add instructions for sensereid

pull/62/head
KaiyangZhou 2018-08-17 10:55:27 +01:00
parent 3bc884770f
commit cc1e23049a
2 changed files with 19 additions and 1 deletions

View File

@ -10,6 +10,8 @@ If you wanna store datasets in another directory, you need to specify `--root pa
Please do not call image dataset when running video reid scripts, otherwise error would occur, and vice versa.
### Image ReID
**Market1501** [7]:
1. Download dataset to `data/` from http://www.liangzheng.org/Project/project_reid.html.
2. Extract dataset and rename to `market1501`. The data structure would look like:
@ -93,6 +95,20 @@ prid450s/
```
**SenseReID** [32]:
1. Create `sensereid/` under `data/` or your custom data dir.
2. Download dataset from this [link](https://drive.google.com/file/d/0B56OfSrVI8hubVJLTzkwV2VaOWM/view) and extract to `sensereid/`. The final folder structure should look like
```
sensereid/
SenseReID/
test_probe/
test_gallery/
```
3. The command for using SenseReID is `-d sensereid`. Note that SenseReID is for test purpose only so training images are unavailable. Please use `--evaluate` along with `-d sensereid`.
### Video ReID
**MARS** [8]:
1. Create a directory named `mars/` under `data/`.
2. Download dataset to `data/mars/` from http://www.liangzheng.com.cn/Project/project_mars.html.

View File

@ -27,6 +27,7 @@ Image reid datasets:
- GRID [29]
- CUHK01 [30]
- PRID450S [31]
- SenseReID [32]
Video reid datasets:
- MARS [8]
@ -141,4 +142,5 @@ Aggregated Residual Transformations for Deep Neural Networks. CVPR 2017.](https:
[28] [Gray et al. Evaluating appearance models for recognition, reacquisition, and tracking. PETS 2007.](http://citeseerx.ist.psu.edu/viewdoc/download?doi=10.1.1.331.7285&rep=rep1&type=pdf) <br />
[29] [Loy et al. Multi-camera activity correlation analysis. CVPR 2009.](https://ieeexplore.ieee.org/document/5206827/) <br />
[30] [Li et al. Human Reidentification with Transferred Metric Learning. ACCV 2012.](http://www.ee.cuhk.edu.hk/~xgwang/papers/liZWaccv12.pdf) <br />
[31] [Roth et al. Mahalanobis Distance Learning for Person Re-Identification. PR 2014.](https://pdfs.semanticscholar.org/f62d/71e701c9fd021610e2076b5e0f5b2c7c86ca.pdf) <br />
[31] [Roth et al. Mahalanobis Distance Learning for Person Re-Identification. PR 2014.](https://pdfs.semanticscholar.org/f62d/71e701c9fd021610e2076b5e0f5b2c7c86ca.pdf) <br />
[32] [Zhao et al. Spindle Net: Person Re-identification with Human Body Region Guided Feature Decomposition and Fusion. CVPR 2017.](http://openaccess.thecvf.com/content_cvpr_2017/papers/Zhao_Spindle_Net_Person_CVPR_2017_paper.pdf) <br />