ConvTranspose

abstract class ConvTranspose(dimensions: Int, name: String) : AbstractConv

A base class for defining transposed convolution layers (sometimes called deconvolution) of different dimensions.

This is an operation going in the opposite direction of a normal convolution: it transforms a tensor shaped like an output of some convolution into tensor that has the shape of the input.

Parameters

name

custom layer name

Constructors

ConvTranspose

fun ConvTranspose(dimensions: Int, name: String = "")

Functions

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

Properties

dimensions

val dimensions: Int

dimensionality of this convolution operation

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.

paramCount

open val paramCount: Int

Number of parameters in this layer.

parentModel

var parentModel: GraphTrainableModel? = null

Model where this layer is used.

variables

open override val variables: List<KVariable>

Variables used in this layer.

Inheritors

Conv1DTranspose

Conv2DTranspose

Conv3DTranspose