lambdaloop / anipose

🐜🐀🐒🚶 A toolkit for robust markerless 3D pose estimation
http://anipose.org
BSD 2-Clause "Simplified" License
351 stars 66 forks source link

How to apply the viterbi + autoencoder filter like in the paper? #79

Open SamMinkowicz opened 2 years ago

SamMinkowicz commented 2 years ago

I enjoyed reading your paper and am looking forward to using Anipose on my data!

Is there a way to apply both the viterbi and autoencoder filters like in the paper? I imagine one could do it by first applying the viterbi filter, renaming the pose-2d-filtered directory to pose-2d, changing the config file to use the autoencoder, and then calling the filter command again but is there a cleaner way?

Thanks! Sam