Skip to content

mask rCNN pipeline for detecting a range of body-parts on black and white mice and back-end for creating features for individual identification

Notifications You must be signed in to change notification settings

sronilsson/mask_rCNN_mouse_resident_intruder

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

13 Commits
 
 
 
 
 
 
 
 
 
 

Repository files navigation

Pipeline for detecting and analyzing body parts of black and white mice using mask RCNN and inception coco. Can be used for 'fingerprinting' animals and individual identification.

alt-text-1 alt-text-1

  • Weights for mouse resident intruder can be downloaded on OSF.
  • Uses a modified version of labelme2coco to create coco.json formats from labelme output.
  • Uses a modified version of create_coco_tf_record.py to create tf records from coco.json format.
  • Example renderings on youtube: [1], [2], [3].
  • Weights were created by labelling images using labelme and labelling 9 body-parts on each mouse. alt-text-1

About

mask rCNN pipeline for detecting a range of body-parts on black and white mice and back-end for creating features for individual identification

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages