<!--
{
  "availability" : [
    "macOS: 14.0.0 -"
  ],
  "documentType" : "symbol",
  "framework" : "CreateML",
  "identifier" : "/documentation/CreateML/MLActivityClassifier/ModelParameters-swift.struct/init(validation:batchSize:maximumIterations:predictionWindowSize:)",
  "metadataVersion" : "0.1.0",
  "role" : "Initializer",
  "symbol" : {
    "kind" : "Initializer",
    "modules" : [
      "Create ML"
    ],
    "preciseIdentifier" : "s:8CreateML20MLActivityClassifierV15ModelParametersV10validation9batchSize17maximumIterations016predictionWindowI0A2E10ValidationO_SiSgA2Ltcfc"
  },
  "title" : "init(validation:batchSize:maximumIterations:predictionWindowSize:)"
}
-->

# init(validation:batchSize:maximumIterations:predictionWindowSize:)

Creates a set of activity classifier parameters that includes a
validation dataset in a data source.

```
init(validation: MLActivityClassifier.ModelParameters.Validation = .split(strategy: .automatic), batchSize: Int? = 32, maximumIterations: Int? = 10, predictionWindowSize: Int? = 100)
```

## Parameters

`validation`

An [`MLActivityClassifier.DataSource`](/documentation/CreateML/MLActivityClassifier/DataSource) instance that contains a validation dataset.

`batchSize`

The number of activity entries the training session uses for each of its training iterations.

`maximumIterations`

The largest number of training iterations the training session can use.

`predictionWindowSize`

The number of time increments the training session uses to train an activity
classifier.

---

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)