Code Monkey home page Code Monkey logo

memtrack's Introduction

Learning Dynamic Memory Networks for Object Tracking

We extend our MemTrack with Distractor Template Canceling mechamism in our journal verison, please check our new method MemDTC. Code is availabe at MemDTC-code

Introduction

This is the Tensorflow implementation of our MemTrack tracker published in ECCV, 2018. Detailed comparision results can be found in the author's webpage

Prerequisites

  • Python 3.5 or higher
  • Tensorflow 1.2.1 or higher
  • CUDA 8.0

Path setting

Set proper home_path in config.py accordingly in order to proceed the following step. Make sure that you place the tracking data properly according to your path setting.

Tracking Demo

You can use our pretrained model to test our tracker first.

  1. Download the model from the link: GoogleDrive
  2. Put the model into directory ./output/models
  3. Run python3 demo.py in directory ./tracking

Training

  1. Download the ILSRVC data from the official website and extract it to proper place according to the path in config.py.
  2. Then run the sh process_data.sh in ./build_tfrecords directory to convert ILSVRC data to tfrecords.
  3. Run python3 experiment.py to train the model.

Citing MemTrack

If you find the code is helpful, please cite

@inproceedings{Yang2018,
	author = {Yang, Tianyu and Chan, Antoni B.},
	booktitle = {ECCV},
	title = {{Learning Dynamic Memory Networks for Object
	Tracking}},
	year = {2018}
}

memtrack's People

Contributors

tyyyang avatar

Stargazers

avatar Shuyue Jia avatar avatar Ming Li avatar Mohamed Lamnouar avatar avatar Bencheng avatar ZhongdaoWang avatar Xavier Weber avatar Fabian avatar Farhan Syakir avatar Siyuan Qiao avatar Quran avatar WillWong avatar avatar avatar Jingbo Lin avatar phiphi avatar Jianxiao Chen avatar avatar avatar Zhihong Fu avatar Dongcheng Zhao avatar avatar avatar avatar avatar avatar avatar XLongFu avatar Shunyu Yao avatar Andrew Yang avatar avatar avatar avatar avatar Bowen Chen avatar Andreu Girbau avatar avatar Bing Penguin avatar Janos Tolgyesi avatar Jack avatar Axel Sauer avatar avatar avatar Ali Hamdi avatar avatar Haoxin Chen avatar Berire Gündüz avatar Shiyang Cheng avatar avatar avatar LitingLin avatar avatar lu zhang avatar Andrew avatar jimmy avatar davci avatar Huang Lianghua avatar Swapnil Bembde avatar Nrupatunga avatar avatar D.P avatar Call Me Maybe avatar Pan He avatar avatar Zhenmei Shi avatar yangyangxie_ahu avatar avatar avatar shicai avatar Yikai Wang avatar avatar avatar Yiming Lin avatar Doyup Lee avatar Liang Depeng avatar Xiao Wang（王逍） avatar Xuejian Rong avatar Yeongjae Cheon avatar avatar

Watchers

avatar Yeongjae Cheon avatar daikaiheng avatar Ming Xue avatar avatar avatar Doyup Lee avatar avatar paper2code - bot avatar

Forkers

knockknock13 saintlogos1234 vodp lifeng9472 guangshengshi gitlyz007 zhaowujie yushenxiang sayanmutd skyellen fegonda tuanthng

memtrack's Issues

where are train.py and process_data.sh file

Hi Tianyu,
I would like to train the tracker from scratch but it seems like there are no training scripts like train.py and process_data.sh, could you please upload them?
Many thanks,
Yiming

VOT test code

Hi, Tianyu:
Thank you for sharing your code, would you like to provide the tracker file you run for the vot-toolkit?

