Mackenzie Mathis

can you share a screen shot? I can't reproduce this with my iphone videos

Hi @sunqy31 awe, so if there are three, then unfortuantely that is what it was trained with too, in the Collecteddata.h5 file. If you put back ind 3 into config,...

can the metrics showing results are identical please be added to top PR comment, thanks!

hey @alexcwsmith thanks! Could you delineate why you needed this addition? we have not experienced memory issues/not closing the TF session properly such that it would hold memory.

okay, makes sense! Thanks! We are doing to do a big push in the next 24 hours, then can work this in/test afterwards!

Hey there, it is currently a WIP in the lab (sorry, long list these days), but we just released 3D maDLC, which goes along this path too, see 2.2.1

hey @roaldarbol if you are using the human pretrained model from Deeplabcut, it actually treats left and right as the same, i.e. there is no distinction; if you want to...

Sounds good! I haven't followed the latest on anipose, but there is the ARMIA model filter within dlc, I'd give that a go as well? `dlc.filterpredictions(config)`

@hyr2 yes, 3.8 will no longer, work, but there is a new GUI :) #1984 which does not rely on wxPython. Please check it out and report any issues you...

please now try running `pip install --upgrade --force-reinstall 'deeplabcut[gui]'==2.3rc1` in your env and/or docker. I will close, but please do post back!