Contents

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

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