This is the environment configuration required for the project（with Conda）

File Name: memtrack.yaml (This is the Conda configuration file)
File Content：

name: memtrack
channels:
  - https://mirrors.ustc.edu.cn/anaconda/pkgs/main
  - https://mirrors.ustc.edu.cn/anaconda/pkgs/free
  - https://mirrors.ustc.edu.cn/anaconda/cloud/conda-forge
  - https://mirrors.tuna.tsinghua.edu.cn/anaconda/cloud/pytorch/linux-64/
  - https://mirrors.tuna.tsinghua.edu.cn/anaconda/cloud/pytorch/
  - https://mirrors.tuna.tsinghua.edu.cn/anaconda/pkgs/main/
  - https://mirrors.tuna.tsinghua.edu.cn/anaconda/pkgs/free/
  - https://mirrors.ustc.edu.cn/anaconda/cloud/menpo/
  - https://mirrors.ustc.edu.cn/anaconda/cloud/bioconda/
  - https://mirrors.ustc.edu.cn/anaconda/cloud/msys2/
  - https://mirrors.ustc.edu.cn/anaconda/cloud/conda-forge/
  - https://mirrors.ustc.edu.cn/anaconda/pkgs/free/
  - https://mirrors.ustc.edu.cn/anaconda/pkgs/main/
  - defaults
dependencies:
  - _libgcc_mutex=0.1=conda_forge
  - _openmp_mutex=4.5=1_gnu
  - backports=1.0=py_2
  - backports.weakref=1.0rc1=py36_0
  - bleach=1.5.0=py36_0
  - bzip2=1.0.8=h7b6447c_0
  - ca-certificates=2021.1.19=h06a4308_0
  - cairo=1.14.12=h8948797_3
  - certifi=2020.12.5=py36h06a4308_0
  - cudatoolkit=8.0=3
  - cudnn=6.0.21=cuda8.0_0
  - ffmpeg=4.0=hcdf2ecd_0
  - fontconfig=2.13.1=h6c09931_0
  - freeglut=3.0.0=hf484d3e_5
  - freetype=2.10.4=h5ab3b9f_0
  - glib=2.67.4=h36276a3_1
  - graphite2=1.3.14=h23475e2_0
  - harfbuzz=1.8.8=hffaf4a1_0
  - hdf5=1.10.2=hc401514_3
  - html5lib=0.9999999=py36_0
  - icu=58.2=he6710b0_3
  - importlib-metadata=3.7.0=py36h5fab9bb_0
  - jasper=2.0.14=h07fcdf6_1
  - jpeg=9b=h024ee3a_2
  - lcms2=2.11=h396b838_0
  - ld_impl_linux-64=2.35.1=hea4e1c9_2
  - libblas=3.9.0=8_openblas
  - libcblas=3.9.0=8_openblas
  - libffi=3.3=h58526e2_2
  - libgcc=7.2.0=h69d50b8_2
  - libgcc-ng=9.3.0=h2828fa1_18
  - libgfortran=3.0.0=1
  - libgfortran-ng=9.3.0=hff62375_18
  - libgfortran5=9.3.0=hff62375_18
  - libglu=9.0.0=hf484d3e_1
  - libgomp=9.3.0=h2828fa1_18
  - liblapack=3.9.0=8_openblas
  - libopenblas=0.3.12=pthreads_h4812303_1
  - libopencv=3.4.2=hb342d67_1
  - libopus=1.3.1=h7b6447c_0
  - libpng=1.6.37=hbc83047_0
  - libprotobuf=3.15.2=h780b84a_0
  - libstdcxx-ng=9.3.0=h6de172a_18
  - libtiff=4.1.0=h2733197_1
  - libuuid=1.0.3=h1bed415_2
  - libvpx=1.7.0=h439df22_0
  - libxcb=1.14=h7b6447c_0
  - libxml2=2.9.10=hb55368b_3
  - lz4-c=1.9.3=h2531618_0
  - markdown=3.3.3=pyh9f0ad1d_0
  - ncurses=6.2=h58526e2_4
  - numpy=1.16.4=py36h95a1406_0
  - olefile=0.46=py36_0
  - opencv=3.4.2=py36h6fd60c2_1
  - openssl=1.1.1j=h27cfd23_0
  - pcre=8.44=he6710b0_0
  - pillow=8.1.0=py36he98fc37_0
  - pip=21.0.1=pyhd8ed1ab_0
  - pixman=0.40.0=h7b6447c_0
  - protobuf=3.15.2=py36hc4f0c31_0
  - py-opencv=3.4.2=py36hb342d67_1
  - python=3.6.13=hffdb5ce_0_cpython
  - python_abi=3.6=1_cp36m
  - readline=8.0=he28a2e2_2
  - setuptools=49.6.0=py36h5fab9bb_3
  - six=1.15.0=pyh9f0ad1d_0
  - sqlite=3.34.0=h74cdb3f_0
  - tensorflow-gpu=1.2.1=py36cuda8.0cudnn6.0_0
  - tk=8.6.10=h21135ba_1
  - typing_extensions=3.7.4.3=py_0
  - webencodings=0.5.1=py_1
  - werkzeug=1.0.1=pyh9f0ad1d_0
  - wheel=0.36.2=pyhd3deb0d_0
  - xz=5.2.5=h516909a_1
  - zipp=3.4.0=py_0
  - zlib=1.2.11=h516909a_1010
  - zstd=1.4.5=h9ceee32_0
  - pip:
    - opencv-python==4.5.1.48
prefix: /home/dc2-user/anaconda3/envs/memtrack

config json file

@skyoung Thank you for the work. Is it possible for you to provide scripts for generating the cfg.json for all the datasets? I can not run your demo with the following error:

Traceback (most recent call last):
  File "demo.py", line 112, in <module>
    run_tracker()
  File "demo.py", line 93, in run_tracker
    seq = load_seq_config('Basketball')
  File "demo.py", line 55, in load_seq_config
    configFile = open(src)

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.