Uses of Class
org.deeplearning4j.nn.conf.layers.ConvolutionLayer.Builder

Packages that use ConvolutionLayer.Builder

Package	Description
org.deeplearning4j.nn.conf.layers

Uses of ConvolutionLayer.Builder in org.deeplearning4j.nn.conf.layers

Methods in org.deeplearning4j.nn.conf.layers that return ConvolutionLayer.Builder

Modifier and Type	Method and Description
ConvolutionLayer.Builder	ConvolutionLayer.Builder.activation(org.nd4j.linalg.activations.Activation activation)
ConvolutionLayer.Builder	ConvolutionLayer.Builder.activation(org.nd4j.linalg.activations.IActivation activationFunction)
ConvolutionLayer.Builder	ConvolutionLayer.Builder.adamMeanDecay(double adamMeanDecay) Mean decay rate for Adam updater.
ConvolutionLayer.Builder	ConvolutionLayer.Builder.adamVarDecay(double adamVarDecay) Variance decay rate for Adam updater.
ConvolutionLayer.Builder	ConvolutionLayer.Builder.biasInit(double biasInit)
ConvolutionLayer.Builder	ConvolutionLayer.Builder.biasLearningRate(double biasLearningRate) Bias learning rate.
ConvolutionLayer.Builder	ConvolutionLayer.Builder.convolutionMode(ConvolutionMode convolutionMode) Set the convolution mode for the Convolution layer.
ConvolutionLayer.Builder	ConvolutionLayer.Builder.cudnnAlgoMode(ConvolutionLayer.AlgoMode cudnnAlgoMode) Defaults to "PREFER_FASTEST", but "NO_WORKSPACE" uses less memory.
ConvolutionLayer.Builder	ConvolutionLayer.Builder.dist(Distribution dist) Distribution to sample initial weights from.
ConvolutionLayer.Builder	ConvolutionLayer.Builder.dropOut(double dropOut) Dropout.
ConvolutionLayer.Builder	ConvolutionLayer.Builder.epsilon(double epsilon) Epsilon value for updaters: Adagrad and Adadelta.
ConvolutionLayer.Builder	ConvolutionLayer.Builder.gradientNormalization(GradientNormalization gradientNormalization) Gradient normalization strategy.
ConvolutionLayer.Builder	ConvolutionLayer.Builder.gradientNormalizationThreshold(double threshold) Threshold for gradient normalization, only used for GradientNormalization.ClipL2PerLayer, GradientNormalization.ClipL2PerParamType, and GradientNormalization.ClipElementWiseAbsoluteValue Not used otherwise. L2 threshold for first two types of clipping, or absolute value threshold for last type of clipping.
ConvolutionLayer.Builder	ConvolutionLayer.Builder.kernelSize(int... kernelSize) Size of the convolution rows/columns
ConvolutionLayer.Builder	ConvolutionLayer.Builder.l1(double l1) L1 regularization coefficient (weights only).
ConvolutionLayer.Builder	ConvolutionLayer.Builder.l1Bias(double l1Bias) L1 regularization coefficient for the bias.
ConvolutionLayer.Builder	ConvolutionLayer.Builder.l2(double l2) L2 regularization coefficient (weights only).
ConvolutionLayer.Builder	ConvolutionLayer.Builder.l2Bias(double l2Bias) L2 regularization coefficient for the bias.
ConvolutionLayer.Builder	ConvolutionLayer.Builder.learningRate(double learningRate) Learning rate.
ConvolutionLayer.Builder	ConvolutionLayer.Builder.learningRateDecayPolicy(LearningRatePolicy policy) Learning rate decay policy.
ConvolutionLayer.Builder	ConvolutionLayer.Builder.learningRateSchedule(Map<Integer,Double> learningRateSchedule) Learning rate schedule.
ConvolutionLayer.Builder	ConvolutionLayer.Builder.momentum(double momentum) Momentum rate.
ConvolutionLayer.Builder	ConvolutionLayer.Builder.momentumAfter(Map<Integer,Double> momentumAfter) Momentum schedule.
ConvolutionLayer.Builder	ConvolutionLayer.Builder.name(String layerName) Layer name assigns layer string name.
ConvolutionLayer.Builder	ConvolutionLayer.Builder.nIn(int nIn)
ConvolutionLayer.Builder	ConvolutionLayer.Builder.nOut(int nOut)
ConvolutionLayer.Builder	ConvolutionLayer.Builder.padding(int... padding)
ConvolutionLayer.Builder	ConvolutionLayer.Builder.rho(double rho) Ada delta coefficient, rho.
ConvolutionLayer.Builder	ConvolutionLayer.Builder.rmsDecay(double rmsDecay) Decay rate for RMSProp.
ConvolutionLayer.Builder	ConvolutionLayer.Builder.stride(int... stride)
ConvolutionLayer.Builder	ConvolutionLayer.Builder.updater(Updater updater) Gradient updater.
ConvolutionLayer.Builder	ConvolutionLayer.Builder.weightInit(WeightInit weightInit) Weight initialization scheme.