DataPredict

API Reference - Models - ConditionalWassersteinGenerativeAdversarialNetwork (CWGAN)

ConditionalWassersteinGenerativeAdversarialNetwork uses two neural networks to generate new contents from noise.

Notes

Constructors

new()

Create new model object. If any of the arguments are nil, default argument values for that argument will be used.

ConditionalWassersteinGenerativeAdversarialNetwork.new(generatorMaximumNumberOfIterations: number, discriminatorMaximumNumberOfIterations: number, sampleSize: number): ModelObject

Parameters:

Returns:

Functions

setParameters()

Set model’s parameters. When any of the arguments are nil, previous argument values for that argument will be used.

ConditionalWassersteinGenerativeAdversarialNetwork:setParameters(generatorMaximumNumberOfIterations: number, discriminatorMaximumNumberOfIterations: number, sampleSize: number)

Parameters:

setGeneratorModel()

Sets the Generator into the model.

ConditionalWassersteinGenerativeAdversarialNetwork:setGeneratorModel(GeneratorModel: Model)

Parameters:

setDiscriminatorModel()

Sets the Discriminator into the model.

ConditionalWassersteinGenerativeAdversarialNetwork:setDiscriminatorModel(DiscriminatorModel: Model)

Parameters:

getGeneratorModel()

Gets the Generator from the model.

ConditionalWassersteinGenerativeAdversarialNetwork:getGeneratorModel(): Model

Returns:

getDiscriminatorModel()

Gets the Discriminator from the model.

ConditionalWassersteinGenerativeAdversarialNetwork:getDiscriminatorModel(): Model

Returns:

train()

Trains the model.

ConditionalWassersteinGenerativeAdversarialNetwork:train(realFeatureMatrix: matrix, noiseFeatureMatrix: matrix, labelMatrix: matrix)

Parameters:

evaluate()

Generates the output from Discriminator.

ConditionalWassersteinGenerativeAdversarialNetwork:evaluate(featureMatrix: matrix, labelMatrix: matrix): matrix

Parameters:

Returns:

generate()

Generates the output from Generator.

ConditionalWassersteinGenerativeAdversarialNetwork:generate(noiseFeatureMatrix: matrix, labelMatrix: matrix): matrix

Parameters:

Returns:

References