---
title: "VisionTask"
sidebar_label: "VisionTask"
description: "Kotlin binding reference: VisionTask."
---

<!-- Generated by tools/api_reference/generate_api_docs.py. Do not edit. -->

//[clika-runtime](../../../index.md)/[io.clika.modelverse](../index.md)/[VisionTask](index.md)

# VisionTask

[common]\
object [VisionTask](index.md)

The tasks a vision model may serve, the spellings [Capabilities.visionTasks](../Capabilities/visionTasks.md) carries.

## Properties

| Name | Summary |
|---|---|
| [CLASSIFY](CLASSIFY.md) | [common]<br>const val [CLASSIFY](CLASSIFY.md): [String](https://kotlinlang.org/api/core/kotlin-stdlib/kotlin/-string/index.html)<br>A score per label the caller names, over a model that embeds text and pictures in one space ([VisionModel.classify](../VisionModel/classify.md)). |
| [DEPTH](DEPTH.md) | [common]<br>const val [DEPTH](DEPTH.md): [String](https://kotlinlang.org/api/core/kotlin-stdlib/kotlin/-string/index.html)<br>A depth value per pixel ([VisionModel.depth](../VisionModel/depth.md)). |
| [DETECT](DETECT.md) | [common]<br>const val [DETECT](DETECT.md): [String](https://kotlinlang.org/api/core/kotlin-stdlib/kotlin/-string/index.html)<br>Boxes with labels and scores over the picture ([VisionModel.detect](../VisionModel/detect.md)). |
| [EMBED](EMBED.md) | [common]<br>const val [EMBED](EMBED.md): [String](https://kotlinlang.org/api/core/kotlin-stdlib/kotlin/-string/index.html)<br>A vector that stands for the picture ([VisionModel.embed](../VisionModel/embed.md)). |
| [OCR](OCR.md) | [common]<br>const val [OCR](OCR.md): [String](https://kotlinlang.org/api/core/kotlin-stdlib/kotlin/-string/index.html)<br>The text written in the picture ([VisionModel.recognizeText](../VisionModel/recognizeText.md)). |