VisionTask

[common]
object VisionTask

The tasks a vision model may serve, the spellings Capabilities.visionTasks carries.

Properties

Name	Summary
CLASSIFY	[common] const val CLASSIFY: String A score per label the caller names, over a model that embeds text and pictures in one space (VisionModel.classify).
DEPTH	[common] const val DEPTH: String A depth value per pixel (VisionModel.depth).
DETECT	[common] const val DETECT: String Boxes with labels and scores over the picture (VisionModel.detect).
EMBED	[common] const val EMBED: String A vector that stands for the picture (VisionModel.embed).
OCR	[common] const val OCR: String The text written in the picture (VisionModel.recognizeText).