Skip to content

Handle the case where not all individuals have the same keypoints. #150

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Open
niksirbi opened this issue Mar 21, 2024 · 2 comments · May be fixed by #543
Open

Handle the case where not all individuals have the same keypoints. #150

niksirbi opened this issue Mar 21, 2024 · 2 comments · May be fixed by #543
Labels
enhancement New optional feature

Comments

@niksirbi
Copy link
Member

Currently our data structure assumes that all individuals (animals) are tracked with the same keypoints (body parts). This assumption holds for most, but not all pose estimation datasets.

We should consider this case and decide what to do about it:

  • figure out a technical workaround for supporting such cases
  • or explicitly state that they are not supported
@niksirbi niksirbi added the enhancement New optional feature label Mar 21, 2024
@Priyam12345-cloud Priyam12345-cloud linked a pull request Apr 5, 2025 that will close this issue
7 tasks
@sfmig
Copy link
Contributor

sfmig commented May 23, 2025

For the time being we should probably document this more clearly. It doesn't seem to be in the Input/output section or in the API reference for the relevant functions, maybe those are nice places to put this?

@niksirbi
Copy link
Member Author

Agreed, document for the short term, and think about supporting this in the long-term—in the sense of loading such data into separate movement datasets (1 per skeleton type).

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
enhancement New optional feature
Projects
Status: 🤔 Triage
Development

Successfully merging a pull request may close this issue.

2 participants