occurrences cannot be negative error

Question

Hell, Im running a simple regression.My network configuration is as below

    MultiLayerConfiguration conf = new NeuralNetConfiguration.Builder()
            .seed(seed)
            .iterations(1)
            .optimizationAlgo(OptimizationAlgorithm.STOCHASTIC_GRADIENT_DESCENT)
            .learningRate(learningRate)
            .updater(Updater.NESTEROVS)
            .weightInit(WeightInit.XAVIER)
            .list()
            .layer(0, new DenseLayer.Builder().nIn(numInputs).nOut(numHiddenNodes)
                    .activation(Activation.RELU)
                    .build())

            .layer(1, new DenseLayer.Builder().nIn(numHiddenNodes).nOut(numHiddenNodes)
                    .activation(Activation.RELU)
                    .build())

            .layer(2, new OutputLayer.Builder(LossFunctions.LossFunction.MSE)
                    .activation(Activation.RELU)
                    .nIn(numHiddenNodes).nOut(numOutputs).build())
            .pretrain(false).backprop(true).build();

Im getting the following error

Exception in thread "main" java.lang.IllegalArgumentException: occurrences cannot be negative: -992 at com.google.common.base.Preconditions.checkArgument(Preconditions.java:145) at com.google.common.collect.AbstractMapBasedMultiset.add(AbstractMapBasedMultiset.java:218) at com.google.common.collect.HashMultiset.add(HashMultiset.java:34)

This is a practice code. I get this error when I try to evaluate the model. The model training itself runs fine but fails in evaluation.Any idea.

Answer 1

I did not noramalize the lables earlier preProcessor.fitLabel(true) in my preprocessor to normalize the labels as well along with the inputs.