{"id":15032247,"url":"https://github.com/stvir/pysot","last_synced_at":"2025-05-14T14:07:33.482Z","repository":{"id":37492867,"uuid":"185398995","full_name":"STVIR/pysot","owner":"STVIR","description":"SenseTime Research platform for single object tracking, implementing algorithms like SiamRPN and SiamMask.","archived":false,"fork":false,"pushed_at":"2023-11-12T03:26:20.000Z","size":6506,"stargazers_count":4500,"open_issues_count":60,"forks_count":1108,"subscribers_count":160,"default_branch":"master","last_synced_at":"2025-05-09T09:02:12.557Z","etag":null,"topics":["computer-vision","siamese-network","tracking"],"latest_commit_sha":null,"homepage":"","language":"Python","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"apache-2.0","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/STVIR.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":"LICENSE","code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null,"governance":null,"roadmap":null,"authors":null,"dei":null,"publiccode":null,"codemeta":null}},"created_at":"2019-05-07T12:37:56.000Z","updated_at":"2025-04-27T13:01:56.000Z","dependencies_parsed_at":"2022-07-31T23:48:07.421Z","dependency_job_id":"c6e8f444-6f76-4010-ae0f-c32423ab5bcd","html_url":"https://github.com/STVIR/pysot","commit_stats":null,"previous_names":[],"tags_count":0,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/STVIR%2Fpysot","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/STVIR%2Fpysot/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/STVIR%2Fpysot/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/STVIR%2Fpysot/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/STVIR","download_url":"https://codeload.github.com/STVIR/pysot/tar.gz/refs/heads/master","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":254159944,"owners_count":22024566,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2022-07-04T15:15:14.044Z","host_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub","repositories_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories","repository_names_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repository_names","owners_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners"}},"keywords":["computer-vision","siamese-network","tracking"],"created_at":"2024-09-24T20:17:49.125Z","updated_at":"2025-05-14T14:07:33.455Z","avatar_url":"https://github.com/STVIR.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"# PySOT\n\n**PySOT** is a software system designed by SenseTime Video Intelligence Research team. It implements state-of-the-art single object tracking algorithms, including [SiamRPN](http://openaccess.thecvf.com/content_cvpr_2018/html/Li_High_Performance_Visual_CVPR_2018_paper.html) and [SiamMask](https://arxiv.org/abs/1812.05050). It is written in Python and powered by the [PyTorch](https://pytorch.org) deep learning framework. This project also contains a Python port of toolkit for evaluating trackers.\n\nPySOT has enabled research projects, including: [SiamRPN](http://openaccess.thecvf.com/content_cvpr_2018/html/Li_High_Performance_Visual_CVPR_2018_paper.html), [DaSiamRPN](https://arxiv.org/abs/1808.06048), [SiamRPN++](https://arxiv.org/abs/1812.11703), and [SiamMask](https://arxiv.org/abs/1812.05050).\n\n\u003cdiv align=\"center\"\u003e\n  \u003cimg src=\"demo/output/bag_demo.gif\" width=\"800px\" /\u003e\n  \u003cp\u003eExample SiamFC, SiamRPN and SiamMask outputs.\u003c/p\u003e\n\u003c/div\u003e\n\n## Introduction\n\nThe goal of PySOT is to provide a high-quality, high-performance codebase for visual tracking *research*. It is designed to be flexible in order to support rapid implementation and evaluation of novel research. PySOT includes implementations of the following visual tracking algorithms:\n\n- [SiamMask](https://arxiv.org/abs/1812.05050)\n- [SiamRPN++](https://arxiv.org/abs/1812.11703)\n- [DaSiamRPN](https://arxiv.org/abs/1808.06048)\n- [SiamRPN](http://openaccess.thecvf.com/content_cvpr_2018/html/Li_High_Performance_Visual_CVPR_2018_paper.html)\n- [SiamFC](https://arxiv.org/abs/1606.09549)\n\nusing the following backbone network architectures:\n\n- [ResNet{18, 34, 50}](https://arxiv.org/abs/1512.03385)\n- [MobileNetV2](https://arxiv.org/abs/1801.04381)\n- [AlexNet](https://papers.nips.cc/paper/4824-imagenet-classification-with-deep-convolutional-neural-networks)\n\nAdditional backbone architectures may be easily implemented. For more details about these models, please see [References](#references) below.