---
title: CoreMLRequest
framework: vision
role: symbol
role_heading: Structure
path: vision/coremlrequest
---

# CoreMLRequest

An image-analysis request that uses a Core ML model to process images.

## Declaration

```swift
struct CoreMLRequest
```

## Overview

Overview The results array of a Core ML-based image-analysis request contain a different observation type, depending on the kind of MLModel object you use: If the model predicts a single feature and the model’s MLModelDescription object has a non-nil value for predictedFeatureName, then Vision treats the model as a classifier. The results are ClassificationObservation objects. If the model’s outputs include at least one output with a feature type of MLFeatureType.image, Vision treats that model as an image-to-image model. The results are PixelBufferObservation objects. Otherwise, Vision treats the model as a general predictor model. The results are CoreMLFeatureValueObservation objects. note: Vision forwards all confidence values from Core ML models as-is and doesn’t normalize them to [0, 1].

## Topics

### Creating a request

- [init(model:_:)](vision/coremlrequest/init(model:_:).md)

### Performing a request

- [perform(on:orientation:)](vision/imageprocessingrequest/perform(on:orientation:)-80bya.md)
- [perform(on:orientation:)](vision/imageprocessingrequest/perform(on:orientation:)-3f3f1.md)
- [perform(on:orientation:)](vision/imageprocessingrequest/perform(on:orientation:)-qxxx.md)
- [perform(on:orientation:)](vision/imageprocessingrequest/perform(on:orientation:)-xspx.md)
- [perform(on:orientation:)](vision/imageprocessingrequest/perform(on:orientation:)-3hddl.md)
- [perform(on:orientation:)](vision/imageprocessingrequest/perform(on:orientation:)-85ex1.md)

### Understanding the result

- [PixelBufferObservation](vision/pixelbufferobservation.md)
- [ClassificationObservation](vision/classificationobservation.md)
- [CoreMLFeatureValueObservation](vision/coremlfeaturevalueobservation.md)

### Configuring a request

- [supportedIdentifiers](vision/coremlrequest/supportedidentifiers.md)
- [modelContainer](vision/coremlrequest/modelcontainer.md)
- [CoreMLModelContainer](vision/coremlmodelcontainer.md)
- [ComputeStage](vision/computestage.md)
- [cropAndScaleAction](vision/coremlrequest/cropandscaleaction.md)
- [ImageCropAndScaleAction](vision/imagecropandscaleaction.md)

### Getting the revision

- [revision](vision/coremlrequest/revision-swift.property.md)
- [supportedRevisions](vision/coremlrequest/supportedrevisions.md)
- [CoreMLRequest.Revision](vision/coremlrequest/revision-swift.enum.md)

## Relationships

### Conforms To

- [CustomStringConvertible](swift/customstringconvertible.md)
- [Equatable](swift/equatable.md)
- [Hashable](swift/hashable.md)
- [ImageProcessingRequest](vision/imageprocessingrequest.md)
- [Sendable](swift/sendable.md)
- [SendableMetatype](swift/sendablemetatype.md)
- [VisionRequest](vision/visionrequest.md)