caglarmert / mot-research Goto Github PK

• Issues
• Readme
• Project
• Project board (kanban)
• Project sprint
• Automated actions
• License

Research Progress Report

• Summary
• Introduction
• Body
• Conclusion
• References

C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v10.0\include\crt/host_config.h(143): fatal error C1189: #error: -- unsupported Microsoft Visual Studio version! Only the versions between 2013 and 2017 (inclusive) are supported!
error: command 'C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v10.0\bin\nvcc.exe' failed with exit status 2

Determine issue types

Steps for simple literature reading

• Collect 5 most recent Multi Object Tracking papers with highest impact from papers with code
• Read 5 paper abstracts
• Read 5 paper introductions
• Read 5 paper conclusions
• Summarize each of the 5 papers
• Choose most relevant 2 papers for the next week reading

Stylistic coding standards

• Introduce PEP-8
• Introduce PEP-257
• Introduce automation of PEP-8
• Introduce automation of PEP-257

Research Progress Report

• Summary
• Introduction
• Body
• Conclusion
• References

INFO: Could not find files for the given pattern(s).
Traceback (most recent call last):
File "setup.py", line 64, in
ext_modules=get_extensions(),
File "setup.py", line 41, in get_extensions
raise NotImplementedError('Cuda is not availabel')
NotImplementedError: Cuda is not availabel

[image2 @ 00000258d494ba80] Could find no file with path 'D:\Work\CV\FairMOT\results\frame/%05d.jpg' and index in the range 0-4
D:\Work\CV\FairMOT\results\frame/%05d.jpg: No such file or directory

• Requirements
• Demo

Find:

• 5 Most prominent papers
• 5 most starred github implementations
• Most used 2 algorithms

Report Template

• Report Template Formation

Report Body

• Summary
• Introduction
• Abstract
• Body
• Conclusion
• References

Literature Survey Summary

• Fast Literature Survey
• MOT Papers List
• MOT Github Repositories List
• Tools

• Create Kanban Project
• Determine Kanban Project Steps
• Create first Kanban sprint

• Python 3.7 (conda environment)
• visual c++ 14+
• yacs
• opencv-python
• cython-bbox
• numba
• progress
• motmetrics
• numba
• matplotlib
• lap
• openpyxl
• Pillow==6.2.2

• pretrained coco model
• pretrained imagenet model
• ffmpeg installation for windows link

The requirement.txt has cython-bbox library.
It is required to be installed for the project

The benchmark dataset for State of the Art Multi Object Tracking methods can be evaluated at MOT Challenge

Preliminary Work for the challenge:

• Challenge summary
• Challenge state of the art methods
• Up-to date novel ideas for MOT
• Proposed method

• MS word .docx Documentation template