Code Monkey home page Code Monkey logo

prcv2019-mvb-renet's Introduction

SetUp

1. ubuntu installs anaconda3 5.X
2. build virtual envs  
   >  conda create -n bagreid python=3.6  
   >  source activate bagreid
3. conda install package
   >  conda install pytorch torchvision cudatoolkit=9.0 -c pytorch 
   >  conda install pandas
   >  pip install tensorboardX yacs
4. > git clone https://github.com/NVIDIA/apex
   > cd apex
   > pip install -v --no-cache-dir ./

Data preparation

1. download mvb dataset from http://volumenet.cn/#/
2. > git clone https://github.com/wuyuejinxia/prcv2019-mvb-renet.git
   > cd prcv2019-mvb-renet
   > mkdir data 
   > mv MVB_train/Image data/MVB/bounding_box_train
   > mv MVB_train/Info/train.json data/MVB/train.json
   > mv MVB_val/Image/gallery data/MVB/gallery
   > mv MVB_val/Info/val_gallery.json data/MVB/val_gallery.json
   > mv MVB_val/Image/probe data/MVB/probe
   > mv MVB_val/Info/val_probe.json data/MVB/val_probe.json

Train

   > python train.py

Result

Rank-1 Rank-3 Rank-5 Rank-10
2019-07-27 84.32% 94.20% 96.67% 98.76%
2019-08-20 84.98% 95.44% 97.24% 98.86%
2019-08-29 88.69% 96.20% 98.38% 99.05%

Citation

You are encouraged to cite the following papers if this work helps your research.
@misc{zhang2019mvb,
      title={MVB: A Large-Scale Dataset for Baggage Re-Identification and Merged Siamese Networks},
      author={Zhulin Zhang and Dong Li and Jinhua Wu and Yunda Sun and Li Zhang},
      year={2019},
      eprint={1907.11366},
      archivePrefix={arXiv},
      primaryClass={cs.CV}
     }
url: https://arxiv.org/abs/1907.11366

prcv2019-mvb-renet's People

Contributors

syncdevwu avatar

Stargazers

 avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar

Watchers

 avatar  avatar

prcv2019-mvb-renet's Issues

MVB dataset

Hello, I'm currently doing the work of baggage REID. I want to try MVB, but the registration channel seems to be closed, so would you please send me a data set? thank you very much indeed.my e-mail is [email protected].

请问模型在哪里下载

windows环境
se_resnext50_32x4d-a260b3a4.pth和resnet50_ibn_a.pth.tar
请问这两个文件可否提供一下下载链接,谢谢。我担心在网上找的文件有差异。

MVB数据集下载

您好,请问现在还有途径能够下载到数据集吗?官网的注册好像不再审核了,可以麻烦您发一份吗?网盘链接也行,非常感谢!我的邮箱:[email protected]

Recommend Projects

  • React photo React

    A declarative, efficient, and flexible JavaScript library for building user interfaces.

  • Vue.js photo Vue.js

    🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.

  • Typescript photo Typescript

    TypeScript is a superset of JavaScript that compiles to clean JavaScript output.

  • TensorFlow photo TensorFlow

    An Open Source Machine Learning Framework for Everyone

  • Django photo Django

    The Web framework for perfectionists with deadlines.

  • D3 photo D3

    Bring data to life with SVG, Canvas and HTML. 📊📈🎉

Recommend Topics

  • javascript

    JavaScript (JS) is a lightweight interpreted programming language with first-class functions.

  • web

    Some thing interesting about web. New door for the world.

  • server

    A server is a program made to process requests and deliver data to clients.

  • Machine learning

    Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.

  • Game

    Some thing interesting about game, make everyone happy.

Recommend Org

  • Facebook photo Facebook

    We are working to build community through open source technology. NB: members must have two-factor auth.

  • Microsoft photo Microsoft

    Open source projects and samples from Microsoft.

  • Google photo Google

    Google ❤️ Open Source for everyone.

  • D3 photo D3

    Data-Driven Documents codes.