Official implementation of the TransT (CVPR2021) , including training code and trained models.
- 🏆 TransT-M wins VOT2021 Real-Time Challenge with EAOMultistart 0.550! The code will be released soon
[Paper] [Models(google)] [Models(baidu:iiau)] [Raw Results]
This work presents a attention-based feature fusion network, which effectively combines the template and search region features using attention. Specifically, the proposed method includes an ego-context augment module based on self-attention and a cross-feature augment module based on cross-attention. We present a Transformer tracking (named TransT) method based on the Siamese-like feature extraction backbone, the designed attention-based fusion mechanism, and the classification and regression head.
TransT is a very simple and efficient tracker,
without online update module, using the same model and hyparameter for all
test sets.
For VOT2020, we add a mask branch to generate mask, without any hyparameter-tuning. The code of the mask branch will be released soon.
| Model | LaSOT AUC (%) |
TrackingNet AUC (%) |
GOT-10k AO (%) |
VOT2020 EAO (%) |
TNL2K AUC (%) |
OTB100 AUC (%) |
NFS AUC (%) |
UAV123 AUC (%) |
Speed |
Params |
|---|---|---|---|---|---|---|---|---|---|---|
| TransT-N2 | 64.2 | 80.9 | 69.9 | - | - | 68.1 | 65.7 | 67.0 | 70fps | 16.7M |
| TransT-N4 | 64.9 | 81.4 | 72.3 | 49.5 | 51.0 | 69.4 | 65.7 | 69.1 | 50fps | 23.0M |
This document contains detailed instructions for installing the necessary dependencied for TransT. The instructions have been tested on Ubuntu 18.04 system.
-
Create and activate a conda environment
conda create -n transt python=3.7 conda activate transt
-
Install PyTorch
conda install -c pytorch pytorch=1.5 torchvision=0.6.1 cudatoolkit=10.2
-
Install other packages
conda install matplotlib pandas tqdm pip install opencv-python tb-nightly visdom scikit-image tikzplotlib gdown conda install cython scipy sudo apt-get install libturbojpeg pip install pycocotools jpeg4py pip install wget yacs pip install shapely==1.6.4.post2
-
Setup the environment
Create the default environment setting files.# Change directory to <PATH_of_TransT> cd TransT # Environment settings for pytracking. Saved at pytracking/evaluation/local.py python -c "from pytracking.evaluation.environment import create_default_local_file; create_default_local_file()" # Environment settings for ltr. Saved at ltr/admin/local.py python -c "from ltr.admin.environment import create_default_local_file; create_default_local_file()"
You can modify these files to set the paths to datasets, results paths etc.
- Add the project path to environment variables
Open ~/.bashrc, and add the following line to the end. Note to change <path_of_TransT> to your real path.export PYTHONPATH=<path_of_TransT>:$PYTHONPATH - Download the pre-trained networks
Download the network for TransT and put it in the directory set by "network_path" in "pytracking/evaluation/local.py". By default, it is set to pytracking/networks.
- Modify local.py to set the paths to datasets, results paths etc.
- Runing the following commands to train the TransT. You can customize some parameters by modifying transt.py
conda activate transt cd TransT/ltr python run_training.py transt transt
-
We integrated PySOT for evaluation. You can download json files in PySOT or here.
You need to specify the path of the model and dataset in the test.py.
net_path = '/path_to_model' #Absolute path of the model dataset_root= '/path_to_datasets' #Absolute path of the datasets
Then run the following commands.
conda activate TransT cd TransT python -u pysot_toolkit/test.py --dataset <name of dataset> --name 'transt' #test tracker #test tracker python pysot_toolkit/eval.py --tracker_path results/ --dataset <name of dataset> --num 1 --tracker_prefix 'transt' #eval tracker
The testing results will in the current directory(results/dataset/transt/)
-
You can also use pytracking to test and evaluate tracker. The results might be slightly different with PySOT due to the slight difference in implementation (pytracking saves results as integers, pysot toolkit saves the results as decimals).
If you meet problem, please try searching our Github issues, if you can't find solutions, feel free to open a new issue.
ImportError: cannot import name region
Solution: You can just delete from pysot_toolkit.toolkit.utils.region import vot_overlap, vot_float2str in test.py if you don't test VOT2019/18/16.
You can also build region by python setup.py build_ext --inplace in pysot_toolkit.
@inproceedings{TransT,
title={Transformer Tracking},
author={Chen, Xin and Yan, Bin and Zhu, Jiawen and Wang, Dong and Yang, Xiaoyun and Lu, Huchuan},
booktitle={CVPR},
year={2021}
}
This is a modified version of the python framework PyTracking based on Pytorch, also borrowing from PySOT and detr. We would like to thank their authors for providing great frameworks and toolkits.
-
Xin Chen (email:[email protected])
Feel free to contact me if you have additional questions.
React
Typescript
Django
Laravel
Facebook
Microsoft
Google
Alibaba
D3
Tencent