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

Types

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.

Conv1D

class Conv1D(filters: Int, kernelLength: Int, strides: IntArray, dilations: IntArray, activation: Activations, kernelInitializer: Initializer, biasInitializer: Initializer, kernelRegularizer: Regularizer?, biasRegularizer: Regularizer?, activityRegularizer: Regularizer?, padding: ConvPadding, useBias: Boolean, name: String) : AbstractConv, TrainableLayer

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

Conv1DTranspose

class Conv1DTranspose(filters: Int, kernelLength: Int, strides: IntArray, dilations: IntArray, activation: Activations, kernelInitializer: Initializer, biasInitializer: Initializer, kernelRegularizer: Regularizer?, biasRegularizer: Regularizer?, activityRegularizer: Regularizer?, padding: ConvPadding, outputPadding: IntArray?, useBias: Boolean, name: String) : ConvTranspose, NoGradients

1D convolution transpose layer.

Conv2D

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

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

Conv2DTranspose

class Conv2DTranspose(filters: Int, kernelSize: IntArray, strides: IntArray, dilations: IntArray, activation: Activations, kernelInitializer: Initializer, biasInitializer: Initializer, kernelRegularizer: Regularizer?, biasRegularizer: Regularizer?, activityRegularizer: Regularizer?, padding: ConvPadding, outputPadding: IntArray?, useBias: Boolean, name: String) : ConvTranspose, NoGradients

2D convolution transpose layer.

Conv3D

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

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

Conv3DTranspose

class Conv3DTranspose(filters: Int, kernelSize: IntArray, strides: IntArray, dilations: IntArray, activation: Activations, kernelInitializer: Initializer, biasInitializer: Initializer, kernelRegularizer: Regularizer?, biasRegularizer: Regularizer?, activityRegularizer: Regularizer?, padding: ConvPadding, useBias: Boolean, name: String) : ConvTranspose, NoGradients

3D convolution transpose layer.

ConvPadding

enum ConvPadding : Enum<ConvPadding>

Type of padding.

ConvTranspose

abstract class ConvTranspose(dimensions: Int, name: String) : AbstractConv

A base class for defining transposed convolution layers (sometimes called deconvolution) of different dimensions.

DepthwiseConv2D

class DepthwiseConv2D(kernelSize: IntArray, strides: IntArray, dilations: IntArray, 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: Int, kernelSize: IntArray, strides: IntArray, dilations: IntArray, 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, ParametrizedLayer

2-D convolution with separable filters.