期刊
ARTIFICIAL NEURAL NETWORKS AND MACHINE LEARNING - ICANN 2018, PT I
卷 11139, 期 -, 页码 402-411出版社
SPRINGER INTERNATIONAL PUBLISHING AG
DOI: 10.1007/978-3-030-01418-6_40
关键词
Neural network quantization; Auto-tuning framework; Edge computing; Collaborative inference
资金
- National Key R&D Program of China [2017YFB0202002]
- Science Fund for Creative Research Groups of the National Natural Science Foundation of China [61521092]
- Key Program of National Natural Science Foundation of China [61432018, 61332009, U1736208]
Recently, deep neural networks (DNNs) have been widely applied in mobile intelligent applications. The inference for the DNNs is usually performed in the cloud. However, it leads to a large overhead of transmitting data via wireless network. In this paper, we demonstrate the advantages of the cloud-edge collaborative inference with quantization. By analyzing the characteristics of layers in DNNs, an auto-tuning neural network quantization framework for collaborative inference is proposed. We study the effectiveness of mixed-precision collaborative inference of state-of-the-art DNNs by using ImageNet dataset. The experimental results show that our framework can generate reasonable network partitions and reduce the storage on mobile devices with trivial loss of accuracy.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据