SiamCAR: Siamese Fully Convolutional Classification and Regression for Visual Tracking (CVPR 2020, Oral)
No Data
This code has been tested on Ubuntu 16.04, Python 3.6, Pytorch 0.4.1/1.2.0, CUDA 9.0. Please install related libraries before running this code:
bash pip install -r requirements.txt
Download the pretrained model:
general_model code: lw7w
got10k_model code: p4zx
LaSOT_model code: 6wer
(The model in google Driver)
and put them into
tools/snapshotdirectory.
Download testing datasets and put them into
test_datasetdirectory. Jsons of commonly used datasets can be downloaded from BaiduYun or Google driver. If you want to test the tracker on a new dataset, please refer to pysot-toolkit to set test_dataset.
python test.py \ --dataset UAV123 \ # dataset_name --snapshot snapshot/general_model.pth # tracker_name
The testing result will be saved in the
results/dataset_name/tracker_namedirectory.
Download the datasets: * VID * YOUTUBEBB (code: v7s6) * DET * COCO * GOT-10K * LaSOT
Note:
train_dataset/dataset_name/readme.mdhas listed detailed operations about how to generate training datasets.
Download pretrained backbones from google driver or BaiduYun (code: 7n7d) and put them into
pretrained_modelsdirectory.
To train the SiamCAR model, run
train.pywith the desired configs:
cd tools python train.py
We provide the tracking results (code: 8c7b) (results in google driver )of GOT10K, LaSOT, OTB and UAV. If you want to evaluate the tracker, please put those results into
resultsdirectory.
python eval.py \ --tracker_path ./results \ # result path --dataset UAV123 \ # dataset_name --tracker_prefix 'general_model' # tracker_name
The code is implemented based on pysot. We would like to express our sincere thanks to the contributors.
If you use SiamCAR in your work please cite our paper:
@InProceedings{Guo2020CVPR,
author = {Guo, Dongyan and Wang, Jun and Cui, Ying and Wang, Zhenhua and Chen, Shengyong},
title = {SiamCAR: Siamese Fully Convolutional Classification and Regression for Visual Tracking},
booktitle = {The IEEE Conference on Computer Vision and Pattern Recognition (CVPR)},
month = {June},
year = {2020}
}