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

Relocate IQR cleaning into egocentric_alignment() and rename function #22

Closed
katiekly opened this issue Jun 3, 2024 · 2 comments
Closed
Labels
refactor Improve internal software structure without changing observable outcomes

Comments

@katiekly
Copy link
Collaborator

katiekly commented Jun 3, 2024

Currently, create_trainset() uses IQR cleaning to nan and interpolate over outlier points to make the pose trajectories smoother. This data cleaning step should be relocated into egocentric_alignment() and then rename egocentric_alignment() to, for example, preprocess_and_egocentric_alignment().

@katiekly katiekly added the refactor Improve internal software structure without changing observable outcomes label Jun 3, 2024
@luiztauffer
Copy link
Collaborator

it might make sense to create an explicit vame.preprocessing() step, where we can include options for:

  • egocentric alignment
  • normalization, IQR, filters, ...
  • other preprocessing operations, such as the ones offered by movement

@luiztauffer luiztauffer mentioned this issue Nov 21, 2024
5 tasks
@luiztauffer
Copy link
Collaborator

covered by #119

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
refactor Improve internal software structure without changing observable outcomes
Projects
None yet
Development

No branches or pull requests

2 participants