Need help with MGN-pytorch?
Click the “chat” button below for chat support from the developer who created it, or find similar developers for support.

About the developer

seathiefwang
245 Stars 96 Forks 8 Commits 19 Opened issues

Description

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

Services available

!
?

Need anything else?

Contributors list

# 73,103
Python
Shell
8 commits

Multiple Granularity Network

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

Dependencies

  • Python >= 3.5
  • PyTorch >= 0.4.0
  • TorchVision
  • Matplotlib
  • Argparse
  • Sklearn
  • Pillow
  • Numpy
  • Scipy
  • Tqdm

Train

Prepare training data

Download Market1501 training data.here

Begin to train

In the demo.sh file, add the Market1501 directory to --datadir

run

sh demo.sh

Result

| | mAP | rank1 | rank3 | rank5 | rank10 | | :------: | :------: | :------: | :------: | :------: | :------: | | 2018-7-22 | 92.17 | 94.60 | 96.53 | 97.06 | 98.01 | | 2018-7-24 | 93.53 | 95.34 | 97.06 | 97.68 | 98.49 | | last | 93.83 | 95.78 | 97.21 | 97.83 | 98.43 |

Download model file in here

The architecture of Multiple Granularity Network (MGN)

Multiple Granularity Network

Figure . Multiple Granularity Network architecture.

@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},
    archivePrefix = "arXiv",
    eprint = {1804.01438},
    primaryClass = "cs.CV",
    keywords = {Computer Science - Computer Vision and Pattern Recognition},
    year = 2018,
    month = apr,
    adsurl = {http://adsabs.harvard.edu/abs/2018arXiv180401438W},
    adsnote = {Provided by the SAO/NASA Astrophysics Data System}
}

We use cookies. If you continue to browse the site, you agree to the use of cookies. For more information on our use of cookies please see our Privacy Policy.