Git Product home page Git Product logo

yolov5_jde_tensorrt_for_track's Introduction

YoloV5_JDE_TensorRT_for_Track

Introduction

A multi object detect and track Library Based on tensorrt

一个基于TensorRT的多目标检测和跟踪融合算法库,可以同时支持行人的多目标检测和跟踪,当然也可以仅仅当检测库使用。

本算法的主框架采用了JDE+deepsort结构,其中由JDE算法检测出人的坐标与其对应的外观特征,然后基于deepsort的方法进行目标与运动轨迹的匹配。 JDE中的检测框架则采用了YOLOV5 L 的模型结构。

CSTrack3_0.yaml为本网络的模型结构,模型训练的代码大部分借鉴了CSTrack原文作者的开源项目,这里不再开源,大家有兴趣可以阅读CSTrack论文。 需要注意的是,本项目由于追求速度将CStrack的CCN和SAAN模块改成了JDE模块,也就是直接在anchor上提取reid特征并没有进行detect和reid的解耦模块。 如果读者需要的话可以自行修改,这样可以提升IDswich方面的性能。

Reference

Requirements

  • ubuntu 18.04 for x86
  • gcc/g++ >= 7.5.0
  • opencv >= 3.4.8
  • cuda >=10.0 cudnn >= 7.6
  • tensorRT >= 7.0.0
  • (Optional) ffmpeg (used in the video demo)

How to build and run

  • modify track/CMakeLists.txt Change opencv and tensorRT to your local directory
  • modify demo/CMakeLists.txt Change opencv and tensorRT to your local directory
  • modify demo/src/main.cpp Change video path to your local directory
  • sh make.sh
  • cd demo/build
  • ./itest

How to convert to tensort gie file

  • cd PytorchToTensorRTGIE
  • modify CMakeLists.txt Change opencv and tensorRT to your local directory
  • download jde.wts file
  • cd build
  • cmake ..
  • make
  • ./yolov5 -s
  • #Verify detect results
  • ./yolov5 -d ../sample/

Model

  • TensorRT GIE Model File: [Baidu] key: 6yc6.

Download the model and put it to /weight/

Download the model and put it to /PytorchToTensorRTGIE/

Video Demo

Acknowledgement

A large portion of code is borrowed from wang-xinyu/tensorrtx and sephirothhua/DeepSort_yoloV3-HOG_feature and , many thanks to their wonderful work!

yolov5_jde_tensorrt_for_track's People

Contributors

zhangwenguanghikvision 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.