layumi / Person Reid Verification
Programming Languages
A Discriminatively Learned CNN Embedding for Person Re-identification (in Pytorch)
In this package, we provide our training and testing code written in pytorch for the paper A Discriminatively Learned CNN Embedding for Person Re-identification.
Compared with the original version, I do some modification:
- I use
x*yinstead of(x-y)^2asSquare Layer. (We do not need to worry about the scale ofxandy.) - I add the bottle-neck fully-connected layer for classification. I use the
512-dimfully-connected feature as pedestrian descriptor. - I tune some hyperparameters.
- On MSMT-17, we arrive [email protected]:0.604769 [email protected]:0.761815 [email protected]:0.815593 mAP:0.315827.
We arrived [email protected]=88.66%, mAP=72.58% with ResNet-50. The code is largely borrowed from my another repo strong Pytorch baseline . Here we provide hyperparameters and architectures, that were used to generate the result. Some of them (i.e. learning rate) are far from optimal. Do not hesitate to change them and see the effect.
Any suggestion is welcomed.
This code is ONLY released for academic use.
Resources
-
Zhedong Zheng The original Matconvnet version in the paper. (
) -
Weihang Chen also realizes our paper in Keras. (
) -
Xuanyi Dong also realizes our paper in Caffe. (
) -
Zhun Zhong provides a extensive Caffe baseline code. You may check it. (
) -
Zhedong Zheng provides a strong Pytorch baseline (
)
Model Structure
You may learn more from model.py.
Prerequisites
- Python 3.6
- GPU Memory >= 6G
- Numpy
- Pytorch 0.3+
(Some reports found that updating numpy can arrive the right accuracy. If you only get 50~80 Top1 Accuracy, just try it.) We have successfully run the code based on numpy 1.12.1 and 1.13.1 .
Getting started
Installation
- Install Pytorch from http://pytorch.org/
- Install Torchvision from the source
git clone https://github.com/pytorch/vision
cd vision
python setup.py install
Because pytorch and torchvision are ongoing projects.
Here we noted that our code is tested based on Pytorch 0.3.0/0.4.0 and Torchvision 0.2.0.
Dataset & Preparation
Download Market1501 Dataset
Preparation: Put the images with the same id in one folder. You may use
python prepare.py
Remember to change the dataset path to your own path.
Futhermore, you also can test our code on DukeMTMC-reID Dataset. Our baseline code is not such high on DukeMTMC-reID [email protected]=64.23%, mAP=43.92%. Hyperparameters are need to be tuned.
To save trained model, we make a dir.
mkdir model
Train
Train a model by
python train_new.py --gpu_ids 0 --name ft_ResNet50 --alpha 1.0 --batchsize 32 --data_dir your_data_path
--gpu_ids which gpu to run.
--name the name of model.
--data_dir the path of the training data.
--batchsize batch size.
--erasing_p random erasing probability.
--alpha the weight of the verification loss.
Train a model with random erasing by
python train_new.py --gpu_ids 0 --name ft_ResNet50 --train_all --batchsize 32 --data_dir your_data_path --erasing_p 0.5
Test
Use trained model to extract feature by
python test.py --gpu_ids 0 --name ft_ResNet50 --test_dir your_data_path --which_epoch 59
--gpu_ids which gpu to run.
--name the dir name of trained model.
--which_epoch select the i-th model.
--data_dir the path of the testing data.
Evaluation
python evaluate.py
It will output [email protected], [email protected], [email protected] and mAP results.
You may also try evaluate_gpu.py to conduct a faster evaluation with GPU.
For mAP calculation, you also can refer to the C++ code for Oxford Building. We use the triangle mAP calculation (consistent with the Market1501 original code).
Citation
Please cite this paper in your publications if it helps your research:
@article{zheng2016discriminatively,
title={A Discriminatively Learned CNN Embedding for Person Re-identification},
author={Zheng, Zhedong and Zheng, Liang and Yang, Yi},
doi={10.1145/3159171},
journal={ACM Transactions on Multimedia Computing Communications and Applications},
year={2017}
}