public interface IOutputLayer extends Layer, Classifier
Layer.TrainingMode, Layer.Type
Modifier and Type | Method and Description |
---|---|
double |
computeScore(double fullNetworkL1,
double fullNetworkL2,
boolean training)
Compute score after labels and input have been set.
|
org.nd4j.linalg.api.ndarray.INDArray |
computeScoreForExamples(double fullNetworkL1,
double fullNetworkL2)
Compute the score for each example individually, after labels and input have been set.
|
org.nd4j.linalg.api.ndarray.INDArray |
getLabels()
Get the labels array previously set with
setLabels(INDArray) |
void |
setLabels(org.nd4j.linalg.api.ndarray.INDArray labels)
Set the labels array for this output layer
|
activate, activate, activate, activate, activate, activate, activationMean, backpropGradient, calcGradient, calcL1, calcL2, clone, derivativeActivation, error, feedForwardMaskArray, getIndex, getInputMiniBatchSize, getListeners, getMaskArray, isPretrainLayer, merge, preOutput, preOutput, preOutput, setIndex, setInput, setInputMiniBatchSize, setListeners, setListeners, setMaskArray, transpose, type
f1Score, f1Score, fit, fit, fit, fit, labelProbabilities, numLabels, predict, predict
accumulateScore, applyLearningRateScoreDecay, batchSize, clear, computeGradientAndScore, conf, fit, fit, getOptimizer, getParam, gradient, gradientAndScore, init, initParams, input, iterate, numParams, numParams, params, paramTable, paramTable, score, setBackpropGradientsViewArray, setConf, setParam, setParams, setParamsViewArray, setParamTable, update, update, validateInput
void setLabels(org.nd4j.linalg.api.ndarray.INDArray labels)
labels
- Labels array to setorg.nd4j.linalg.api.ndarray.INDArray getLabels()
setLabels(INDArray)
double computeScore(double fullNetworkL1, double fullNetworkL2, boolean training)
fullNetworkL1
- L1 regularization term for the entire networkfullNetworkL2
- L2 regularization term for the entire networktraining
- whether score should be calculated at train or test time (this affects things like application of
dropout, etc)org.nd4j.linalg.api.ndarray.INDArray computeScoreForExamples(double fullNetworkL1, double fullNetworkL2)
fullNetworkL1
- L1 regularization term for the entire network (or, 0.0 to not include regularization)fullNetworkL2
- L2 regularization term for the entire network (or, 0.0 to not include regularization)