文件名称：ShuffleNet V2: Practical Guidelines for Efficient CNN Architecture Design
文件大小：1.58MB
文件格式：PDF
更新时间：2021-12-23 09:05:36
ShuffleNet V CNN
Abstract. 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 de- sign. 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.