GV

GeezerVison

The World Wide Web, restored to 800 pixels of glory.

Home|About|Gaming cabinet|Archives|How it works|Starter sites

On this site

  • Sign in
  • ActionsCI/CD and automation
  • CodespacesCloud development environments
  • All Features
  • Documentation
  • Training
  • Certifications
  • Build with Copilot
  • Customize Copilot
  • Integrations
  • Trending repos
  • GitHub Sponsors
  • Developer articles
  • Enterprises

This view

  • Original page
  • New address

GeezerVison is showing github.com — GitHub - deep-learning-algorithm/ResNet: Implementation of ResNet series Algorithm

BranchesTags
Open more actions menu

Latest commit

 

History

70 Commits
70 Commits

Folders and files

NameName
Last commit message
Last commit date
docs
docs
 
 
py
py
 
 
.gitignore
.gitignore
 
 
LICENSE
LICENSE
 
 
README.md
README.md
 
 
mkdocs.yml
mkdocs.yml
 
 
requirements.txt
requirements.txt
 
 

Repository files navigation

ResNet

Documentation Status standard-readme compliant Conventional Commits Commitizen friendly

ResNet算法实现

实现ResNet及后续版本,同时实现了相关模型:

  • ResNet v1/v2
  • DenseNet
CNN Architecture Data Type (bit) Model Size (MB) GFlops (1080Ti) Top-1 Acc(VOC 07+12) Top-5 Acc(VOC 07+12)
ResNet-18 32 44.607 3.641 89.98% 99.29%
ResNet-34 32 83.180 7.348 90.01% 99.29%
ResNet-34_v2 32 83.177 7.349 90.50% 99.29%
ResNet-50 32 97.492 8.223 89.37% 99.39%
ResNet-101 32 169.942 15.668 90.66% 99.35%
ResNet-101_v2 32 169.926 15.668 90.85% 99.48%
DenseNet-121 32 30.437 5.731 89.86% 99.20%

内容列表

  • 背景
  • 安装
  • 用法
  • 主要维护人员
  • 致谢
  • 参与贡献方式
  • 许可证

背景

  • Deep Residual Learning for Image Recognition
  • Identity Mappings in Deep Residual Networks
  • Wide Residual Networks
  • Aggregated Residual Transformations for Deep Neural Networks
  • Densely Connected Convolutional Networks

安装

文档工具依赖

# 文档工具依赖
$ pip install -r requirements.txt

python库依赖

$ cd py
$ pip install -r requirements.txt

用法

文档浏览

有两种使用方式

  1. 在线浏览文档:ResNet

  2. 本地浏览文档,实现如下:

    $ git clone https://github.com/zjZSTU/ResNet.git
    $ cd ResNet
    $ mkdocs serve
    

    启动本地服务器后即可登录浏览器localhost:8000

主要维护人员

  • zhujian - Initial work - zjZSTU

致谢

引用

@misc{he2015deep,
    title={Deep Residual Learning for Image Recognition},
    author={Kaiming He and Xiangyu Zhang and Shaoqing Ren and Jian Sun},
    year={2015},
    eprint={1512.03385},
    archivePrefix={arXiv},
    primaryClass={cs.CV}
}

@misc{he2016identity,
    title={Identity Mappings in Deep Residual Networks},
    author={Kaiming He and Xiangyu Zhang and Shaoqing Ren and Jian Sun},
    year={2016},
    eprint={1603.05027},
    archivePrefix={arXiv},
    primaryClass={cs.CV}
}

@misc{huang2016densely,
    title={Densely Connected Convolutional Networks},
    author={Gao Huang and Zhuang Liu and Laurens van der Maaten and Kilian Q. Weinberger},
    year={2016},
    eprint={1608.06993},
    archivePrefix={arXiv},
    primaryClass={cs.CV}
}

@misc{pascal-voc-2007,
	author = "Everingham, M. and Van~Gool, L. and Williams, C. K. I. and Winn, J. and Zisserman, A.",
	title = "The {PASCAL} {V}isual {O}bject {C}lasses {C}hallenge 2007 {(VOC2007)} {R}esults",
	howpublished = "http://www.pascal-network.org/challenges/VOC/voc2007/workshop/index.html"}

@misc{pascal-voc-2012,
	author = "Everingham, M. and Van~Gool, L. and Williams, C. K. I. and Winn, J. and Zisserman, A.",
	title = "The {PASCAL} {V}isual {O}bject {C}lasses {C}hallenge 2012 {(VOC2012)} {R}esults",
	howpublished = "http://www.pascal-network.org/challenges/VOC/voc2012/workshop/index.html"}

参与贡献方式

欢迎任何人的参与!打开issue或提交合并请求。

注意:

  • GIT提交,请遵守Conventional Commits规范
  • 语义版本化,请遵守Semantic Versioning 2.0.0规范
  • README编写,请遵守standard-readme规范

许可证

Apache License 2.0 © 2020 zjZSTU

About

Implementation of ResNet series Algorithm

Topics

densenet-201densenet-264densetnetdensetnet-121densetnet-169pytorchresidual-learningresidual-networkresnetresnet-101resnet-152resnet-18resnet-34resnet-50

Resources

Readme
Apache-2.0 license
Activity
Custom properties

Stars

2 stars

Watchers

1 watching

Forks

1 fork
Report repository

Releases

Packages

Used by

Contributors

Languages

You are visitor 01402503 — GeezerVison does not store the pages you look up.
Best viewed with Netscape Navigator 4.7 or Internet Explorer 6 at 800×600. No cookies required.