BriefGPT.xyz
May, 2016
深度神经网络模型在实践应用中的分析
An Analysis of Deep Neural Network Models for Practical Applications
HTML
PDF
Alfredo Canziani, Adam Paszke, Eugenio Culurciello
TL;DR
本文对深度神经网络在计算机视觉领域中的重要应用指标进行全面分析,发现能耗与批次大小和架构无关,准确度和推断时间在双曲线关系中,能源约束是最大可实现准确度和模型复杂度的上限,操作次数是推断时间的可靠估计。
Abstract
Since the emergence of
deep neural networks
(DNNs) as a prominent technique in the field of computer vision, the
imagenet classification
challenge has played a major role in advancing the state-of-the-art. While
→