Git Product home page Git Product logo

mmp_track1_iccv21's Introduction

Tracking Code for the winner of track1 in MMP-Trakcing challenge

This repository contains our tracking code for the Multi-camera Multiple People Tracking (MMP-Tracking) Challenge at ICCV 2021 Workshop.

1. Environment setup

This tracking code has been tested on Python 3.7.6, Pytorch 1.5.1, CUDA 10.1, please install related libraries before running this code:

pip install -r requirements.txt
pip install torch==1.5.1+cu101 torchvision==0.6.1+cu101 -f https://download.pytorch.org/whl/torch_stable.html

2. Detection

We provide the detection results on the test split in yolox_baseline.zip and yolox_finetune.zip. They should be extracted first.

3. Tracking

Run the following script to reproduce our tracking results.

sh auto_run.sh

4. Acknowledgement

We use YOLOX to train our detection model. Some code from deep_sort, FairMOT, and tao.

mmp_track1_iccv21's People

Contributors

feiaxyt avatar

Stargazers

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

mmp_track1_iccv21's Issues

Regarding test data detections used in the repo.

Hi, I am doing Research for my Master's thesis on multi camera multi object tracking. I have seen your presentation, that was really nice. I was going through your code. You have provided the detections for the test data. How did you got the test data.

I have mailed the ICCV2021 team, and I got the dataset link for train and validation set but not the test set that you used.

I am actually hoping that whether you can provide some link to the test data or some refence for that so that I can understand your code in a better way. This would help a lot in my thesis project.

Thanks.

About training code

I noticed that this code is just test code.
Could you provide full code including training code?

Non English Comments

You guys probably would want to change those non English comments all over the project. It's pretty hard to follow the program flow.

Question about dataSet

Hi,

thank you so much about sharring this code.
Can you share with me subset from data just for testing your code ?

Thank you in advance

Question about calibration.json

thank you for your work i've read the json clibration file but i don't know how to retrieve the environment space cords.
"Space": {
"MaxU": 2860,
"MinU": -4200,
"MaxV": 3180,
"MinV": -2960,
"MaxW": 2100,
"MinW": 100,
"VoxelSizeInMM": 20
}

Recommend Projects

  • React photo React

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

  • Vue.js photo Vue.js

    ๐Ÿ–– 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. ๐Ÿ“Š๐Ÿ“ˆ๐ŸŽ‰

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 โค๏ธ Open Source for everyone.

  • D3 photo D3

    Data-Driven Documents codes.