Cropping3D

class Cropping3D(cropping: Array<IntArray>, name: String) : AbstractCropping

Cropping layer for 3D data (e.g. video, spatio-temporal)

Crops input along the second, third and forth dimensions.

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

Output shape: 5D tensor with shape (batch_size, cropped_dim1, cropped_dim2, cropped_dim3, depth).

Constructors

Cropping3D

fun Cropping3D(cropping: Array<IntArray>, name: String = "")

Functions

build

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

Extend this function to define variables in layer.

buildFromInboundLayers

fun buildFromInboundLayers(tf: Ops, kGraph: KGraph)

Extend this function to define variables in layer.

computeOutputShape

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

cropping

val cropping: Array<IntArray>

An array consisting of three integer arrays of size two which are interpreted as [[left_dim1_crop, right_dim1_crop], [left_dim2_crop, right_dim2_crop], [left_dim3_crop, right_dim3_crop]].

croppingInternal

val croppingInternal: Array<IntArray>

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

hasActivation

open override val hasActivation: Boolean

Returns True, if layer has internal activation function.

inboundLayers

var inboundLayers: MutableList<Layer>

Returns inbound layers.

isTrainable

var isTrainable: Boolean = true

True, if layer's weights could be changed during training. If false, layer's weights are frozen and could be changed during the training.

name

var name: String

outboundLayers