<!--
{
  "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",
  "metadataVersion" : "0.1.0",
  "role" : "Class",
  "symbol" : {
    "kind" : "Class",
    "modules" : [
      "ML Compute"
    ],
    "preciseIdentifier" : "c:objc(cs)MLCInstanceNormalizationLayer"
  },
  "title" : "MLCInstanceNormalizationLayer"
}
-->

# MLCInstanceNormalizationLayer

A layer that normalizes all features of one channel.

```
class MLCInstanceNormalizationLayer
```

## Topics

### Creating Instance Normalization Layers

[`init(featureChannelCount:beta:gamma:varianceEpsilon:)`](/documentation/MLCompute/MLCInstanceNormalizationLayer/init(featureChannelCount:beta:gamma:varianceEpsilon:))

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

[`init(featureChannelCount:beta:gamma:varianceEpsilon:momentum:)`](/documentation/MLCompute/MLCInstanceNormalizationLayer/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.

[`init(featureChannelCount:mean:variance:beta:gamma:varianceEpsilon:momentum:)`](/documentation/MLCompute/MLCInstanceNormalizationLayer/init(featureChannelCount:mean:variance:beta:gamma:varianceEpsilon:momentum:))

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

### Inspecting Instance Normalization Layers

[`beta`](/documentation/MLCompute/MLCInstanceNormalizationLayer/beta)

The beta tensor.

[`betaParameter`](/documentation/MLCompute/MLCInstanceNormalizationLayer/betaParameter)

The beta tensor parameter you use for optimizer updates.

[`featureChannelCount`](/documentation/MLCompute/MLCInstanceNormalizationLayer/featureChannelCount)

The number of feature channels.

[`gamma`](/documentation/MLCompute/MLCInstanceNormalizationLayer/gamma)

The gamma tensor.

[`gammaParameter`](/documentation/MLCompute/MLCInstanceNormalizationLayer/gammaParameter)

The gamma tensor parameter you use for optimizer updates.

[`mean`](/documentation/MLCompute/MLCInstanceNormalizationLayer/mean)

The running mean tensor.

[`momentum`](/documentation/MLCompute/MLCInstanceNormalizationLayer/momentum)

The momentum value for the running mean and variance computation.

[`variance`](/documentation/MLCompute/MLCInstanceNormalizationLayer/variance)

The running variance tensor.

[`varianceEpsilon`](/documentation/MLCompute/MLCInstanceNormalizationLayer/varianceEpsilon)

The variance epsilon you use for numerical stability.


---

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)