Pepijn 58eecad8a4 feat(viz): add image-based consistency analysis with SigLIP ...

Run two parallel KNN analyses per dataset:
  1. State-based: KNN in joint-state space
  2. Image-based: KNN in SigLIP embedding space (google/siglip-base-patch16-224)

Both measure action chunk variance among cross-episode neighbors.
Comparing them reveals whether visual and proprioceptive similarity
agree on where data is inconsistent.

Output is a 4-row figure: state histogram, image histogram,
overlaid per-episode curves, and spatial heatmap colored by
image-based variance.

Made-with: Cursor

2026-03-23 20:29:36 -07:00

..

action_consistency.py

feat(viz): add image-based consistency analysis with SigLIP

2026-03-23 20:29:36 -07:00

create_frame_grid.py

fix(viz): use relative output path instead of hardcoded absolute path

2026-03-23 20:17:59 -07:00

create_progress_videos.py

fix(viz): use relative output path instead of hardcoded absolute path

2026-03-23 20:17:59 -07:00

workspace_density.py

fix(viz): use relative output path instead of hardcoded absolute path

2026-03-23 20:17:59 -07:00