Class

MPSCNNCrossChannelNormalization

Specifies a normalization kernel across feature channels.

Overview

The normalization kernel applies the kernel to a local region across nearby feature channels, but with no spatial extent (i.e., they have the shape kernel size x 1 x 1). The normalized output is given by the function:

Y(i,j,k) = X(i,j,k) / L(i,j,k)^beta

Where the normalizing factor is:

L(i,j,k) = delta + alpha/N * (sum_{q in Q(k)} X(i,j,q)^2)

Where N is the kernel size. The window Q(k) itself is defined as:

Q(k) = [max(0, k-floor(N/2)), min(D-1, k+floor((N-1)/2))]

Where k is the feature channel index (running from 0 to D-1) and D is the number of feature channels, and the values of alpha, beta, and delta are set via properties.

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.

Symbols

Instance Properties

alpha

The "alpha" variable of the kernel function.

beta

The "beta" variable of the kernel function.

delta

The "delta" variable of the kernel function.

kernelSize

The size of the square kernel window.

Instance Methods

- initWithDevice:kernelSize:

Initializes a normalization kernel in a channel.

Relationships

Inherits From