\n\nEvaluation toolkit can support the following datasets:\n\n:paperclip: [OTB2015](http://faculty.ucmerced.edu/mhyang/papers/pami15_tracking_benchmark.pdf) \n:paperclip: [VOT16/18/19](http://votchallenge.net) \n:paperclip: [VOT18-LT](http://votchallenge.net/vot2018/index.html) \n:paperclip: [LaSOT](https://arxiv.org/pdf/1809.07845.pdf) \n:paperclip: [UAV123](https://arxiv.org/pdf/1804.00518.pdf)\n\n## Model Zoo and Baselines\n\nWe provide a large set of baseline results and trained models available for download in the [PySOT Model Zoo](MODEL_ZOO.md).\n\n## Installation\n\nPlease find installation instructions for PyTorch and PySOT in [`INSTALL.md`](INSTALL.md).\n\n## Quick Start: Using PySOT\n\n### Add PySOT to your PYTHONPATH\n```bash\nexport PYTHONPATH=/path/to/pysot:$PYTHONPATH\n```\n\n### Download models\nDownload models in [PySOT Model Zoo](MODEL_ZOO.md) and put the model.pth in the correct directory in experiments\n\n### Webcam demo\n```bash\npython tools/demo.py \\\n    --config experiments/siamrpn_r50_l234_dwxcorr/config.yaml \\\n    --snapshot experiments/siamrpn_r50_l234_dwxcorr/model.pth\n    # --video demo/bag.avi # (in case you don't have webcam)\n```\n\n### Download testing datasets\nDownload datasets and put them into `testing_dataset` directory. Jsons of commonly used datasets can be downloaded from [Google Drive](https://drive.google.com/drive/folders/10cfXjwQQBQeu48XMf2xc_W1LucpistPI) or [BaiduYun](https://pan.baidu.com/s/1js0Qhykqqur7_lNRtle1tA#list/path=%2F). If you want to test tracker on new dataset, please refer to [pysot-toolkit](https://github.com/StrangerZhang/pysot-toolkit) to setting `testing_dataset`. \n\n### Test tracker\n```bash\ncd experiments/siamrpn_r50_l234_dwxcorr\npython -u ../../tools/test.py \t\\\n\t--snapshot model.pth \t\\ # model path\n\t--dataset VOT2018 \t\\ # dataset name\n\t--config config.yaml\t  # config file\n```\nThe testing results will in the current directory(results/dataset/model_name/)\n\n### Eval tracker\nassume still in experiments/siamrpn_r50_l234_dwxcorr_8gpu\n``` bash\npython ../../tools/eval.py \t \\\n\t--tracker_path ./results \\ # result path\n\t--dataset VOT2018        \\ # dataset name\n\t--num 1 \t\t \\ # number thread to eval\n\t--tracker_prefix 'model'   # tracker_name\n```\n\n###  Training :wrench:\nSee [TRAIN.md](TRAIN.md) for detailed instruction.\n\n\n### Getting Help :hammer:\nIf you meet problem, try searching our GitHub issues first. We intend the issues page to be a forum in which the community collectively troubleshoots problems. But please do **not** post **duplicate** issues. If you have similar issue that has been closed, you can reopen it.\n\n- `ModuleNotFoundError: No module named 'pysot'`\n\n:dart:Solution: Run `export PYTHONPATH=path/to/pysot` first before you run the code.\n\n- `ImportError: cannot import name region`\n\n:dart:Solution: Build `region` by `python setup.py build_ext —-inplace` as decribled in [INSTALL.md](INSTALL.md).\n\n\n## References\n\n- [Fast Online Object Tracking and Segmentation: A Unifying Approach](https://arxiv.org/abs/1812.05050).\n  Qiang Wang, Li Zhang, Luca Bertinetto, Weiming Hu, Philip H.S. Torr.\n  IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2019.\n\n- [SiamRPN++: Evolution of Siamese Visual Tracking with Very Deep Networks](https://arxiv.org/abs/1812.11703).\n  Bo Li, Wei Wu, Qiang Wang, Fangyi Zhang, Junliang Xing, Junjie Yan.\n  IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2019.\n\n- [Distractor-aware Siamese Networks for Visual Object Tracking](https://arxiv.org/abs/1808.06048).\n  Zheng Zhu, Qiang Wang, Bo Li, Wu Wei, Junjie Yan, Weiming Hu.\n  The European Conference on Computer Vision (ECCV), 2018.\n\n- [High Performance Visual Tracking with Siamese Region Proposal Network](http://openaccess.thecvf.com/content_cvpr_2018/html/Li_High_Performance_Visual_CVPR_2018_paper.html).\n  Bo Li, Wei Wu, Zheng Zhu, Junjie Yan, Xiaolin Hu.\n  IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2018.\n\n- [Fully-Convolutional Siamese Networks for Object Tracking](https://arxiv.org/abs/1606.09549).\n  Luca Bertinetto, Jack Valmadre, João F. Henriques, Andrea Vedaldi, Philip H. S. Torr.\n  The European Conference on Computer Vision (ECCV) Workshops, 2016.\n  \n## Contributors\n\n- [Fangyi Zhang](https://github.com/StrangerZhang)\n- [Qiang Wang](http://www.robots.ox.ac.uk/~qwang/)\n- [Bo Li](http://bo-li.info/)\n- [Zhiyuan Chen](https://zyc.ai/)\n- [Jinghao Zhou](https://shallowtoil.github.io/)\n\n## License\n\nPySOT is released under the [Apache 2.0 license](https://github.com/STVIR/pysot/blob/master/LICENSE). \n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fstvir%2Fpysot","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fstvir%2Fpysot","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fstvir%2Fpysot/lists"}