.@marius10p thanks for the idea - seems like nothing is camouflaged to #DeepLabCut - Trained with !! 14 frames !! for 8min on GPU (6,000 iterations). Frame-by-frame prediction. Paper: https://t.co/CoAsiyrlel @sofiabiologista pic.twitter.com/pUSlaQwvaJ

— Alexander Mathis (@TrackingPlumes) May 30, 2018