计算机科学
失败
公制(单位)
建筑
计算
性能指标
分布式计算
计算机体系结构
计算机工程
并行计算
算法
工程类
艺术
视觉艺术
经济
运营管理
管理
作者
Ningning Ma,Xiangyu Zhang,Hai-Tao Zheng,Jian Sun
标识
DOI:10.1007/978-3-030-01264-9_8
摘要
Currently, the neural network architecture design is mostly guided by the indirect metric of computation complexity, i.e., FLOPs. However, the direct metric, e.g., speed, also depends on the other factors such as memory access cost and platform characterics. Thus, this work proposes to evaluate the direct metric on the target platform, beyond only considering FLOPs. Based on a series of controlled experiments, this work derives several practical guidelines for efficient network design. Accordingly, a new architecture is presented, called ShuffleNet V2. Comprehensive ablation experiments verify that our model is the state-of-the-art in terms of speed and accuracy tradeoff.
科研通智能强力驱动
Strongly Powered by AbleSci AI