deep-person-reid

This repo contains pytorch implementations of deep person re-identification approaches.

We will actively maintain this repo.

Install

1. cd to the folder where you want to download this repo.
2. run git clone https://github.com/KaiyangZhou/deep-person-reid.

Prepare data

Create a directory to store reid datasets under this repo via

cd deep-person-reid/
mkdir data/

Market1501 [7]:

1. download dataset to data/ from http://www.liangzheng.org/Project/project_reid.html.
2. extract dataset and rename to market1501.

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.
3. extract bbox_train.zip and bbox_test.zip.
4. download split information from https://github.com/liangzheng06/MARS-evaluation/tree/master/info and put info/ in data/mars. (we want to follow the standard split in [8])

Models

• models/ResNet.py: ResNet50 [1], ResNet50M [2].
• models/DenseNet.py: DenseNet121 [3].

Train

Training codes are implemented in

• train_img_model_xent.py: train image model with cross entropy loss.
• train_img_model_xent_htri.py: train image model with combination of cross entropy loss and hard triplet loss.
• train_vid_model_xent.py: train video model with cross entropy loss.
• train_vid_model_xent_htri.py: train video model with combination of cross entropy loss and hard triplet loss.

For example, to train an image reid model using ResNet50 and cross entropy loss, run

python train_img_model_xent.py -d market1501 -a resnet50 --max-epoch 60 --train-batch 32 --test-batch 32 --stepsize 20 --eval-step 20 --save-dir log/resnet50 --gpu-devices 0

Results

Setup

• Image size: 256-by-128
  
• Batch: 32
  
• Optimizer: Adam [6]
  
• Loss functions:
  xent: cross entropy + label smoothing regularizer [5]
  htri: triplet loss with hard positive/negative mining [4]
  

Note: size of the same model may vary across different datasets due to different number of identities.

Image person reid

Market1501

Model	Size (M)	Loss	Rank-1/5/10 (%)	mAP (%)	Model weights	Published Rank	Published mAP
DenseNet121	7.72	xent	86.5/93.6/95.7	67.8	download
DenseNet121	7.72	xent+htri	89.5/96.3/97.5	72.6	download
ResNet50	25.05	xent	85.4/94.1/95.9	68.8	download	87.3/-/-	67.6
ResNet50	25.05	xent+htri	87.5/95.3/97.3	72.3	download
ResNet50M	30.01	xent	89.0/95.5/97.3	75.0	download	89.9/-/-	75.6
ResNet50M	30.01	xent+htri	90.4/96.7/98.0	76.6	download

Video person reid

MARS

Model	Size (M)	Loss	Rank-1/5/10 (%)	mAP (%)	Model weights	Published Rank	Published mAP
ResNet50	24.79	xent			download
ResNet50	24.79	xent+htri			download
ResNet50M		xent			download
ResNet50M		xent+htri			download

Test

Say you have downloaded ResNet50 trained with xent on market1501. The path to this model is 'saved-models/resnet50-xent-market1501.pth.tar' (create a directory to store model weights mkdir saved-models/). Then, run the following command to test

python train_img_model_xent.py -d market1501 -a resnet50 --evaluate --resume saved-models/resnet50_xent_market1501.pth.tar

References

[1] He et al. Deep Residual Learning for Image Recognition. CVPR 2016.
[2] Yu et al. The Devil is in the Middle: Exploiting Mid-level Representations for Cross-Domain Instance Matching. arXiv:1711.08106.
[3] Huang et al. Densely Connected Convolutional Networks. CVPR 2017.
[4] Hermans et al. In Defense of the Triplet Loss for Person Re-Identification. arXiv:1703.07737.
[5] Szegedy et al. Rethinking the Inception Architecture for Computer Vision. CVPR 2016.
[6] Kingma and Ba. Adam: A Method for Stochastic Optimization. ICLR 2015.
[7] Zheng et al. Scalable Person Re-identification: A Benchmark. ICCV 2015.
[8] Zheng et al. MARS: A Video Benchmark for Large-Scale Person Re-identification. ECCV 2016.