Skip to content
/ FairMOT Public
forked from ifzhang/FairMOT

A simple baseline for one-shot multi-object tracking

License

Notifications You must be signed in to change notification settings

isangu/FairMOT

 
 

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

75 Commits
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

Installation

  • Install dependencies. We use python 3.7 and pytorch >= 1.2.0
1. clone후 conda install pytorch==1.2.0 torchvision==0.4.0 cudatoolkit=10.0 -c pytorch로 torch 및 torchvision 설치  

2. pip install -r requirements.txt로 관련 패키지 설치  

3. src/lib/models/networks/DCNv2_new sh make.sh 실행  

4. 아래 링크에 있는 all_hrnet_v2_w18.pth 및 hrnetv2_w18_imagenet_pretrained.pth파일 다운로드 후 models 폴더 새로 만들어서 fairmot/models 위치에 해당 .pth파일을 넣어 주시면 됩니다.  

HRNetV2_W18: [Google] [Baidu, code: z4ft].
HRNetV2 ImageNet pretrained model: HRNetV2-W18 official
After downloading, you should put the baseline model in the following structure:

${FAIRMOT_ROOT}
   └——————models
           └——————all_hrnet_v2_w18.pth
           └——————...

Demo

python demo.py를 이용하면 WebCam에서 동작하는 데모 파일을 실행하실 수 있습니다.

About

A simple baseline for one-shot multi-object tracking

Resources

License

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages

  • Python 61.8%
  • Cuda 19.4%
  • C++ 14.9%
  • C 3.1%
  • Other 0.8%