Class

MPSCNNLocalContrastNormalization

A local-contrast normalization kernel.

Declaration

class MPSCNNLocalContrastNormalization : MPSCNNKernel

Overview

The local contrast normalization kernel is quite similar to the spatial normalization kernel, described in the MPSCNNSpatialNormalization class, in that it applies the kernel over local regions which extend spatially, but are in separate feature channels (i.e., they have the shape 1 x kernel width x kernel height). However, instead of dividing by the local "energy" of the feature, the denominator uses the local variance of the feature - effectively the mean value of the feature is subtracted from the signal. For each feature channel, the function computes the variance VAR(i,j) and mean M(i,j) of X(i,j) inside each rectangle around the spatial point (i,j). Then the result is computed for each element of X as follows:

Y(i,j) = pm + ps * ( X(i,j) - p0 * M(i,j)) / (delta + alpha * VAR(i,j))^beta

Where kw and kh are the values of the kernelWidth and the kernelHeight properties, respectively, and the values of the pm, ps, and p0 properties can be used to offset and scale the result in various ways. For example setting pm=0, ps=1, p0=1, delta=0, alpha=1.0 and beta=0.5 scales input data so that the result has unit variance and zero mean, provided that input variance is positive.

It is your responsibility to ensure that the combination of the values of the delta and alpha properties does not result in a situation where the denominator becomes zero - in such situations the resulting pixel-value is undefined. A good way to guard against tiny variances is to regulate the expression with a small delta value, for example delta=1/1024.

Topics

Initializers

init?(coder: NSCoder, device: MTLDevice)

Initializes a local contrast normalization kernel.

init(device: MTLDevice, kernelWidth: Int, kernelHeight: Int)

Initializes a local contrast normalization kernel.

Instance Properties

var alpha: Float

The "alpha" variable of the kernel function.

var beta: Float

The "beta" variable of the kernel function.

var delta: Float

The "delta" variable of the kernel function.

var p0: Float

The "p0" variable of the kernel function.

var pm: Float

The "pm" variable of the kernel function.

var ps: Float

The "ps" variable of the kernel function.

Relationships

Inherits From

Conforms To

See Also

Normalization Layers

class MPSCNNCrossChannelNormalization

A normalization kernel applied across feature channels.

class MPSCNNCrossChannelNormalizationGradient

A gradient normalization kernel applied across feature channels.

class MPSCNNLocalContrastNormalizationGradient

A gradient local-contrast normalization kernel.

class MPSCNNSpatialNormalization

A spatial normalization kernel.

class MPSCNNSpatialNormalizationGradient

A gradient spatial normalization kernel.

class MPSCNNBatchNormalization

A batch normalization kernel.

class MPSCNNBatchNormalizationGradient

A gradient batch normalization kernel.

class MPSCNNBatchNormalizationState

An object that stores data required to execute batch normalization.

class MPSCNNNormalizationMeanAndVarianceState

An object that stores mean and variance terms used to execute batch normalization.

class MPSCNNBatchNormalizationStatistics

An object that stores statistics required to execute batch normalization.

class MPSCNNBatchNormalizationStatisticsGradient

An object that stores the gradient of the loss function with respect to the batch statistics and batch normalization weights.

class MPSCNNInstanceNormalization

An instance normalization kernel.

class MPSCNNInstanceNormalizationGradient

A gradient instance normalization kernel.

class MPSCNNInstanceNormalizationGradientState

An object that stores information required to execute a gradient pass for instance normalization.

class MPSCNNNormalizationGammaAndBetaState

An object that stores gamma and beta terms used to apply a scale and bias in instance- or batch-normalization operations.