Package io.github.kirstenali.deepj.nn

Class Dropout

java.lang.Object

io.github.kirstenali.deepj.nn.Module

io.github.kirstenali.deepj.nn.Dropout

All Implemented Interfaces:

Layer, Trainable

public final class Dropout
extends Module

Inverted dropout. Only random mask generation uses the host; tensor arithmetic uses the backend.

Constructor Summary

Constructors

Constructor	Description
Dropout(float probability, long seed)
Dropout(float probability, Random random)

Method Summary

Modifier and Type	Method	Description
Tensor	forward(Tensor input)

Methods inherited from class io.github.kirstenali.deepj.nn.Module

buffers, children, eval, isTraining, parameters, setTraining, train

Methods inherited from class java.lang.Object

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

Methods inherited from interface io.github.kirstenali.deepj.layers.Layer

forward, supportsIncrementalInference

Methods inherited from interface io.github.kirstenali.deepj.training.Trainable

zeroGrad

Constructor Details

Dropout

public Dropout(float probability,
 long seed)

Dropout

public Dropout(float probability,
 Random random)

Method Details

forward

public Tensor forward(Tensor input)