<!--
{
  "availability" : [
    "iOS: 15.0.0 -",
    "iPadOS: 15.0.0 -",
    "macCatalyst: 15.0.0 -",
    "macOS: 11.0.0 -",
    "visionOS: 1.0.0 -"
  ],
  "documentType" : "symbol",
  "framework" : "CreateML",
  "identifier" : "/documentation/CreateML/MLImageClassifier/ModelParameters-swift.struct/init(validation:maxIterations:augmentation:algorithm:)",
  "metadataVersion" : "0.1.0",
  "role" : "Initializer",
  "symbol" : {
    "kind" : "Initializer",
    "modules" : [
      "Create ML"
    ],
    "preciseIdentifier" : "s:8CreateML17MLImageClassifierV15ModelParametersV10validation13maxIterations12augmentation9algorithmA2E14ValidationDataO_SiAC24ImageAugmentationOptionsVAE0E13AlgorithmTypeOtcfc"
  },
  "title" : "init(validation:maxIterations:augmentation:algorithm:)"
}
-->

# init(validation:maxIterations:augmentation:algorithm:)

Creates model training parameters.

```
init(validation: MLImageClassifier.ModelParameters.ValidationData = __Defaults.validation, maxIterations: Int = __Defaults.maximumIterations, augmentation: MLImageClassifier.ImageAugmentationOptions, algorithm: MLImageClassifier.ModelParameters.ModelAlgorithmType = __Defaults.algorithm)
```

## Parameters

`validation`

Labeled data that the model evaluates on for validation. The default is
`.split(strategy: .automatic)`.

`maxIterations`

The maximum number of training iterations to use during training. The default is 25.

`augmentation`

The image augmentation options to use to increase the training data variety. If no data
augmentation needs to be applied, use `[]` as input. Otherwise, inputs take the form `[.crop, .blur]`.

`algorithm`

The type of model algorithm to use for training. The default is a logistic regression
classifier with a `sceneprint(revision: 1)` feature extractor.

---

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)