public class DeepWaterParametersV3 extends ModelParametersSchemaV3
| Modifier and Type | Field and Description |
|---|---|
DeepWaterParametersActivation |
activation
Activation function.
|
boolean |
autoencoder
Auto-Encoder.
|
DeepWaterParametersBackend |
backend
Deep Learning Backend.
|
boolean |
balanceClasses
Balance training data class counts via over/under-sampling (for imbalanced data).
|
int |
channels
Number of (color) channels.
|
double |
classificationStop
Stopping criterion for classification error fraction on training data (-1 to disable).
|
float[] |
classSamplingFactors
Desired over/under-sampling ratios per class (in lexicographic order).
|
double |
clipGradient
Clip gradients once their absolute value is larger than this value.
|
int[] |
deviceId
Device IDs (which GPUs to use).
|
boolean |
diagnostics
Enable diagnostics for hidden layers.
|
double |
epochs
How many times the dataset should be iterated (streamed), can be fractional.
|
java.lang.String |
exportNativeParametersPrefix
Path (prefix) where to export the native model parameters after every iteration.
|
boolean |
gpu
Whether to use a GPU (if available).
|
int[] |
hidden
Hidden layer sizes (e.g.
|
double[] |
hiddenDropoutRatios
Hidden layer dropout ratios (can improve generalization), specify one value per hidden layer, defaults to 0.5.
|
int[] |
imageShape
Width and height of image.
|
double |
inputDropoutRatio
Input layer dropout ratio (can improve generalization, try 0.1 or 0.2).
|
double |
learningRate
Learning rate (higher => less stable, lower => slower convergence).
|
double |
learningRateAnnealing
Learning rate annealing: rate / (1 + rate_annealing * samples).
|
float |
maxAfterBalanceSize
Maximum relative size of the training data after balancing class counts (can be less than 1.0).
|
int |
maxConfusionMatrixSize
[Deprecated] Maximum size (# classes) for confusion matrices to be printed in the Logs.
|
int |
maxHitRatioK
Max.
|
java.lang.String |
meanImageFile
Path of file containing the mean image data for data normalization.
|
int |
miniBatchSize
Mini-batch size (smaller leads to better fit, larger can speed up and generalize better).
|
double |
momentumRamp
Number of training samples for which momentum increases.
|
double |
momentumStable
Final momentum after the ramp is over (try 0.99).
|
double |
momentumStart
Initial momentum at the beginning of training (try 0.5).
|
DeepWaterParametersNetwork |
network
Network architecture.
|
java.lang.String |
networkDefinitionFile
Path of file containing network definition (graph, architecture).
|
java.lang.String |
networkParametersFile
Path of file containing network (initial) parameters (weights, biases).
|
boolean |
overwriteWithBestModel
If enabled, override the final model with the best model found during training.
|
DeepWaterParametersProblemType |
problemType
Problem type, auto-detected by default.
|
boolean |
quietMode
Enable quiet mode for less output to standard output.
|
double |
regressionStop
Stopping criterion for regression error (MSE) on training data (-1 to disable).
|
boolean |
replicateTrainingData
Replicate the entire training dataset onto every node for faster training on small datasets.
|
double |
scoreDutyCycle
Maximum duty cycle fraction for scoring (lower: more training, higher: more scoring).
|
double |
scoreInterval
Shortest time interval (in seconds) between model scoring.
|
long |
scoreTrainingSamples
Number of training set samples for scoring (0 for all).
|
long |
scoreValidationSamples
Number of validation set samples for scoring (0 for all).
|
long |
seed
Seed for random numbers (affects sampling) - Note: only reproducible when running single threaded.
|
boolean |
shuffleTrainingData
Enable global shuffling of training data.
|
boolean |
singleNodeMode
Run on a single node for fine-tuning of model parameters.
|
boolean |
sparse
Sparse data handling (more efficient for data with lots of 0 values).
|
boolean |
standardize
If enabled, automatically standardize the data.
|
double |
targetRatioCommToComp
Target ratio of communication overhead to computation.
|
long |
trainSamplesPerIteration
Number of training samples (globally) per MapReduce iteration.
|
boolean |
variableImportances
Compute variable importances for input features (Gedeon method) - can be slow for large networks.
|
categoricalEncoding, checkpoint, distribution, foldAssignment, foldColumn, huberAlpha, ignoreConstCols, ignoredColumns, keepCrossValidationFoldAssignment, keepCrossValidationPredictions, maxRuntimeSecs, modelId, nfolds, offsetColumn, parallelizeCrossValidation, quantileAlpha, responseColumn, scoreEachIteration, stoppingMetric, stoppingRounds, stoppingTolerance, trainingFrame, tweediePower, validationFrame, weightsColumn| Constructor and Description |
|---|
DeepWaterParametersV3()
Public constructor
|
| Modifier and Type | Method and Description |
|---|---|
java.lang.String |
toString()
Return the contents of this object as a JSON String.
|
public DeepWaterParametersProblemType problemType
public DeepWaterParametersActivation activation
public int[] hidden
public double inputDropoutRatio
public double[] hiddenDropoutRatios
public int maxConfusionMatrixSize
public boolean sparse
public int maxHitRatioK
public double epochs
public long trainSamplesPerIteration
public double targetRatioCommToComp
public long seed
public double learningRate
public double learningRateAnnealing
public double momentumStart
public double momentumRamp
public double momentumStable
public double scoreInterval
public long scoreTrainingSamples
public long scoreValidationSamples
public double scoreDutyCycle
public double classificationStop
public double regressionStop
public boolean quietMode
public boolean overwriteWithBestModel
public boolean autoencoder
public boolean diagnostics
public boolean variableImportances
public boolean replicateTrainingData
public boolean singleNodeMode
public boolean shuffleTrainingData
public int miniBatchSize
public double clipGradient
public DeepWaterParametersNetwork network
public DeepWaterParametersBackend backend
public int[] imageShape
public int channels
public boolean gpu
public int[] deviceId
public java.lang.String networkDefinitionFile
public java.lang.String networkParametersFile
public java.lang.String meanImageFile
public java.lang.String exportNativeParametersPrefix
public boolean standardize
public boolean balanceClasses
public float[] classSamplingFactors
public float maxAfterBalanceSize
public java.lang.String toString()
toString in class ModelParametersSchemaV3