Uses of Class
org.deeplearning4j.nn.transferlearning.FineTuneConfiguration.Builder

Packages that use FineTuneConfiguration.Builder

Package	Description
org.deeplearning4j.nn.transferlearning

Uses of FineTuneConfiguration.Builder in org.deeplearning4j.nn.transferlearning

Methods in org.deeplearning4j.nn.transferlearning that return FineTuneConfiguration.Builder

Modifier and Type	Method and Description
FineTuneConfiguration.Builder	FineTuneConfiguration.Builder.activation(Activation activation) Activation function / neuron non-linearity
FineTuneConfiguration.Builder	FineTuneConfiguration.Builder.activation(IActivation activationFn) Activation function / neuron non-linearity
FineTuneConfiguration.Builder	FineTuneConfiguration.Builder.backprop(boolean backprop)
FineTuneConfiguration.Builder	FineTuneConfiguration.Builder.backpropType(BackpropType backpropType) The type of backprop.
FineTuneConfiguration.Builder	FineTuneConfiguration.Builder.biasInit(double biasInit) Constant for bias initialization.
FineTuneConfiguration.Builder	FineTuneConfiguration.Builder.biasUpdater(IUpdater biasUpdater) Gradient updater configuration, for the biases only.
static FineTuneConfiguration.Builder	FineTuneConfiguration.builder()
FineTuneConfiguration.Builder	FineTuneConfiguration.Builder.constraints(List<LayerConstraint> constraints) Set constraints to be applied to all layers.
FineTuneConfiguration.Builder	FineTuneConfiguration.Builder.convolutionMode(ConvolutionMode convolutionMode) Sets the convolution mode for convolutional layers, which impacts padding and output sizes.
FineTuneConfiguration.Builder	FineTuneConfiguration.Builder.cudnnAlgoMode(ConvolutionLayer.AlgoMode cudnnAlgoMode) Sets the cuDNN algo mode for convolutional layers, which impacts performance and memory usage of cuDNN.
FineTuneConfiguration.Builder	FineTuneConfiguration.Builder.dist(Distribution dist) Deprecated.
FineTuneConfiguration.Builder	FineTuneConfiguration.Builder.dropOut(double inputRetainProbability) Dropout probability.
FineTuneConfiguration.Builder	FineTuneConfiguration.Builder.dropout(IDropout dropout) Set the dropout
FineTuneConfiguration.Builder	FineTuneConfiguration.Builder.gradientNormalization(GradientNormalization gradientNormalization) Gradient normalization strategy.
FineTuneConfiguration.Builder	FineTuneConfiguration.Builder.gradientNormalizationThreshold(double gradientNormalizationThreshold) 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
FineTuneConfiguration.Builder	FineTuneConfiguration.Builder.inferenceWorkspaceMode(WorkspaceMode inferenceWorkspaceMode) This method defines Workspace mode being used during inference: NONE: workspace won't be used ENABLED: workspaces will be used for inference (reduced memory and better performance)
FineTuneConfiguration.Builder	FineTuneConfiguration.Builder.l1(double l1) L1 regularization coefficient for the weights (excluding biases)
FineTuneConfiguration.Builder	FineTuneConfiguration.Builder.l1Bias(double l1Bias) L1 regularization coefficient for the bias parameters
FineTuneConfiguration.Builder	FineTuneConfiguration.Builder.l2(double l2) L2 regularization coefficient for the weights (excluding biases) Note: Generally, WeightDecay (set via weightDecay(double,boolean) should be preferred to L2 regularization.
FineTuneConfiguration.Builder	FineTuneConfiguration.Builder.l2Bias(double l2Bias) L2 regularization coefficient for the bias parameters Note: Generally, WeightDecay (set via weightDecayBias(double,boolean) should be preferred to L2 regularization.
FineTuneConfiguration.Builder	FineTuneConfiguration.Builder.maxNumLineSearchIterations(int maxNumLineSearchIterations)
