Code Monkey home page Code Monkey logo

ssdlite-pytorch-mobilenext's Introduction

AcadHomepage

一个现代、响应式的个人学术主页



一些例子:

主要特点

  • 自动更新谷歌学术引用: 借助谷歌学术爬虫和github action功能,本仓库可以自动更新作者的引用数和论文引用数。
  • 支持谷歌Analytics: 你可以通过简单的配置来实现使用谷歌Analytics跟踪网页的流量。
  • 响应式的: 此主页会针对不同的屏幕尺寸自动调整布局。
  • 美观而简约: 此主页美观而简约,适合个人学术主页的搭建。
  • 搜索引擎优化: 搜索引擎优化 (SEO) 帮助搜索引擎轻松找到您在主页上发布的信息,然后将其与类似网站进行排名,并获得排名优势。

快速开始

  1. Fork本仓库到USERNAME/USERNAME.github.io,其中USERNAME是你的github用户名。
  2. 配置谷歌学术引用爬虫:
    1. 在你的谷歌学术引用页面的url里找到你的谷歌学术ID:例如,在url https://scholar.google.com/citations?user=SCHOLAR_ID 中,SCHOLAR_ID部分即为你的谷歌学术ID。
    2. 在github本仓库页面的Settings -> Secrets -> Actions -> New repository secret中,添加GOOGLE_SCHOLAR_ID变量:name=GOOGLE_SCHOLAR_IDvalue=SCHOLAR_ID
    3. 在github本仓库页面的Action中,点击*"I understand my workflows, go ahead and enable them"*启用workflows by clicking *"。本action将会谷歌学术引用的统计量数据gs_data.json到本仓库的google-scholar-stats分支中。每次修改main分支的内容会触发该action。本action也会在每天08:00 UTC定时触发。
  3. 使用 favicon-generator生成favicon(网页icon文件),并下载所有文件到REPO/images
  4. 修改主页配置文件_config.yml:
    1. title: 主页标题
    2. description: 主页的描述
    3. repository: USER_NAME/REPO_NAME
    4. google_analytics_id (可选的): 谷歌Analytics ID
    5. SEO相关的键值 (可选的): 从搜索引擎的控制台里获得对应的ID (例如:Google, Bing and Baidu),然后粘贴到这里。
    6. author: 主页作者信息,包括其他网页、Email、所在城市、大学等。
    7. google_scholar_stats_use_cdn: 使用CDN读取存储于https://raw.githubusercontent.com/的google scholar引用统计数据,防止中国大陆地区被墙无法访问的情况。但是CDN有缓存,因此google_scholar_stats_use_cdn : True时,引用数据更新会有延迟。
    8. 更多的配置信息在注释中有详细描述。
  5. 将你的主页内容添加到 _pages/about.md.
  6. 你的主页将会被部署到https://USERNAME.github.io.

本地调试

  1. 使用git clone将本项目克隆到本地。
  2. 安装Jekyll的构建环境,包括RubyRubyGemsGCCMake。可参考该教程
  3. 运行 bash run_server.sh 来启动Jekyll实时重载服务器。
  4. 在浏览器里打开 http://127.0.0.1:4000。如果你修改了网页的源码,服务器会自动重新编译并刷新页面。
  5. 当你修改完毕你的页面以后, 使用git命令,commit你的改动并push到你的github仓库中。

Acknowledges

  • AcadHomepage incorporates Font Awesome, which is distributed under the terms of the SIL OFL 1.1 and MIT License.
  • AcadHomepage is influenced by the github repo mmistakes/minimal-mistakes, which is distributed under the MIT License.
  • AcadHomepage is influenced by the github repo academicpages/academicpages.github.io, which is distributed under the MIT License.

ssdlite-pytorch-mobilenext's People

Contributors

houqb avatar

Stargazers

 avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar

Watchers

 avatar  avatar  avatar

ssdlite-pytorch-mobilenext's Issues

How could I use the pretrained model for evaluation?

@Andrew-Qibin I am trying to test the results based on the given pre-trained model. But it seems that tthe .pth provided is saved from .state_dict(), which cannot be used to load the structure of the network. Could you please show how can I evaluate the network? Thank you.

help

hi,,in ssdlite-pytorch-mobilenext. The compression pack of pretrained models is damaged. I really need this weight pack,Please help me,Please!thanks!

Help, train on voc

Hello, thanks for your excellent job. I use it to train voc datasets. After 40000 iterations, the results are as follows. It seems the miou only 7%? Can you help me, where I am wrong?
2021-09-15 03:23:16,957 SSD.trainer INFO: Total training time: 2 days, 9:11:49 (5.1477 s / it)
2021-09-15 03:23:16,981 SSD INFO: Start evaluating...
2021-09-15 03:23:17,036 SSD.inference INFO: Evaluating voc_2007_test dataset(4952 images):
2021-09-15 03:24:05,197 SSD.inference WARNING: Number of images that were gathered from multiple processes is not a contiguous set. Some images might be missing from the evaluation
2021-09-15 03:24:37,639 SSD.inference INFO: mAP: 0.0723
aeroplane : 0.0652
bicycle : 0.0396
bird : 0.1066
boat : 0.1150
bottle : 0.0238
bus : 0.0395
car : 0.0527
cat : 0.1141
chair : 0.1031
cow : 0.0233
diningtable : 0.0628
dog : 0.0737
horse : 0.0834
motorbike : 0.0736
person : 0.0704
pottedplant : 0.0180
sheep : 0.1083
sofa : 0.0568
train : 0.1090
tvmonitor : 0.1067

mobilenet_v2 pascal voc model and weight are mismatched

I try to use pretrained weigth of mobilenet_v2 pascal voc and test using the given config file. However, it seems like the model and weight are mismatch. I have tried to manually adjust the channel numbers of extra layers to match the weight but accuracy is not correct.
image
ed.

Confusion about the number of model parameters.

Thank you for your wonderful research. Regarding some of your code, I have a few confusions. When I selected mobilenet_v2ussd320_voc0712.yaml as the configuration file, I calculated the model parameter count to be 3.43M, while in Table 8 of your paper, the model parameter count is 4.3M. Is there anything else that needs to be changed in the configuration file or elsewhere?? Looking forward to your reply very much, thank you.....

Recommend Projects

  • React photo React

    A declarative, efficient, and flexible JavaScript library for building user interfaces.

  • Vue.js photo Vue.js

    🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.

  • Typescript photo Typescript

    TypeScript is a superset of JavaScript that compiles to clean JavaScript output.

  • TensorFlow photo TensorFlow

    An Open Source Machine Learning Framework for Everyone

  • Django photo Django

    The Web framework for perfectionists with deadlines.

  • D3 photo D3

    Bring data to life with SVG, Canvas and HTML. 📊📈🎉

Recommend Topics

  • javascript

    JavaScript (JS) is a lightweight interpreted programming language with first-class functions.

  • web

    Some thing interesting about web. New door for the world.

  • server

    A server is a program made to process requests and deliver data to clients.

  • Machine learning

    Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.

  • Game

    Some thing interesting about game, make everyone happy.

Recommend Org

  • Facebook photo Facebook

    We are working to build community through open source technology. NB: members must have two-factor auth.

  • Microsoft photo Microsoft

    Open source projects and samples from Microsoft.

  • Google photo Google

    Google ❤️ Open Source for everyone.

  • D3 photo D3

    Data-Driven Documents codes.