Input

class Input(dims: Long, name: String) : Layer

This layer is responsible for the input shape of the built model.

First and required layer in org.jetbrains.kotlinx.dl.api.core.Sequential.of method.

Constructors

Input

fun Input(vararg dims: Long, name: String = "")

Creates Input layer from packedDims representing input data shape.

Functions

build

fun build(tf: Ops)

Extend this function to define placeholder in layer.

open override fun build(tf: Ops, inputShape: Shape)

Extend this function to define variables in layer.

buildFromInboundLayers

fun buildFromInboundLayers(tf: Ops)

Extend this function to define variables in layer.

computeOutputShape

fun computeOutputShape(): Shape

Computes output shape, based on input and Layer type.

open override fun computeOutputShape(inputShape: Shape): Shape

Computes output shape, based on inputShape and Layer type.

computeOutputShapeFromInboundLayers

open fun computeOutputShapeFromInboundLayers(): TensorShape

Computes output shape, based on input shapes of inbound layers.

forward

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

Builds main layer input transformation with tf. Depends on Layer type.

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

Builds main layer input transformation with tf. Depends on Layer type.

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.

input

lateinit var input: Placeholder<Float>

Placeholder for input data.

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.

packedDims

var packedDims: LongArray

Input data dimensions. Rank = 3 or 4 for most popular supported cases.

parentModel

var parentModel: GraphTrainableModel? = null

Model where this layer is used.