UpSampling3D

class UpSampling3D(size: IntArray, name: String) : AbstractUpSampling

Upsampling layer for 3D input.

Repeats the second, third and forth dimensions of the input by size[0], size[1] and size[2] times, respectively.

Input shape: 5D tensor with shape (batch_size, dim1, dim2, dim3, depth).

Output shape: 5D tensor with shape (batch_size, dim1 * size[0], dim2 * size[1], dim3 * size[2], depth).

Since

0.3

Constructors

UpSampling3D

fun UpSampling3D(size: IntArray = intArrayOf(2, 2, 2), 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

hasActivation

open override val hasActivation: Boolean

Returns True, if layer has internal activation function.

inboundLayers

var inboundLayers: MutableList<Layer>

Returns inbound layers.

interpolationInternal

val interpolationInternal: InterpolationMethod

Interpolation method used for filling values (only applicable to 2D data for the moment).

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.

size

val size: IntArray

Upsampling factor array of size 3 (i.e. number of repeats per each dimension).

sizeInternal

val sizeInternal: IntArray

UpSampling size factors; currently, they are not used in the implementation of this abstract class and each subclassed layer uses its own copy of the upsampling size factors.