<!--
{
  "availability" : [
    "iOS: 14.0.0 - 17.4.0",
    "iPadOS: 14.0.0 - 17.4.0",
    "macCatalyst: 14.0.0 - 17.4.0",
    "macOS: 11.0.0 - 14.3.0",
    "tvOS: 14.0.0 - 17.4.0"
  ],
  "documentType" : "symbol",
  "framework" : "MLCompute",
  "identifier" : "/documentation/MLCompute/MLCInstanceNormalizationLayer/init(featureChannelCount:beta:gamma:varianceEpsilon:momentum:)",
  "metadataVersion" : "0.1.0",
  "role" : "Initializer",
  "symbol" : {
    "kind" : "Initializer",
    "modules" : [
      "ML Compute"
    ],
    "preciseIdentifier" : "c:objc(cs)MLCInstanceNormalizationLayer(cm)layerWithFeatureChannelCount:beta:gamma:varianceEpsilon:momentum:"
  },
  "title" : "init(featureChannelCount:beta:gamma:varianceEpsilon:momentum:)"
}
-->

# init(featureChannelCount:beta:gamma:varianceEpsilon:momentum:)

Creates an instance normalization layer with the number of feature channels, beta and gamma tensors, variance epsilon, and momentum you specify.

```
convenience init?(featureChannelCount: Int, beta: MLCTensor?, gamma: MLCTensor?, varianceEpsilon: Float, momentum: Float)
```

## Parameters

`featureChannelCount`

The number of feature channels.

`beta`

The beta tensor.

`gamma`

The gamma tensor.

`varianceEpsilon`

The variance epsilon you use for numerical stability.

`momentum`

The momentum value for the running mean and variance computation.

## Discussion

---

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)