Mackenzie Mathis

@stes lets decide what to do here ...

Hey @sneakers-the-rat afaik its not strictly the same though; this the same reason we don't keep dlc-live in DeepLabCut main. We also used to have core, but it becomes yet...

Using pytest would be much better, I agree

Agree! Let's do this @maximpavliv ; it's what we have in cebra and it's extremely useful

@tshindmarsh can you see if rc10 (the latest release) helps with this issue?

Hi @nshettigar02 I can't quite follow -- the error seems you are doing something in the evaluation step, but you report the issue is you cannot get a labeled video...

from evaluation you must run analyze videos first; could you update your post to include minimal example steps/calls that you are using to get the error?

seems the GPU is not actually in use; can you check your CUDA version & pytorch version -- how did you install it? for example, you need to be sure...

Perhaps back to an installation issue; given your CUDA version & pytorch version -- how did you install it? `CUDA runtime: 12.4` for example, you need to be sure you...

Did you change the max size of the image you use for training? by default we throw out images >1500 pixels (as to truly get 4K training you need a...