This repository was archived by the owner on Sep 12, 2025. It is now read-only.

Description
Idea description
In movement, we can currently only load pose data where all individuals have the same set of keypoints (i.e. same skeleton). This is often the most common case, but some frameworks (such as DeepLabCut) do support predicting poses for different user-defined skeletons.
It would be nice to mention this somewhere in the movement documentation, as it may come as a surprise to new users and the error message is not very clear. See issue #150 for more details.
As a stretch, we could explore how we could deal with such data in movement.
What skills are needed to tackle the project
The documenting part of this issue is well suited for beginners to open source.
Would you be willing to lead this project?