Git Product home page Git Product logo

rfl's Introduction

Recurrent Filter Learning for Visual Tracking

This is the implementation of our RFL tracker published in ICCV2017 workshop on VOT. Our code is written in python3(3.5) using Tensorflow(>=1.2) toolbox

For easy comparison, we upload our OTB100 results files to the main directory ./otb100_results.zip

Tracking

You use our pretrained model to test our tracker first.

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

Training

  1. Download the ILSRVC data from the official website and set proper paths for ISLVRC and their tfrecords in config.py
  2. Then run the process_data.sh in ./data_preprocssing directory to convert ILSVRC data to tfrecords.
  3. Run python3 train.py to train the model.

If you find the code is helpful, please cite

@inproceedings{Yang2017,
    author = {Yang, Tianyu and Chan, Antoni B.},
    booktitle = {ICCV Workshop on VOT},
    title = {Recurrent Filter Learning for Visual Tracking},
    url = {http://arxiv.org/abs/1708.03874},
    year = {2017}
}

rfl's People

Contributors

tyyyang avatar

Stargazers

avatar Ming Li avatar Jianxiao Chen avatar avatar avatar avatar Maaz Ullah avatar Md Maklachur Rahman avatar avatar springtime-cn avatar 王开开 avatar Pai3Dot14 avatar avatar Emma avatar avatar avatar xiaowang avatar avatar avatar avatar Moore July avatar

Watchers

avatar avatar daikaiheng avatar Ming Xue avatar Moore July avatar paper2code - bot avatar

Forkers

huangpu1 smzcc happyjin xuexia7023 zellford tomingz wyukai shenwenxiao fegonda wangxc2015 brilliantsong2 codertcm teamspeakuse

rfl's Issues

Some problems

Hello

Thank you for your contributions 👍
  • I am confusing with the function, would you please make any explanation to me? what does it work ?
  • Thanks in advance.
Looking forward to your reply
Best regards

where is the cfg.json?

I have already downloaded basketball sequence from OTB-100,and put it in C:/Users/acer/Desktop/程序/RFL-master/output/models
when I run tracking.demo.py,there is a bug:

File "C:/Users/acer/Desktop/程序/RFL-master/tracking/tracking_demo.py", line 57, in load_seq_config
configFile = open(src)
FileNotFoundError: [Errno 2] No such file or directory: 'C:/Users/acer/Desktop/程序/RFL-master\Basketball\cfg.json'

Memory Leak problem

Hello,
Thank you for your contributions .
I am confusing with two problems when I reproduce your method, would you please make any explanation to me?
(1) The search image seems to be reshaped to 239 x 239, so the size of the response map eventually becomes 15 x 15. What is the reason for this treatment?
(2) During the training process, the memory will continue to grow. Is there a memory leak?

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.