<!--
{
  "availability" : [
    "iOS: 15.0.0 -",
    "iPadOS: 15.0.0 -",
    "macCatalyst: 15.0.0 -",
    "macOS: 10.14.0 -",
    "visionOS: 1.0.0 -"
  ],
  "documentType" : "symbol",
  "framework" : "CreateML",
  "identifier" : "/documentation/CreateML/MLImageClassifier/ImageAugmentationOptions/blur",
  "metadataVersion" : "0.1.0",
  "role" : "Type Property",
  "symbol" : {
    "kind" : "Type Property",
    "modules" : [
      "Create ML"
    ],
    "preciseIdentifier" : "s:8CreateML17MLImageClassifierV24ImageAugmentationOptionsV4blurAEvpZ"
  },
  "title" : "blur"
}
-->

# blur

An option for augmenting training data by blurring each image.

```
static let blur: MLImageClassifier.ImageAugmentationOptions
```

## Discussion

Use this option to tell the image classifier to augment your training data set by creating blurred versions
of the original images.

![Diagram showing how the original image results in four blurred variants.](images/com.apple.createml/MLImageClassifier-ImageAugmentationOptions-blur-1@2x.png)

The classifier creates four new images with random amounts of blur for each original.

---

Copyright &copy; 2026 Apple Inc. All rights reserved. | [Terms of Use](https://www.apple.com/legal/internet-services/terms/site.html) | [Privacy Policy](https://www.apple.com/privacy/privacy-policy)