SiamMask
1.0.0
新：现在包括培训和推理的代码！
这是针对Siammask（CVPR2019）的培训代码的官方实施。有关技术详细信息，请参考：
快速在线对象跟踪和细分：统一的方法
Qiang Wang*，Li Zhang*，Luca Bertinetto*，Weiming Hu，Philip HS Torr（*表示同等贡献）
CVPR 2019
[纸] [视频] [项目页面]
如果您发现此代码有用，请考虑引用：
@inproceedings{wang2019fast,
title={Fast online object tracking and segmentation: A unifying approach},
author={Wang, Qiang and Zhang, Li and Bertinetto, Luca and Hu, Weiming and Torr, Philip HS},
booktitle={Proceedings of the IEEE conference on computer vision and pattern recognition},
year={2019}
}
该代码已在Ubuntu 16.04，Python 3.6，Pytorch 0.4.1，CUDA 9.2，RTX 2080 GPU上进行了测试。
git clone https://github.com/foolwood/SiamMask.git && cd SiamMask
export SiamMask=$PWD
conda create -n siammask python=3.6
source activate siammask
pip install -r requirements.txt
bash make.sh
export PYTHONPATH=$PWD:$PYTHONPATH
cd $SiamMask /experiments/siammask_sharp
wget http://www.robots.ox.ac.uk/~qwang/SiamMask_VOT.pth
wget http://www.robots.ox.ac.uk/~qwang/SiamMask_DAVIS.pthdemo.py cd $SiamMask /experiments/siammask_sharp
export PYTHONPATH= $PWD : $PYTHONPATH
python ../../tools/demo.py --resume SiamMask_DAVIS.pth --config config_davis.json cd $SiamMask /data
sudo apt-get install jq
bash get_test_data.sh cd $SiamMask /experiments/siammask_sharp
wget http://www.robots.ox.ac.uk/~qwang/SiamMask_VOT.pth
wget http://www.robots.ox.ac.uk/~qwang/SiamMask_VOT_LD.pth
wget http://www.robots.ox.ac.uk/~qwang/SiamMask_DAVIS.pthbash test_mask_refine.sh config_vot.json SiamMask_VOT.pth VOT2016 0
bash test_mask_refine.sh config_vot.json SiamMask_VOT.pth VOT2018 0
bash test_mask_refine.sh config_vot.json SiamMask_VOT.pth VOT2019 0
bash test_mask_refine.sh config_vot18.json SiamMask_VOT_LD.pth VOT2016 0
bash test_mask_refine.sh config_vot18.json SiamMask_VOT_LD.pth VOT2018 0
python ../../tools/eval.py --dataset VOT2016 --tracker_prefix C --result_dir ./test/VOT2016
python ../../tools/eval.py --dataset VOT2018 --tracker_prefix C --result_dir ./test/VOT2018
python ../../tools/eval.py --dataset VOT2019 --tracker_prefix C --result_dir ./test/VOT2019bash test_mask_refine.sh config_davis.json SiamMask_DAVIS.pth DAVIS2016 0
bash test_mask_refine.sh config_davis.json SiamMask_DAVIS.pth DAVIS2017 0bash test_mask_refine.sh config_davis.json SiamMask_DAVIS.pth ytb_vos 0这些是该存储库的繁殖结果。所有结果都可以从我们的项目页面下载。
| 跟踪器 | vot2016 eao / a / r | vot2018 eao / a / r | 戴维斯2016 J / f | Davis2017 J / f | YouTube-Vos j_s / j_u / f_s / f_u | 速度 |
|---|---|---|---|---|---|---|
| Siammask-Box | 0.412/0.623/0.233 | 0.363/0.584/0.300 | - / - | - / - | - / - / - / - | 77 fps |
| 暹罗 | 0.433 / 0.639 / 0.214 | 0.380 / 0.609 / 0.276 | 0.713 / 0.674 | 0.543 / 0.585 | 0.602 / 0.451 / 0.582 / 0.477 | 56 fps |
| Siammask-d | 0.455 / 0.634 / 0.219 | 0.423 / 0.615 / 0.248 | - / - | - / - | - / - / - / - | 56 fps |
笔记：
-box从框分支报告了一个与轴对齐的边界框。-LD表示使用大数据集（YTB-BB+YTB-VOS+VID+COCO+DET）训练。 （该模型在Imagenet-1k数据集上进行了训练）
cd $SiamMask/experiments
wget http://www.robots.ox.ac.uk/~qwang/resnet.model
ls | grep siam | xargs -I {} cp resnet.model {}
cd $SiamMask/experiments/siammask_base/
bash run.sh
run.sh中的批次尺寸。bash test_all.sh -s 1 -e 20 -d VOT2018 -g 4 # test all snapshots with 4 GPUs # bash test_all.sh -m [best_test_model] -d VOT2018 -n [thread_num] -g [gpu_num] # 8 threads with 4 GPUS
bash test_all.sh -m snapshot/checkpoint_e12.pth -d VOT2018 -n 8 -g 4 # 8 threads with 4 GPUS cd $SiamMask/experiments/siammask_sharp
bash run.sh <best_base_model>
bash run.sh checkpoint_e12.pth
bash test_all.sh -s 1 -e 20 -d VOT2018 -g 4 cd $SiamMask/experiments/siamrpn_resnet
bash run.sh
bash test_all.sh -h
bash test_all.sh -s 1 -e 20 -d VOT2018 -g 4根据MIT许可获得许可。
