Normalizing

class Normalizing : FloatArrayOperation
Content copied to clipboard

This preprocessor defines normalizing operation. Given mean and std for n channels, this operation normalizes each channel of the input array, i.e.

output[channel] = (input[channel] - mean[channel]) / std[channel].

Constructors

Normalizing
Link copied to clipboard
common
fun Normalizing()
Content copied to clipboard

Functions

apply
Link copied to clipboard
common
open fun apply(input: <ERROR CLASS><FloatArray, <ERROR CLASS>>): <ERROR CLASS><FloatArray, <ERROR CLASS>>
Content copied to clipboard
getOutputShape
Link copied to clipboard
common
open fun getOutputShape(inputShape: <ERROR CLASS>): <ERROR CLASS>
Content copied to clipboard

Properties

channelsLast
Link copied to clipboard
common
var channelsLast: Boolean = true
Content copied to clipboard

true is channel dimension is the last one, false if it's the first one.

mean
Link copied to clipboard
common
lateinit var mean: FloatArray
Content copied to clipboard

an array of mean values for each channel.

std
Link copied to clipboard
common
lateinit var std: FloatArray
Content copied to clipboard

an array of std values for each channel.