Skip to content

Markerless tracking of user-defined features with deep learning

License

Notifications You must be signed in to change notification settings

timegate/DeepLabCut

 
 

Repository files navigation

Deeplabcut_KAIST

Changed DeepLabCut for Synaptic Brain Dysfunctions Lab in KAIST, South Korea.

Alt Text Alt Text Alt Text

DeepLabCut 1.0.0 + fixed & added codes ---> Merged to DeepLabCut 2.0.4(latest version based on 2019.02.10)

Forked from commit https://github.com/altairlight/DeepLabCut/commit/195c32e3aa05fce46c57639e238ab3525682ccb8 and some of it's codes have been fixed(optimized GUI mainframe & train parameters for our lab videos, project codes & files & training dataset which can be used for your new project & transfer learning, labeling restart function(by down arrow key), memory clear, cpp codes to remove mis-generated/unused files, and Korean manuals! https://github.com/altairlight/DeepLabCut/tree/master/deeplabcut/Desktop_Files/Deeplabcut%20Guide)

You can use this code after 3 steps.

  1. Install original all deeplabcut package from https://github.com/AlexEMG/DeepLabCut to your new anaconda environment. For this step, you may follow my manual "시작하기.txt" in deeplabcut/Desktop_Files/Deeplabcut Guide

  2. Please copy the DeepLabCut/deeplabcut/ folder to anaconda3\(your new environment)\Lib\site-packages(you should overwrite the deeplabcut folder from above step while your copying! 위에서 만든 deeplabcut 폴더를 덮어쓰세요!)

  3. Next, you should copy some files of Desktop_Files to your desktop. For analyzing linear chamber tests, you may need to download these files.

    1)Deeplabcut Guide

    2)LinearChamber-KAIST-2018-11-19

    3)LinearChamber2-KAIST-2019-01-07

    4)projects (which have .ipynb files)

    5)Video_files_Deeplabcut

    6)Video_files_other

    But you know, I'm sorry that I cannot share full project folders(2, 3) and video files(5, 6) through github website(because of copyright issues and problem with size of this git repo)

    If you need the video files and you can prove you are related to the Synaptic Brain Dysfunctions Lab in KAIST, you could get the data from me([email protected]) or from Ms.WooHyun Kim.

Now you can follow my manuals in deeplabcut/Desktop_Files/Deeplabcut Guide and enjoy your projects!

Also please contact to [email protected] if you got stuck on some problems. Thanks!

About

Markerless tracking of user-defined features with deep learning

Resources

License

Stars

Watchers

Forks

Packages

No packages published

Languages

  • Jupyter Notebook 98.5%
  • Python 1.5%