PaddlePaddle==2.1
The data structure will be like:
data/
bounding_box_test/
bounding_box_train/
gt_bbox/
gt_query/
query/
You can download dataset from here . The password is : RWZW
The weights we have already trained can be download here . The password is : qqqq
python main.py --mode train --data_path <path/to/Market-1501-v15.09.15>
You can find more parameters in opt.py
You can use our weight or your trained weight
python main.py --mode evaluate --data_path <path/to/Market-1501-v15.09.15> --weight <path/to/weight_name.pdparams>
python main.py --mode vis --query_image <path/to/query_image> --weight <path/to/weight_name.pdparams>
Visualize rank10 query result from bounding_box_test
@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,
}
https://github.com/GNAYUOHZ/ReID-MGN