Giters

haoranD / PersonReIdentification

My team was a finalist in the Walmart Deep Learning Computer Vision Competition. The project was part of the graduate machine learning course at Texas A&M. We built a CNN with mutual & transfer learning, and more in PyTorch.

Geek Repo:Geek Repo

Github PK Tool:Github PK Tool

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.

The architecture with a little more details

More Detailed MGN

About

My team was a finalist in the Walmart Deep Learning Computer Vision Competition. The project was part of the graduate machine learning course at Texas A&M. We built a CNN with mutual & transfer learning, and more in PyTorch.

Languages

Language:Python 97.0%Language:Shell 3.0%