Package io.github.kirstenali.deepj.tensor

Class CpuNdStatistics

java.lang.Object

io.github.kirstenali.deepj.tensor.CpuNdStatistics

public final class CpuNdStatistics
extends Object

Two-pass FLOAT32 statistics without a full-sized FLOAT32 shadow of compact input.

Method Summary

Modifier and Type	Method	Description
static Tensor	maximum(Tensor input, int[] axes, boolean keep)
static Tensor	maximumGradient(Tensor input, Tensor maximum, Tensor gradient, int[] axes, boolean keep)
static Tensor	variance(Tensor input, int[] axes, boolean keep, int correction)

Methods inherited from class java.lang.Object

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

Method Details

variance

public static Tensor variance(Tensor input,
 int[] axes,
 boolean keep,
 int correction)

maximum

public static Tensor maximum(Tensor input,
 int[] axes,
 boolean keep)

maximumGradient

public static Tensor maximumGradient(Tensor input,
 Tensor maximum,
 Tensor gradient,
 int[] axes,
 boolean keep)