系统评估神经网络能耗，揭示模型与图像格式对能效的影响
Phoeni6: a Systematic Approach for Evaluating the Energy Consumption of Neural Networks
- 用容器化工具自动测量能耗，确保可复现性
- MobileNet在原始图上节能6.25%，缩放图上节能2.32%
- 发现BMP格式比PNG节能最高达30%，适合能效优化场景
本文提出Phoeni6，一种系统化的神经网络能耗评估方法，兼顾公平比较与可复现性。该方法通过容器化工具、数据库管理和灵活数据模型，实现能耗数据与配置的可移植性、透明性和协调性。第一项案例研究对比了AlexNet与MobileNet在原始图像和缩放图像上的能耗，结果表明：在原始图像上MobileNet能效高6.25%，缩放图像上高2.32%，且保持竞争力准确率；第二项研究评估图像文件格式影响，发现BMP相比PNG最多可降低30%能耗。这些结果凸显了Phoeni6在优化多样化神经网络应用能耗、推动可持续人工智能实践中的重要价值。
原文摘要 · Abstract (English)
This paper presents Phoeni6, a systematic approach for assessing the energy consumption of neural networks while upholding the principles of fair comparison and reproducibility. Phoeni6 offers a comprehensive solution for managing energy-related data and configurations, ensuring portability, transparency, and coordination during evaluations. The methodology automates energy evaluations through containerized tools, robust database management, and versatile data models. In the first case study, the energy consumption of AlexNet and MobileNet was compared using raw and resized images. Results showed that MobileNet is up to 6.25% more energy-efficient for raw images and 2.32% for resized datasets, while maintaining competitive accuracy levels. In the second study, the impact of image file formats on energy consumption was evaluated. BMP images reduced energy usage by up to 30% compared to PNG, highlighting the influence of file formats on energy efficiency. These findings emphasize the importance of Phoeni6 in optimizing energy consumption for diverse neural network applications and establishing sustainable artificial intelligence practices.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。