AbstractConv

abstract class AbstractConv(name: String) : Layer, ParametrizedLayer

Abstract Convolutional layer is a base block for building base types of convolutional layers of any dimensionality. It should simplify the internal calculations needed in most convolutional layers and abstract the naming weights for these layers. It keeps the actual implementation of convolutional layers, i.e., the kernel and bias learnable variables that should be used in child classes in actual implementations of these layers.

Parameters

name

of the layer to name its variables

Constructors

AbstractConv

fun AbstractConv(name: String)

Creates AbstractConv object

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.

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.

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

Conv1D

Conv2D

Conv3D

ConvTranspose

DepthwiseConv2D