热门文章

【参赛经验】深度学习入门指南:从零开始TinyMind汉字书法识别

Link 2018-04-20 14:13
主要是代码,介绍如何从零开始完成TinyMind汉字书法识别比赛的第一次提交
387 0 0

Fast.ai 深度学习实战课程 Lesson0 [中文字幕][免费观看]

AI科技大本营 2018-04-08 18:16
本节课不需要深入研究高水平数学问题的情况下,学习如何建立最先进的深度学习模型。
542 2 0

搭建mxnet-gpu docker的pyhon remote kernel

dwSun 2018-04-08 17:52
起因 最近看mxnet的东西,打算给实验室的机器装一个mxnet的环境,无奈实验室里面机器已经装了tensorflow,运行了好久了,环境比较老。而mxnet可是支持最新的cuda9和cudnn7的。研究了一段时间后,发现cuda的docker镜像是个不错的选择。别问我为啥不编译tensorflow以获得cuda9和cudnn7的支持,谁再让我编译tensorflow,谁是XX。 试着装了一个cu
101 1 0

深度学习资料汇总

Jason 2018-04-19 18:45
深度学习资料汇总,各种书籍、视频、资料、课程链接,欢迎补充。
30 0 0

自然语言处理资料汇总

Jason 2018-04-19 18:48
自然语言处理资料汇总,各种书籍、视频、资料、课程链接,欢迎补充。
26 0 0

强化学习资料汇总

Jason 2018-04-19 18:51
强化学习资料汇总,各种书籍、视频、资料、课程链接,欢迎补充。
20 0 0
查看更多文章
热门论文
dwSun 2018-02-06 17:25

Inverted Residuals and Linear Bottlenecks: Mobile Networks for Classification, Detection and Segmentation EN

Mark Sandler,Andrew Howard, Menglong Zhu, Andrey Zhmoginov, Liang-Chieh Chen
发表时间:2018-01-16

In this paper we describe a new mobile architecture, MobileNetV2, that improves the state of the art performance of mobile models on multiple tasks and benchmarks as well as across a spectrum of different model sizes. We also describe efficient ways of applying these mobile models to object detection in a novel framework we call SSDLite. Additionally, we demonstrate how to build mobile semantic segmentation models through a reduced form of DeepLabv3 which we call Mobile DeepLabv3. The MobileNetV2 architecture is based on an inverted residual structure where the input and output of the residual block are thin bottleneck layers opposite to traditional residual models which use expanded representations in the input an MobileNetV2 uses lightweight depthwise convolutions to filter features in the intermediate expansion layer. Additionally, we find that it is important to remove non-linearities in the narrow layers in order to maintain representational power. We demonstrate that this improves performance and provide an intuition that led to this design. Finally, our approach allows decoupling of the input/output domains from the expressiveness of the transformation, which provides a convenient framework for further analysis. We measure our performance on Imagenet classification, COCO object detection, VOC image segmentation. We evaluate the trade-offs between accuracy, and number of operations measured by multiply-adds (MAdd), as well as the number of parameters

查看更多论文
热门算法实现