FineTuneConfiguration.Builder	FineTuneConfiguration.Builder.miniBatch(boolean miniBatch) Whether scores and gradients should be divided by the minibatch size. Most users should leave this ast he default value of true.
FineTuneConfiguration.Builder	FineTuneConfiguration.Builder.minimize(boolean minimize)
FineTuneConfiguration.Builder	FineTuneConfiguration.Builder.optimizationAlgo(OptimizationAlgorithm optimizationAlgo)
FineTuneConfiguration.Builder	FineTuneConfiguration.Builder.pretrain(boolean pretrain)
FineTuneConfiguration.Builder	FineTuneConfiguration.Builder.seed(int seed) RNG seed for reproducibility
FineTuneConfiguration.Builder	FineTuneConfiguration.Builder.seed(long seed) RNG seed for reproducibility
FineTuneConfiguration.Builder	FineTuneConfiguration.Builder.stepFunction(StepFunction stepFunction)
FineTuneConfiguration.Builder	FineTuneConfiguration.Builder.tbpttBackLength(int tbpttBackLength) When doing truncated BPTT: how many steps of backward should we do? Only applicable when doing backpropType(BackpropType.TruncatedBPTT) This is the k2 parameter on pg23 of http://www.cs.utoronto.ca/~ilya/pubs/ilya_sutskever_phd_thesis.pdf
FineTuneConfiguration.Builder	FineTuneConfiguration.Builder.tbpttFwdLength(int tbpttFwdLength) When doing truncated BPTT: how many steps of forward pass should we do before doing (truncated) backprop? Only applicable when doing backpropType(BackpropType.TruncatedBPTT) Typically tBPTTForwardLength parameter is same as the tBPTTBackwardLength parameter, but may be larger than it in some circumstances (but never smaller) Ideally your training data time series length should be divisible by this This is the k1 parameter on pg23 of http://www.cs.utoronto.ca/~ilya/pubs/ilya_sutskever_phd_thesis.pdf
FineTuneConfiguration.Builder	FineTuneConfiguration.Builder.trainingWorkspaceMode(WorkspaceMode trainingWorkspaceMode) This method defines Workspace mode being used during training: NONE: workspace won't be used ENABLED: workspaces will be used for training (reduced memory and better performance)
FineTuneConfiguration.Builder	FineTuneConfiguration.Builder.updater(IUpdater updater) Gradient updater configuration.
FineTuneConfiguration.Builder	FineTuneConfiguration.Builder.updater(Updater updater) Deprecated. Use updater(IUpdater)
FineTuneConfiguration.Builder	FineTuneConfiguration.Builder.weightDecay(double coefficient) Add weight decay regularization for the network parameters (excluding biases). This applies weight decay with multiplying the learning rate - see WeightDecay for more details.
FineTuneConfiguration.Builder	FineTuneConfiguration.Builder.weightDecay(double coefficient, boolean applyLR) Add weight decay regularization for the network parameters (excluding biases).
FineTuneConfiguration.Builder	FineTuneConfiguration.Builder.weightDecayBias(double coefficient) Weight decay for the biases only - see weightDecay(double) for more details.
FineTuneConfiguration.Builder	FineTuneConfiguration.Builder.weightDecayBias(double coefficient, boolean applyLR) Weight decay for the biases only - see weightDecay(double) for more details
FineTuneConfiguration.Builder	FineTuneConfiguration.Builder.weightInit(Distribution distribution) Set weight initialization scheme to random sampling via the specified distribution.
FineTuneConfiguration.Builder	FineTuneConfiguration.Builder.weightInit(IWeightInit weightInit) Weight initialization scheme to use, for initial weight values
FineTuneConfiguration.Builder	FineTuneConfiguration.Builder.weightInit(WeightInit weightInit) Weight initialization scheme to use, for initial weight values
FineTuneConfiguration.Builder	FineTuneConfiguration.Builder.weightNoise(IWeightNoise weightNoise) Set the weight noise (such as DropConnect and WeightNoise)