Package oracle.pgx.api.mllib

Class GraphWisePredictionLayerConfigBuilder

java.lang.Object

oracle.pgx.api.mllib.GraphWisePredictionLayerConfigBuilder

public class GraphWisePredictionLayerConfigBuilder
extends java.lang.Object

Builder for GraphWisePredictionLayerConfig.

Since:

19.4

Constructor Summary

Constructors

Constructor	Description
GraphWisePredictionLayerConfigBuilder()

Method Summary

Modifier and Type	Method	Description
GraphWisePredictionLayerConfig	build()	Build the configuration
GraphWisePredictionLayerConfigBuilder	setActivationFunction(ActivationFunction activationFunction)	Set the activation function of the layer.
GraphWisePredictionLayerConfigBuilder	setDropoutRate(double dropoutRate)	Set the dropout rate for this layer.
GraphWisePredictionLayerConfigBuilder	setHiddenDimension(java.lang.Integer hiddenDimension)	Set the hidden dimension of the layer.
GraphWisePredictionLayerConfigBuilder	setWeightInitScheme(WeightInitScheme weightInitScheme)	Sets the weight initialization scheme for the weights of the layer.

Methods inherited from class java.lang.Object

equals, getClass, hashCode, notify, notifyAll, toString, wait, wait, wait

Constructor Detail

GraphWisePredictionLayerConfigBuilder

public GraphWisePredictionLayerConfigBuilder()

Method Detail

setHiddenDimension

public GraphWisePredictionLayerConfigBuilder setHiddenDimension(java.lang.Integer hiddenDimension)

Set the hidden dimension of the layer.

default: GraphWisePredictionLayerConfig.DEFAULT_HIDDEN_DIMENSION

Parameters:

hiddenDimension - hidden dimension

Returns:

this

Since:

19.4

setActivationFunction

public GraphWisePredictionLayerConfigBuilder setActivationFunction(ActivationFunction activationFunction)

Set the activation function of the layer. See ActivationFunction.

default: GraphWisePredictionLayerConfig.DEFAULT_ACTIVATION_FUNCTION

Parameters:

activationFunction - activation function

Returns:

this

Since:

19.4

setWeightInitScheme

public GraphWisePredictionLayerConfigBuilder setWeightInitScheme(WeightInitScheme weightInitScheme)

Sets the weight initialization scheme for the weights of the layer. Note that biases are always initialized with zeros. See WeightInitScheme.

default: GraphWisePredictionLayerConfig.DEFAULT_WEIGHT_INIT_SCHEME

Parameters:

weightInitScheme - weight initialization scheme

Returns:

this

Since:

19.4

setDropoutRate

public GraphWisePredictionLayerConfigBuilder setDropoutRate(double dropoutRate)

Set the dropout rate for this layer. Represents the probability to drop each neuron. Note that dropoutRate must satisfy 0 <= dropoutRate < 1. If dropoutRate = 0, dropout layer will not be constructed.

Note that if it is the last layer, this setting will be ignored and dropout will not be applied

default: GraphWisePredictionLayerConfig.DEFAULT_DROPOUT_RATE

Parameters:

dropoutRate - dropout rate

Returns:

this

Since:

22.3

build

public GraphWisePredictionLayerConfig build()

Build the configuration

Returns:

built configuration

Since:

19.4