Dropout

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.

Dropout

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

Creates Dropout object.

build

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

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

Extend this function to define variables in the layer and compute layer output.

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

hasActivation

Returns True, if layer has internal activation function.

inboundLayers

Returns inbound layers.

name

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

outboundLayers

Returns outbound layers.

outputShape

Output data tensor shape.

parentModel

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.