Skip to content
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

[feature request] Use same xz alignment in keypoint-only grid movies as in trajectory plots #187

Open
jonahpearl opened this issue Jan 16, 2025 · 0 comments

Comments

@jonahpearl
Copy link

Hey Caleb — minor feature request here for the future. I wanted to generate some grid movies with keypoints only (because there's an issue with vidio being unable to infer the num frames from some of the 6cam videos, I will maybe make a separate PR to fix that). I used this command

kpms.generate_grid_movies(
   results,
   project_dir,
   model_name,
   video_paths=video_paths,
   coordinates=coordinates,  # the 3D coords
   keypoints_only=True,
   use_dims=[0,2],
   headings=headings,  # this was all zeros as described in the docs
   **config())

and got the attached movie out. I was hoping to have each syllable instance aligned in the sagital / XZ plane the way they are in the trajectory plots. Instead, each instance remains as it is in the data, such that sometimes the mice are aligned XZ but other times you're seeing them head-on. I imagine this could be done by calculating the sagital plane of the mouse and then projecting the 3d coords onto that plane, and using that as the "fictive" XZ coords for the grid movie.

Thanks (and no rush :) )

syllable0.mp4
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

No branches or pull requests

1 participant