ZeroPadding2D

class ZeroPadding2D : AbstractZeroPadding

Zero-padding layer for 2D input (e.g. picture). This layer can add rows and columns of zeros at the top, bottom, left and right side of an image tensor.

Constructors

ZeroPadding2D

fun ZeroPadding2D(padding: Int, dataFormat: String?, name: String = "")

Constructs an instance of ZeroPadding2D layer

ZeroPadding2D

fun ZeroPadding2D(padding: Pair<Int, Int>, dataFormat: String?, name: String = "")

Constructs an instance of ZeroPadding2D layer

ZeroPadding2D

fun ZeroPadding2D(padding: IntArray, dataFormat: String?, name: String = "")

Constructs an instance of ZeroPadding2D layer

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.

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.

padding

val padding: IntArray

4 numbers interpreted as (top_pad, bottom_pad, left_pad, right_pad).

parentModel

var parentModel: GraphTrainableModel? = null

Model where this layer is used.