---
title: "init(featureChannelCount:beta:gamma:varianceEpsilon:)"
framework: ML Compute
role: symbol
role_heading: Initializer
platforms: [iOS 14.0+, iPadOS 14.0+, Mac Catalyst 14.0+, macOS 11.0+, tvOS 14.0+]
path: "mlcompute/mlcinstancenormalizationlayer/init(featurechannelcount:beta:gamma:varianceepsilon:)"
---

# 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.

## Declaration

```swift
convenience init?(featureChannelCount: Int, beta: MLCTensor?, gamma: MLCTensor?, varianceEpsilon: 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.

## See Also

### Creating Instance Normalization Layers

- [init(featureChannelCount:beta:gamma:varianceEpsilon:momentum:)](mlcompute/mlcinstancenormalizationlayer/init(featurechannelcount:beta:gamma:varianceepsilon:momentum:).md)
- [init(featureChannelCount:mean:variance:beta:gamma:varianceEpsilon:momentum:)](mlcompute/mlcinstancenormalizationlayer/init(featurechannelcount:mean:variance:beta:gamma:varianceepsilon:momentum:).md)