Package org.jetbrains.kotlinx.dl.api.core.layer.convolutional

Types

AbstractConv

abstract class AbstractConv(filtersInternal: Long, kernelSizeInternal: LongArray, stridesInternal: LongArray, dilationsInternal: LongArray, activationInternal: Activations, kernelInitializerInternal: Initializer, biasInitializerInternal: Initializer, kernelRegularizerInternal: Regularizer?, biasRegularizerInternal: Regularizer?, activityRegularizerInternal: Regularizer?, paddingInternal: ConvPadding, useBiasInternal: Boolean, kernelVariableName: String, biasVariableName: String, name: String) : Layer

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. If the child class uses some values for its implementation in other form than it is kept in this child class, then this abstract class internal properties should keep the implementation values while the child class properties should keep the printable values that are more representative. But in most cases, the internal and child values will be the same.

Conv1D

class Conv1D(filters: Long, kernelSize: Long, strides: LongArray, dilations: LongArray, activation: Activations, kernelInitializer: Initializer, biasInitializer: Initializer, kernelRegularizer: Regularizer?, biasRegularizer: Regularizer?, activityRegularizer: Regularizer?, padding: ConvPadding, useBias: Boolean, name: String) : AbstractConv

1D convolution layer (e.g. convolution over audio data).

Conv2D

class Conv2D(filters: Long, kernelSize: LongArray, strides: LongArray, dilations: LongArray, activation: Activations, kernelInitializer: Initializer, biasInitializer: Initializer, kernelRegularizer: Regularizer?, biasRegularizer: Regularizer?, activityRegularizer: Regularizer?, padding: ConvPadding, useBias: Boolean, name: String) : AbstractConv

2D convolution layer (e.g. spatial convolution over images).

Conv3D

class Conv3D(filters: Long, kernelSize: LongArray, strides: LongArray, dilations: LongArray, activation: Activations, kernelInitializer: Initializer, biasInitializer: Initializer, kernelRegularizer: Regularizer?, biasRegularizer: Regularizer?, activityRegularizer: Regularizer?, padding: ConvPadding, useBias: Boolean, name: String) : AbstractConv

3D convolution layer (e.g. spatial convolution over video frames or 3D images).

ConvPadding

enum ConvPadding : Enum<ConvPadding>

Type of padding.

DepthwiseConv2D

class DepthwiseConv2D(kernelSize: LongArray, strides: LongArray, dilations: LongArray, activation: Activations, depthMultiplier: Int, depthwiseInitializer: Initializer, biasInitializer: Initializer, depthwiseRegularizer: Regularizer?, biasRegularizer: Regularizer?, activityRegularizer: Regularizer?, padding: ConvPadding, useBias: Boolean, name: String) : AbstractConv, NoGradients

Depthwise separable 2D convolution. (e.g. spatial convolution over images).

SeparableConv2D

class SeparableConv2D(filters: Long, kernelSize: LongArray, strides: LongArray, dilations: LongArray, activation: Activations, depthMultiplier: Int, depthwiseInitializer: Initializer, pointwiseInitializer: Initializer, biasInitializer: Initializer, depthwiseRegularizer: Regularizer?, pointwiseRegularizer: Regularizer?, biasRegularizer: Regularizer?, activityRegularizer: Regularizer?, padding: ConvPadding, useBias: Boolean, name: String) : Layer, NoGradients

2-D convolution with separable filters.