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

..

visualization_tools

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

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

load_lerobot_dataset.py

refactor(dataset): modular files (#3171)

2026-03-15 23:58:09 -07:00

slurm_compute_rabc.py

Feat/slurm compute rabc script (#3041)

2026-03-05 18:27:58 +01:00

use_dataset_image_transforms.py

Add docs for LeRobot Image transforms (#1972)

2025-09-19 15:19:49 +02:00

use_dataset_tools.py

Feat/expand add features (#2202)

2025-10-14 16:19:50 +02:00