CVPR2019跟踪算法SiamMask的配置(Fast Online Object Tracking and Segmentation: A Unifying Approach)

1、代码下载地址:

https://github.com/foolwood/SiamMask/

2、解压后进入工程路径

cd ~/Codes/SiamMask-master/

3、将当前路径设置成环境变量

export SiamMask=$PWD

4、设置python环境

conda create -n siammask python=3.5.2
source activate siammask
pip install -r requirements.txt
bash make.sh

注:

1)查看python的版本

python2 --version #查看python2安装版本

python3 --version #查看python3安装版本

2)正确安装conda,添加conda环境变量

 export PATH=$PATH:/home/user/anaconda3/bin/

 5、将工程添加到python路径

export PYTHONPATH=$PWD:$PYTHONPATH

6、下载预训练模型

http://www.robots.ox.ac.uk/~qwang/SiamMask_VOT.pth
http://www.robots.ox.ac.uk/~qwang/SiamMask_DAVIS.pth

由于服务器没联网,可以事先下载后拷贝到~/Codes/SiamMask-master/experiments/siammask_sharp路径中,

7、运行demo

cd $SiamMask/experiments/siammask_sharp
export PYTHONPATH=$PWD:$PYTHONPATH
python ../../tools/demo.py --resume SiamMask_DAVIS.pth --config config_davis.json

8、选择区域按回车,开始跟踪

 CVPR2019跟踪算法SiamMask的配置(Fast Online Object Tracking and Segmentation: A Unifying Approach)

 CVPR2019跟踪算法SiamMask的配置(Fast Online Object Tracking and Segmentation: A Unifying Approach)

上一篇:COCO数据集笔记


下一篇:Proposal, Tracking and Segmentation (PTS)论文解读