Package io.github.kirstenali.deepj.tensor

Class CpuNdNormalization

java.lang.Object

io.github.kirstenali.deepj.tensor.CpuNdNormalization

public final class CpuNdNormalization
extends Object

Last-axis CPU normalization, with FLOAT32 statistics and no intermediate compact rounding.

Method Summary

Modifier and Type	Method	Description
static NormalizationResult	apply(Tensor input, Tensor gamma, Tensor beta, float epsilon, boolean centered)
static Tensor	backward(Tensor gradient, Tensor normalized, Tensor denominator, Tensor gamma, boolean centered)

Methods inherited from class java.lang.Object

clone, equals, finalize, getClass, hashCode, notify, notifyAll, toString, wait, wait, wait

Method Details

apply

public static NormalizationResult apply(Tensor input,
 Tensor gamma,
 Tensor beta,
 float epsilon,
 boolean centered)

backward

public static Tensor backward(Tensor gradient,
 Tensor normalized,
 Tensor denominator,
 Tensor gamma,
 boolean centered)