---
title: "init(depthwiseWithKernelWidth:kernelHeight:inputFeatureChannelCount:channelMultiplier:)"
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/mlcconvolutiondescriptor/init(depthwisewithkernelwidth:kernelheight:inputfeaturechannelcount:channelmultiplier:)"
---

# init(depthwiseWithKernelWidth:kernelHeight:inputFeatureChannelCount:channelMultiplier:)

Creates a descriptor for depthwise convolution with the kernel sizes, number of input feature channels, and channel multiplier you specify.

## Declaration

```swift
convenience init(depthwiseWithKernelWidth kernelWidth: Int, kernelHeight: Int, inputFeatureChannelCount: Int, channelMultiplier: Int)
```

## Parameters

- `kernelWidth`: The kernel size in x.
- `kernelHeight`: The kernel size in y.
- `inputFeatureChannelCount`: The number of feature channels in the input tensor.
- `channelMultiplier`: The channel multiplier.

## See Also

### Creating Convolution Descriptors

- [init(type:kernelSizes:inputFeatureChannelCount:outputFeatureChannelCount:groupCount:strides:dilationRates:paddingPolicy:)](mlcompute/mlcconvolutiondescriptor/init(type:kernelsizes:inputfeaturechannelcount:outputfeaturechannelcount:groupcount:strides:dilationrates:paddingpolicy:).md)
- [init(transposeWithKernelWidth:kernelHeight:inputFeatureChannelCount:outputFeatureChannelCount:)](mlcompute/mlcconvolutiondescriptor/init(transposewithkernelwidth:kernelheight:inputfeaturechannelcount:outputfeaturechannelcount:).md)
- [MLCConvolutionType](mlcompute/mlcconvolutiontype.md)