : 10.1145/1816038.1815993
  9. Heekyeong Jeon, "A Design of Convolutional neural network Processor for ADAS", Master thesis, Seokyeong University, 2017