Electronics and Telecommunications Trends (전자통신동향분석)

Electronics and Telecommunications Research Institute (한국전자통신연구원)
권호 표지
DOI QR코드

DOI QR Code

Trends in Deep Learning Inference Engines for Embedded Systems

임베디드 시스템용 딥러닝 추론엔진 기술 동향

  • 유승목 (고성능디바이스SW연구실) ;
  • 이경희 (고성능디바이스SW연구실) ;
  • 박재복 (고성능디바이스SW연구실) ;
  • 윤석진 (고성능디바이스SW연구실) ;
  • 조창식 (고성능디바이스SW연구실) ;
  • 정영준 (차세대시스템SW연구실) ;
  • 조일연 (초성능컴퓨팅연구본부)
  • Published : 2019.08.01
Download PDF
⟨ Previous Next ⟩

Abstract

Deep learning is a hot topic in both academic and industrial fields. Deep learning applications can be categorized into two areas. The first category involves applications such as Google Alpha Go using interfaces with human operators to run complicated inference engines in high-performance servers. The second category includes embedded applications for mobile Internet-of-Things devices, automotive vehicles, etc. Owing to the characteristics of the deployment environment, applications in the second category should be bounded by certain H/W and S/W restrictions depending on their running environment. For example, image recognition in an autonomous vehicle requires low latency, while that on a mobile device requires low power consumption. In this paper, we describe issues faced by embedded applications and review popular inference engines. We also introduce a project that is being development to satisfy the H/W and S/W requirements.

Keywords

Acknowledgement

Grant : 운전자 주행경험 모사기반 일반도로환경의 자율주행4단계(SAE)를 지원하는 주행판단엔진 개발

Supported by : 정보통신기술진흥센터

References

  1. TensorFlow, "TensorFlow Lite guide," https://www.tensorflow.org/lite/guide?hl=ko
  2. Nvidia, "TensorRT," https://developer.nvidia.com/tensorrt
  3. Microsoft, "Windows Machine Learning," https://docs.microsoft.com/en-us/windows/ai/windows-ml
  4. Developer.apple, "Core ML," https://developer.apple.com/documentation/coreml
  5. Appcoda, "Introduction to the Accelerate Framework in Swift," https://www.appcoda.com/accelerate-framework/
  6. KHRONOS, "Neural Network Exchange Format (NNEF)," https://www.khronos.org/nnef
  7. ONNX, https://onnx.ai/
  8. ONNX.GitHub, "Open Neural Network Exchange-ONNX," https://github.com/onnx/onnx/blob/master/docs/IR.md
  9. KHRONOS, "NNEF and ONNX: Similarities and Differences," https://www.khronos.org/blog/nnef-and-onnx-similarities-and-differences
  10. Intel, AI, https://www.intel.ai/plaidml/
  11. K. H. Lee et al., "An Implementation of a Parser for Neural Network Exchange Format," IEMEK Symp.Embedded Technol., Jeju island, Rep. of Korea, May 24-25, 2018, pp. 49-51.