This is a PyTorch implementation of SiameseRPN. This project is mainly based on SiamFC-PyTorch and DaSiamRPN.
For more details about siameseRPN please refer to the paper : High Performance Visual Tracking with Siamese Region Proposal Network by Bo Li, Junjie Yan,Wei Wu, Zheng Zhu, Xiaolin Hu.
This repository includes training and tracking codes.
This project can get 0.626 AUC on OTB100, and can get better result than the DaSiamRPN on 46 videos. Test results of 50 trained models on OTB100 are available in the eval_result.json. The best is the 38 epoch.
You should first get VID dataset and youtube-bb dataset. This process is a little troublesome. The part of code has not been formatted by now. If any one do this, please give a git pull request.
python bin/create_dataset_ytbid.py --vid-dir /PATH/TO/ILSVRC2015 --ytb-dir /PATH/TO/YT-BB --output-dir /PATH/TO/SAVE_DATA --num_threads 6
The command above will get a dataset, I put the dataset in the baiduyundisk. Use this data to create lmdb. 链接:https://pan.baidu.com/s/1QnQEM_jtc3alX8RyZ3i4-g 密码:myq4
python bin/create_lmdb.py --data-dir /PATH/TO/SAVE_DATA --output-dir /PATH/TO/RESULT.lmdb --num_threads 12
python bin/train_siamrpn.py --data_dir /PATH/TO/SAVE_DATA
Change the data_path first in the test_OTB.py, then run:
python bin/test_OTB.py -ms /PATH/TO/MODEL -v cvpr2013
python version == 3.6.5
pytorch version == 1.0.0
Pretrained model on Imagenet: https://drive.google.com/drive/folders/1HJOvl_irX3KFbtfj88_FVLtukMI1GTCR
Model with 0.626 AUC: https://pan.baidu.com/s/1vSvTqxaFwgmZdS00U3YIzQ keyword:v91k
[1] Li B , Yan J , Wu W , et al. High Performance Visual Tracking with Siamese Region Proposal Network[C]// 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). IEEE, 2018.