<!--
{
  "availability" : [
    "iOS: 15.0.0 -",
    "iPadOS: 15.0.0 -",
    "macCatalyst: 15.0.0 -",
    "macOS: 12.0.0 -",
    "visionOS: 1.0.0 -"
  ],
  "documentType" : "symbol",
  "framework" : "CreateML",
  "identifier" : "/documentation/CreateML/MLHandActionClassifier/ModelParameters-swift.struct/init(validation:batchSize:maximumIterations:predictionWindowSize:augmentationOptions:algorithm:targetFrameRate:)",
  "metadataVersion" : "0.1.0",
  "role" : "Initializer",
  "symbol" : {
    "kind" : "Initializer",
    "modules" : [
      "Create ML"
    ],
    "preciseIdentifier" : "s:8CreateML22MLHandActionClassifierV15ModelParametersV10validation9batchSize17maximumIterations016predictionWindowJ019augmentationOptions9algorithm15targetFrameRateA2E14ValidationDataO_S3iAC017VideoAugmentationP0VAE0F13AlgorithmTypeOSdtcfc"
  },
  "title" : "init(validation:batchSize:maximumIterations:predictionWindowSize:augmentationOptions:algorithm:targetFrameRate:)"
}
-->

# init(validation:batchSize:maximumIterations:predictionWindowSize:augmentationOptions:algorithm:targetFrameRate:)

Creates a set of training session parameters for a hand action
classifier task.

```
init(validation: MLHandActionClassifier.ModelParameters.ValidationData = .split(strategy: .automatic), batchSize: Int = MLHandActionClassifier.__Defaults.batchSize, maximumIterations: Int = MLHandActionClassifier.__Defaults.maximumIterations, predictionWindowSize: Int = MLHandActionClassifier.__Defaults.predictionWindowSize, augmentationOptions: MLHandActionClassifier.VideoAugmentationOptions = [], algorithm: MLHandActionClassifier.ModelParameters.ModelAlgorithmType = .gcn, targetFrameRate: Double = MLHandActionClassifier.__Defaults.targetFrameRate)
```

## Discussion

- validation: An
  [`MLHandActionClassifier.ModelParameters.ValidationData`](/documentation/CreateML/MLHandActionClassifier/ModelParameters-swift.struct/ValidationData)
  instance.
- batchSize: The number of videos 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 frames the training session
  uses to train a hand action classifier. For example, set to 60 to
  capture hand actions that take 2 seconds from videos that have a
  frame rate of 30 frames per second.
- augmentationOptions: The variations the training session uses to
  add more variety to its training dataset.
- algorithm: The algorithm the training session uses to train the
  hand action classifier.
- targetFrameRate: The number of frames the training session uses
  per second of video to train a hand action 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)