arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2108.13465cs.CVcs.LG
收藏

低碳计算机视觉全周期能耗基准

Full-Cycle Energy Consumption Benchmark for Low-Carbon Computer Vision

Microsoft Research Asia(微软亚洲研究院);University of Technology Sydney(悉尼科技大学)

Bo Li, Xinyang Jiang, Donglin Bai, Yuge Zhang, Ningxin Zheng, Xuanyi Dong, Lu Liu, Yuqing Yang, Dongsheng Li

摘要:

深度学习模型的能耗正以惊人的速度增长,这引起了人们的担忧,因为在全球变暖和气候变化的背景下,这对碳中和有潜在的负面影响。随着有效的深度学习技术的进步,模型压缩,研究人员可以获得更少的参数和更小的延迟的高效模型。然而,大多数现有的高效深度学习方法没有明确地将能耗作为关键性能指标。此外,现有的方法大多集中在推理成本的有效模型,但忽略了显着的能量消耗在整个生存周期的算法。在本文中,我们提出了高效的计算机视觉模型的第一个大规模的能源消耗基准,其中提出了一个新的度量,明确评估不同的模型使用强度下的全周期能源消耗。该基准可以为在不同模型使用场景下选择高效的深度学习算法提供低碳排放的见解。

英文摘要:

The energy consumption of deep learning models is increasing at a breathtaking rate, which raises concerns due to potential negative effects on carbon neutrality in the context of global warming and climate change. With the progress of efficient deep learning techniques, e.g., model compression, researchers can obtain efficient models with fewer parameters and smaller latency. However, most of the existing efficient deep learning methods do not explicitly consider energy consumption as a key performance indicator. Furthermore, existing methods mostly focus on the inference costs of the resulting efficient models, but neglect the notable energy consumption throughout the entire life cycle of the algorithm. In this paper, we present the first large-scale energy consumption benchmark for efficient computer vision models, where a new metric is proposed to explicitly evaluate the full-cycle energy consumption under different model usage intensity. The benchmark can provide insights for low carbon emission when selecting efficient deep learning algorithms in different model usage scenarios.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