Input

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

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

Constructors

Input

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

Creates Input layer from packedDims representing input data shape.

build

fun build(tf: Ops): Placeholder<Float>

Extend this function to define placeholder in layer.

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

hasActivation

Returns True, if layer has internal activation function.

inboundLayers

Returns inbound layers.

input

lateinit var input: Placeholder<Float>

Placeholder for input data.

name

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

outboundLayers

Returns outbound layers.

outputShape

Output data tensor shape.

packedDims

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

parentModel

Model where this layer is used.