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

Data Organization - egocentric alignment and create training dataset interpolation table #18

Open
npranav9 opened this issue Jun 13, 2024 · 2 comments

Comments

@npranav9
Copy link

When performing egocentric alignment and creating the training dataset in the "Data Organization" tab, would it be possible to generate and save a table with the following information?

Rows = Sessions
Column-1 = # of frames interpolated over due to low DLC likelihood value (# of NaN frames after pose_confidence thresholding).
Column-2 = same as column-1, but represented as % of total frames, relative to the length of that session.
Note: Columns 1 and 2 are for values generated after vame.egocentric_alignment().

Column-3 = # of frames interpolated over due to IQR outlier status.
Column-4 = same as column-3, but represented as % of total frames, relative to the length of that session.
Note: Columns 3 and 4 are for values generated after vame.create_trainingset().

Column-6 = summarize rescaled egocentric coordinates by showing the global min and max of the new X and Y coordinate time series (for all body parts combined, not individual bodyparts). Format should be column 5 (X min, x max), column 6 (y min, y max).

@garrettmflynn
Copy link
Collaborator

Sure! You would want this rendered afterwards as a record of the run?

@npranav9
Copy link
Author

npranav9 commented Jun 14, 2024

Yeah rendering and saving the table after the tab has run works. Thanks!

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

2 participants