Giter Club home page Giter Club logo

centernet-tensorflow2.0's Introduction

Centernet-Tensorflow2.0

Tensorflow2.0下运行目标检测网络Centernet(基于see--的keras-centernet)
Centernet目标检测属于anchor-free系列的目标检测,相比于CornerNet做出了改进,使得检测速度和精度相比于one-stage和two-stage的框架都有不小的提高,尤其是与YOLOv3作比较,在相同速度的条件下,CenterNet的精度比YOLOv3提高了4个左右的点。

Centernet
CenterNet是一种用于所有类型的对象检测相关任务的元算法。官方代码解决了2D检测,3D检测和人体姿势估计。对象不是常用的锚盒,而是表示为点。CenterNet还删除了以前单次探测器所需的许多超参数和概念:

  • 没有更多的锚箱
  • 只有一个功能图表示所有比例
  • 没有边界框匹配
  • 没有非极大抑制

Centernet
Centernet
Centernet

权重下载:

点击网址或复制网址到浏览器链接即可下载,比较大,都在700MB以上.
对象检测:
https://github.com/see--/keras-centernet/releases/download/0.1.0/ctdet_coco_hg.hdf5
人体姿态估计:
https://github.com/see--/keras-centernet/releases/download/0.1.0/hpdet_coco_hg.hdf5

参考

see--/keras-centernet
感谢see--的代码,修改很少,修改后可以在Tensorflow2.0下运行,在1版本包含keras下,也可以运行。
kuku-sichuan/CenterNet

其他框架下的Centernet

xingyizhou-CenterNet-pytorch-官方
Duankaiwen-CenterNet-pytorch

运行:

python TF2-CenterNet/ctdet_image.py    #对象检测-图片
python TF2-CenterNet/hpdet_image.py    #人体姿态估计-图片
python TF2-CenterNet/ctdet_video.py    #对象检测-视频
python TF2-CenterNet/hpdet_video.py    #人体姿态估计-视频

#在coco2017val数据集上执行测试-对象检测:
python TF2-CenterNet/ctdet_coco.py --data val2017 --annotations annotations
#在coco2017val数据集上执行测试-人体姿态估计:
python TF2-CenterNet/hpdet_coco.py --data val2017 --annotations annotations

centernet-tensorflow2.0's People

Contributors

1044197988 avatar

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.