Joint optimization of speed, accuracy, and energy for embedded image recognition systems
| Autor: | Sungjoo Yoo, Duseok Kang, Soonhoi Ha, Jintaek Kang, Dong-Hyun Kang |
|---|---|
| Rok vydání: | 2018 |
| Předmět: |
business.industry
Computer science 02 engineering and technology Energy consumption 010501 environmental sciences 01 natural sciences Multithreading 0202 electrical engineering electronic engineering information engineering 020201 artificial intelligence & image processing Computer vision Artificial intelligence business Quantization (image processing) Throughput (business) Energy (signal processing) 0105 earth and related environmental sciences |
| Zdroj: | DATE |
| DOI: | 10.23919/date.2018.8342102 |
| Popis: | This paper presents the image recognition system that won the first prize in the LPIRC (Low Power Image Recognition Challenge) in 2017. The goal of the challenge is to maximize the ratio between the accuracy and energy consumption within a time limit of 10 minutes for the processing of 20,000 images. Among three conflicting goals of accuracy, speed, and energy consumption, we considered the trade-off between accuracy and speed first to select Nvidia Jetson TX2 as the hardware platform and Tiny YOLO as the image recognition algorithm. Next, we applied a series of software optimization techniques to improve throughput, such as pipelining, multithreading, Tucker decomposition, and 16-bit quantization. Lastly, we explored the CPU and GPU frequencies to minimize the total energy consumption. As a result, we could achieve an accuracy of 0.24 mAP with energy consumption of 2.08Wh, which corresponds to the score of 0.11931, 2.7 times higher than the winner of LPIRC 2016. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|