Reading Note: MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications
2017-07-24 08:46
615 查看
TITLE: MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications
AUTHOR: Andrew G. Howard, Menglong Zhu, Bo Chen, Dmitry Kalenichenko, Weijun Wang, Tobias Weyand, Marco Andreetto, Hartwig Adam
ASSOCIATION: Google
FROM: arXiv:1704.04861
Two simple global hyper-parameters that efficiently trade off between latency and
accuracy are introduced.
The standard convolution has the computation cost of
Dk⋅Dk⋅M⋅N⋅DF⋅DF
Depthwise separable convolution costs
Dk⋅Dk⋅M⋅DF⋅DF+M⋅N⋅DF⋅DF
AUTHOR: Andrew G. Howard, Menglong Zhu, Bo Chen, Dmitry Kalenichenko, Weijun Wang, Tobias Weyand, Marco Andreetto, Hartwig Adam
ASSOCIATION: Google
FROM: arXiv:1704.04861
CONTRIBUTIONS
A class of efficient models called MobileNets for mobile and embedded vision applications is proposed, which are based on a streamlined architecture that uses depthwise separable convolutions to build light weight deep neural networksTwo simple global hyper-parameters that efficiently trade off between latency and
accuracy are introduced.
MobileNet Architecture
The core layer of MobileNet is depthwise separable filters, named as Depthwise Separable Convolution. The network structure is another factor to boost the performance. Finally, the width and resolution can be tuned to trade off between latency and accuracy.Depthwise Separable Convolution
Depthwise separable convolutions which is a form of factorized convolutions which factorize a standard convolution into a depthwise convolution and a 1×1 convolution called a pointwise convolution. In MobileNet, the depthwise convolution applies a single filter to each input channel. The pointwise convolution then applies a 1×1 convolution to combine the outputs the depthwise convolution. The following figure illustrates the difference between standard convolution and depthwise separable convolution.The standard convolution has the computation cost of
Dk⋅Dk⋅M⋅N⋅DF⋅DF
Depthwise separable convolution costs
Dk⋅Dk⋅M⋅DF⋅DF+M⋅N⋅DF⋅DF
MobileNet Structure
The following table shows the structure of MobileNetWidth and Resolution Multiplier
The Width Multiplier is used to reduce the number of the channels. The Resolution Multiplier is used to reduce the input image of the network.Comparison
相关文章推荐
- MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications
- MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications
- MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications
- 【论文学习】MobileNets:Efficient Convolutional Neural Networks for Mobile Vision Applications
- 手机CNN网络模型--MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications
- MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications
- MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications个人理解
- 论文阅读笔记:MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications
- [论文解读] MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications
- [论文阅读]MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications
- 论文笔记——MobileNets(Efficient Convolutional Neural Networks for Mobile Vision Applications)
- 网络小型化MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications
- MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications
- How to design DL model(1):Efficient Convolutional Neural Networks for Mobile Vision Applications
- MobileNets: Efficient Convolutional Neural Networks for Mobile Vision
- 论文记录_MobileNets Efficient Convolutional Neural Networks for Mobile Vision Application
- 论文记录_MobileNets Efficient Convolutional Neural Networks for Mobile Vision Application
- 论文阅读笔记:ShuffleNet: An Extremely Efficient Convolutional Neural Network for Mobile Devices
- 网络量化——Quantized Convolutional Neural Networks for Mobile Devices
- Highly Efficient Forward and Backward Propagation of Convolutional Neural Networks for Pixelwise Cla