MPSCNNSpatialNormalization
A spatial normalization kernel.
Declaration
class MPSCNNSpatialNormalizationOverview
The spatial normalization for a feature channel 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).
For each feature channel, the function computes the sum of squares of X inside each rectangle, N2(i,j). It then divides each element of X as follows:
[Image]
Where kw and kh are the values of the kernelWidth and kernelHeight properties, respectively. It is your responsibility to ensure that the combination of the values of the delta and alpha kernelWidth kernelHeight properties does not result in a situation where the denominator becomes zero (in such situations the resulting pixel-value is undefined).
Topics
Initializers
Instance Properties
Instance Methods
See Also
Normalization Layers
MPSCNNCrossChannelNormalizationMPSCNNCrossChannelNormalizationGradientMPSCNNLocalContrastNormalizationMPSCNNLocalContrastNormalizationGradientMPSCNNSpatialNormalizationGradientMPSCNNBatchNormalizationMPSCNNBatchNormalizationGradientMPSCNNBatchNormalizationStateMPSCNNNormalizationMeanAndVarianceStateMPSCNNBatchNormalizationStatisticsMPSCNNBatchNormalizationStatisticsGradientMPSCNNInstanceNormalizationMPSCNNInstanceNormalizationGradientMPSCNNInstanceNormalizationGradientStateMPSCNNNormalizationGammaAndBetaState