mirrors/deep-person-reid
1
0
Fork 0
mirror of https://github.com/KaiyangZhou/deep-person-reid.git synced 2025-06-03 14:53:23 +08:00
Code Issues Projects Releases Wiki Activity

update readme: add keys to datasets

Browse Source
This commit is contained in:
KaiyangZhou 2018-11-10 11:49:34 +00:00
parent 7cec0167cd
commit 80a26caf70
1 changed files with 16 additions and 14 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

30
README.md
View File

@ -26,21 +26,23 @@ It has the following features:
## Datasets
Image-reid datasets:
- [Market1501](https://www.cv-foundation.org/openaccess/content_iccv_2015/papers/Zheng_Scalable_Person_Re-Identification_ICCV_2015_paper.pdf)
- [CUHK03](https://www.cv-foundation.org/openaccess/content_cvpr_2014/papers/Li_DeepReID_Deep_Filter_2014_CVPR_paper.pdf)
- [DukeMTMC-reID](https://arxiv.org/abs/1701.07717)
- [MSMT17](https://arxiv.org/abs/1711.08565)
- [VIPeR](http://citeseerx.ist.psu.edu/viewdoc/download?doi=10.1.1.331.7285&rep=rep1&type=pdf)
- [GRID](http://www.eecs.qmul.ac.uk/~txiang/publications/LoyXiangGong_cvpr_2009.pdf)
- [CUHK01](http://www.ee.cuhk.edu.hk/~xgwang/papers/liZWaccv12.pdf)
- [PRID450S](https://pdfs.semanticscholar.org/f62d/71e701c9fd021610e2076b5e0f5b2c7c86ca.pdf)
- [SenseReID](http://openaccess.thecvf.com/content_cvpr_2017/papers/Zhao_Spindle_Net_Person_CVPR_2017_paper.pdf)
- [Market1501](https://www.cv-foundation.org/openaccess/content_iccv_2015/papers/Zheng_Scalable_Person_Re-Identification_ICCV_2015_paper.pdf) (`market1501`)
- [CUHK03](https://www.cv-foundation.org/openaccess/content_cvpr_2014/papers/Li_DeepReID_Deep_Filter_2014_CVPR_paper.pdf) (`cuhk03`)
- [DukeMTMC-reID](https://arxiv.org/abs/1701.07717) (`dukemtmcreid`)
- [MSMT17](https://arxiv.org/abs/1711.08565) (`msmt17`)
- [VIPeR](http://citeseerx.ist.psu.edu/viewdoc/download?doi=10.1.1.331.7285&rep=rep1&type=pdf) (`viper`)
- [GRID](http://www.eecs.qmul.ac.uk/~txiang/publications/LoyXiangGong_cvpr_2009.pdf) (`grid`)
- [CUHK01](http://www.ee.cuhk.edu.hk/~xgwang/papers/liZWaccv12.pdf) (`cuhk01`)
- [PRID450S](https://pdfs.semanticscholar.org/f62d/71e701c9fd021610e2076b5e0f5b2c7c86ca.pdf) (`prid450s`)
- [SenseReID](http://openaccess.thecvf.com/content_cvpr_2017/papers/Zhao_Spindle_Net_Person_CVPR_2017_paper.pdf) (`sensereid`)
Video-reid datasets:
- [MARS](http://www.liangzheng.org/1320.pdf)
- [iLIDS-VID](https://www.eecs.qmul.ac.uk/~sgg/papers/WangEtAl_ECCV14.pdf)
- [PRID2011](https://pdfs.semanticscholar.org/4c1b/f0592be3e535faf256c95e27982db9b3d3d3.pdf)
- [DukeMTMC-VideoReID](http://openaccess.thecvf.com/content_cvpr_2018/papers/Wu_Exploit_the_Unknown_CVPR_2018_paper.pdf)
- [MARS](http://www.liangzheng.org/1320.pdf) (`mars`)
- [iLIDS-VID](https://www.eecs.qmul.ac.uk/~sgg/papers/WangEtAl_ECCV14.pdf) (`ilidsvid`)
- [PRID2011](https://pdfs.semanticscholar.org/4c1b/f0592be3e535faf256c95e27982db9b3d3d3.pdf) (`prid2011`)
- [DukeMTMC-VideoReID](http://openaccess.thecvf.com/content_cvpr_2018/papers/Wu_Exploit_the_Unknown_CVPR_2018_paper.pdf) (`dukemtmcvidreid`)
The keys to use these datasets are enclosed in the parentheses. See [torchreid/datasets/\_\_init__.py](torchreid/datasets/__init__.py) for details. The data managers of image reid and video reid are implemented in [torchreid/data_manager.py](torchreid/data_manager.py).
Instructions regarding how to prepare (and do evaluation on) these datasets can be found in [DATASETS.md](DATASETS.md).
@ -68,7 +70,7 @@ Instructions regarding how to prepare (and do evaluation on) these datasets can
- [PCB](https://arxiv.org/abs/1711.09349)
- [MLFN](https://arxiv.org/abs/1803.09132)
Please refer to [torchreid/models/\_\_init__.py](torchreid/models/__init__.py) for more details. In the [MODEL_ZOO](MODEL_ZOO.md), we provide pretrained models and the training scripts to reproduce the results.
Please refer to [torchreid/models/\_\_init__.py](torchreid/models/__init__.py) for the keys to build these models. In the [MODEL_ZOO](MODEL_ZOO.md), we provide pretrained model weights and the training scripts to reproduce the results.
## Losses
- `xent`: cross entropy loss (enable the [label smoothing regularizer](https://www.cv-foundation.org/openaccess/content_cvpr_2016/papers/Szegedy_Rethinking_the_Inception_CVPR_2016_paper.pdf) by `--label-smooth`).