Implement of paper:Learning Discriminative Features with Multiple Granularities for Person Re-Identification

• Python >= 3.5
• PyTorch >= 0.4.0
• torchvision
• scipy
• numpy
• scikit_learn

The data structure would look like:

data/
    bounding_box_train/
    bounding_box_test/
    query/

Download from here

Download from here

1. Download cuhk03 dataset from "http://www.ee.cuhk.edu.hk/~xgwang/CUHK_identification.html"
2. Unzip the file and you will get the cuhk03_release dir include cuhk-03.mat
3. Download "cuhk03_new_protocol_config_detected.mat" from "https://github.com/zhunzhong07/person-re-ranking/tree/master/evaluation/data/CUHK03" and put it with cuhk-03.mat. We need this new protocol to split the dataset.

python utils/transform_cuhk03.py --src <path/to/cuhk03_release> --dst <path/to/save>

NOTICE:You need to change num_classes in network depend on how many people in your train dataset! e.g. 751 in Market1501

Pretrained weight download from google drive or baidu drive password:mrl5

You can specify more parameters in opt.py

python main.py --mode train --data_path <path/to/Market-1501-v15.09.15> 

Use pretrained weight or your trained weight

python main.py --mode evaluate --data_path <path/to/Market-1501-v15.09.15> --weight <path/to/weight_name.pt> 

Visualize rank10 query result of one image(query from bounding_box_test)

Extract features will take a few munutes, or you can save features as .mat file for multiple uses

python main.py --mode vis --query_image <path/to/query_image> --weight <path/to/weight_name.pt> 

@ARTICLE{2018arXiv180401438W,
    author = {{Wang}, G. and {Yuan}, Y. and {Chen}, X. and {Li}, J. and {Zhou}, X.},
    title = "{Learning Discriminative Features with Multiple Granularities for Person Re-Identification}",
    journal = {ArXiv e-prints},
    year = 2018,
}