KIPS Transactions on Software and Data Engineering (정보처리학회논문지:소프트웨어 및 데이터공학)

Korea Information Processing Society (한국정보처리학회)
권호 표지
DOI QR코드

DOI QR Code

An Efficient Deep Learning Based Image Recognition Service System Using AWS Lambda Serverless Computing Technology

AWS Lambda Serverless Computing 기술을 활용한 효율적인 딥러닝 기반 이미지 인식 서비스 시스템

  • Received : 2019.11.08
  • Accepted : 2020.02.27
  • Published : 2020.06.30
Download PDF
⟨ Previous Next ⟩

Abstract

Recent advances in deep learning technology have improved image recognition performance in the field of computer vision, and serverless computing is emerging as the next generation cloud computing technology for event-based cloud application development and services. Attempts to use deep learning and serverless computing technology to increase the number of real-world image recognition services are increasing. Therefore, this paper describes how to develop an efficient deep learning based image recognition service system using serverless computing technology. The proposed system suggests a method that can serve large neural network model to users at low cost by using AWS Lambda Server based on serverless computing. We also show that we can effectively build a serverless computing system that uses a large neural network model by addressing the shortcomings of AWS Lambda Server, cold start time and capacity limitation. Through experiments, we confirmed that the proposed system, using AWS Lambda Serverless Computing technology, is efficient for servicing large neural network models by solving processing time and capacity limitations as well as cost reduction.

최근 딥러닝(Deep Learning) 기술의 발전에 따라 컴퓨터 비전(Computer Vision) 분야의 이미지 인식 성능이 향상되고 있으며, 또한 Serverless Computing이 이벤트 기반의 클라우드 애플리케이션 개발 및 서비스를 위한 차세대 클라우드 컴퓨팅 기술로 각광받고 있어 딥러닝과 Serverless Computing 기술을 접목하여 실생활에 이미지 인식 서비스를 사용하고자 하는 시도가 증가하고 있다. 따라서 본 논문에서는 Serverless Computing 기술을 활용하여 효율적인 딥러닝 기반 이미지 인식 서비스 시스템 개발 방법을 기술한다. 제안하는 시스템은 Serverless Computing 기반 AWS Lambda Server를 이용하여 적은 비용으로 대형 신경망 모델을 사용자에게 서비스할 수 있는 방법을 제안한다. 또한 AWS Lambda Server의 단점인 Cold Start Time 문제와 용량제한 문제를 해결하여 효과적으로 대형 신경망 모델을 사용하는 Serverless Computing 시스템을 구축할 수 있음을 보인다. 실험을 통해 AWS Lambda Serverless Computing 기술을 활용하여 본 논문에서 제안한 시스템이 비용 절감뿐만 아니라 처리 시간 및 용량제한 문제를 해결하여 대형 신경망 모델을 서비스하기에 효율적인 성능을 보임을 확인하였다.

Keywords

References

  1. L. Feng, P. Kudva, D. D. Silva, and J. Hu, "Exploring serverless computing for neural network training," IEEE 11th International Conference on Cloud Computing (CLOUD), San Francisco, CA, USA, Jul. 2-7, 2018, DOI: 10.1109/CLOUD.2018.00049
  2. G. C. Fox, V. Ishakian, V. Muthusamy, and A. Slominski, "Status of serverless computing and Function-as-a-service (FaaS) in industry and research," arXiv preprint arXiv:1708.08028, Aug. 2017, DOI: 10.13140/RG.2.2.15007.87206.
  3. I. Baldini, P. Castro, K. Chang, P. Cheng, S. Fink, V. Ishakian, N. Mitchell, V. Muthusamy, R. Rabbah, A. Slominski et al., "Serverless computing: Current trends and open problems," Research Advances in Cloud Computing. Springer, Singapore, pp.1-20, Dec. 2017, DOI: 10.1007/978-981-10-5026-8_1.
  4. AWS (Amazon Web Services) [Internet], https://aws.amazon.com/ko/.
  5. Lambda Server [Internet], https://aws.amazon.com/ko/lambda/.
  6. V. Ishakian, V. Muthusamy, and A. Slominski, "Serving deep learning models in a serverless platform," 2018 IEEE International Conference on Cloud Engineering (IC2E), Orlando, FL, USA, 17-20 April 2018, DOI: 10.1109/IC2E.2018.00052.
  7. Y. LeCun, Y. Bengio, and G. Hinton, "Deep learning," Nature, Vol.521, No.7553, pp.436-444, May 2015, DOI:10.1038/nature14539.
  8. K. He, X. Zhang, S. Ren, and J. Sun, "Deep residual learning for image recognition," 2016 IEEE Conference on Computer Vision and Pattern Recognition(CVPR), pp.770-778, Jun. 2016, DOI: 10.1109/CVPR.2016.90.
  9. J. Deng, W. Dong, R. Socher, L. Li, K. Li, and L. Fei-Fei, "ImageNet: A large-scale hierarchical image database," 2009 IEEE Conference on Computer Vision and Pattern Recognition, Miami, FL, pp.248-255, 20-25 Jun. 2009, DOI: 10.1109/CVPR.2009.5206848.
  10. W. Ge and Y. Yu, "Borrowing treasures from the wealthy: Deep transfer learning through selective joint fine-tuning," arXiv preprint, 2017, https://arxiv.org/abs/1702.08690.
  11. H. Inoue, "Data augmentation by pairing samples for images classification," arXiv preprint, 2018, https://arxiv.org/abs/1801.02929.
  12. R. Chard, K. Chard, J. Alt, D. Y. Parkinson, S. Tuecke, and I. Foster, "Ripple: Home automation for research data management," IEEE 37th International Conference on Distributed Computing Systems Workshops (ICDCSW), pp. 389-394, Jun. 2017.
  13. M. Yan, P. Castro, P. Cheng, and V. Ishakian, "Building a chatbot with serverless computing," Proceedings of the 1st International Workshop on Mashups of Things and APIs, Trento, Italy, Dec. 12-16, pp.1-4, 2016, DOI: 10.1145/3007203.3007217.
  14. Amazon API Gateway [Internet], https://aws.amazon.com/ko/api-gateway/.
  15. Apache JMeter [Internet], https://jmeter.apache.org/.
  16. PyTorch [Internet], https://pytorch.org/.
  17. AWS Lambda Limits [Internet], https://docs.aws.amazon.com/ko_kr/lambda/latest/dg/limits.html.
  18. AWS Lambda Pricing, https://www.amazonaws.cn/en/lambda/pricing/.