Model-free: give it the embeddings and it applies each feature's rule.
centroid_patch_max features need patches; clip_text_pair features
need image and textEmb (rows named by prompt). For external
features supply the scores yourself.
Arguments
- key
A dimoose key with a
featurestable.- image
objects x dmatrix of image embeddings (unit rows).- patches
objects x patches x darray of patch embeddings.- textEmb
prompts x dmatrix of text embeddings whose row names are the prompt texts, e.g. fromembedTexts().
See also
scoreImages() for images-to-scores in one call.