Dropout

class Dropout(rate: Float, seed: Long, name: String) : Layer, NoGradients

Applies Dropout to the input.

The Dropout layer randomly sets input units to 0 with a frequency of rate at each step during training time, which helps prevent overfitting.

Inputs not set to 0 are scaled up by 1/(1 - rate) such that the sum over all inputs is unchanged.

NOTE: Export for this layer is not supported yet. NOTE: This layer used for inference purposes only.

Parameters

name

Custom layer name.

Constructors

Dropout

fun Dropout(rate: Float = 0.1f, seed: Long = 12L, name: String = "")

Creates Dropout object.

Functions

build

open override fun build(tf: Ops, inputShape: Shape)

Extend this function to define variables in layer.

buildFromInboundLayers

fun buildFromInboundLayers(tf: Ops)

Extend this function to define variables in layer.

computeOutputShape

open override fun computeOutputShape(inputShape: Shape): Shape

Computes output shape, based on inputShape and Layer type.

computeOutputShapeFromInboundLayers

open fun computeOutputShapeFromInboundLayers(): TensorShape

Computes output shape, based on input shapes of inbound layers.

forward

open override fun forward(tf: Ops, input: Operand<Float>, isTraining: Operand<Boolean>, numberOfLosses: Operand<Float>?): Operand<Float>

Builds main layer input transformation with tf. Depends on Layer type.

open fun forward(tf: Ops, input: List<Operand<Float>>, isTraining: Operand<Boolean>, numberOfLosses: Operand<Float>?): Operand<Float>

Builds main layer input transformation with tf. Depends on Layer type.

invoke

operator fun invoke(vararg layers: Layer): Layer

Important part of functional API. It takes layers as input and saves them to the inboundLayers of the given layer.

toString

open override fun toString(): String

Properties

hasActivation

open override val hasActivation: Boolean

Returns True, if layer has internal activation function.

inboundLayers

var inboundLayers: MutableList<Layer>

Returns inbound layers.

name

var name: String

Layer name. A new name is generated during model compilation when provided name is empty.

outboundLayers

var outboundLayers: MutableList<Layer>

Returns outbound layers.

outputShape

lateinit var outputShape: TensorShape

Output data tensor shape.

parentModel

var parentModel: GraphTrainableModel? = null

Model where this layer is used.

rate

val rate: Float = 0.1f

A fraction of the input units to drop, should be between 0 and 1.

seed

val seed: Long = 12L

A seed for the random number generator.