Dot

class Dot(axis: IntArray, normalize: Boolean, name: String) : AbstractMerge

Layer that computes a dot product between samples in two tensors.

Since

0.4

Parameters

axis

: Axis along which to take the dot product.

normalize

: Whether to L2-normalize samples along the dot product axis before taking the dot product.

Constructors

Dot

fun Dot(axis: Int)

Dot

fun Dot(axis: IntArray, normalize: Boolean = false, name: String = "")

Functions

build

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

open override fun build(tf: Ops, input: 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

Properties

axis

val axis: IntArray

hasActivation

open override val hasActivation: Boolean

Returns True, if layer has internal activation function.

inboundLayers

var inboundLayers: MutableList<Layer>

Returns inbound layers.

layerTypeName

val layerTypeName: String

Specified layer name used for tf operation alias building.

name

var name: String

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

normalize

val normalize: Boolean = false

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.