Skip to content
DukeMTMC-reID_baseline (Matlab)
Cuda MATLAB C++ C Shell
Branch: master
Clone or download
Fetching latest commit…
Cannot retrieve the latest commit at this time.
Permalink
Type Name Latest commit message Commit time
Failed to load latest commit information.
examples v1.0 May 27, 2017
matlab v1.0 May 27, 2017
test v1.0 May 27, 2017
License Create License May 27, 2017
README.md Update README.md Aug 8, 2017
gpu_compile.m v1.0 May 27, 2017
prepare_data_duke.m v1.0 May 27, 2017
resnet52_duke.m v1.0 May 27, 2017
train_id_net_res_duke.m v1.0 May 27, 2017

README.md

DukeMTMC-reID_baseline

Here we provide ResNet-50 baseline training code on DukeMTMC-reID Dataset. You can download DukeMTMC-reID in https://github.com/layumi/DukeMTMC-reID_baseline.

Installation

  1. Clone this repo

    git clone https://github.com/layumi/DukeMTMC-reID_baseline.git
    cd DukeMTMC-reID_baseline
    mkdir data
  2. Download the pretrained model.

    This model is ONLY released for academic use. You can find the pretrained model in GoogleDriver or [BaiduYun] (http://pan.baidu.com/s/1jIHqSQy). Download and put the files into the ./data.

    BaiduYun sometime changes the link. If you find the url fail, you can contact me to update it.

  3. Compile matconvnet

    You just need to uncomment and modify some lines in gpu_compile.m and run it in Matlab. Try it~

    If you fail in compilation, you may refer to http://www.vlfeat.org/matconvnet/install/

Test

  1. After installation, you can run test/test_duke.m to extract the features of images in the gallery and query set. They will store in a .mat file. Then you can use it to do evaluation.

  2. Evaluate feature on the DukeMTMC-reID. You can directly use the code in https://github.com/layumi/DukeMTMC-reID_evaluation.

Train

  1. Add your dataset path into prepare_data.m and run it. Make sure the code outputs the right image path.

  2. Run train_id_net_duke.m to have fun.

Citation

Please cite this paper in your publications if it helps your research:

@inproceedings{zheng2017unlabeled,
  title={Unlabeled Samples Generated by GAN Improve the Person Re-identification Baseline in vitro},
  author={Zheng, Zhedong and Zheng, Liang and Yang, Yi},
  booktitle={Proceedings of the IEEE International Conference on Computer Vision},
  year={2017}
}
You can’t perform that action at this time.