Package org.deeplearning4j.nn.layers.recurrent

Class RnnOutputLayer

    • Method Detail

      • backpropGradient

        public Pair<Gradient,​INDArray> backpropGradient​(INDArray epsilon,
                                                      LayerWorkspaceMgr workspaceMgr)
        Description copied from interface: Layer
        Calculate the gradient relative to the error in the next layer
        Specified by:
        backpropGradient in interface Layer
        Overrides:
        backpropGradient in class BaseOutputLayer<RnnOutputLayer>
        Parameters:
        epsilon - w^(L+1)*delta^(L+1). Or, equiv: dC/da, i.e., (dC/dz)*(dz/da) = dC/da, where C is cost function a=sigma(z) is activation.
        workspaceMgr - Workspace manager
        Returns:
        Pair where Gradient is gradient for this layer, INDArray is epsilon (activation gradient) needed by next layer, but before element-wise multiply by sigmaPrime(z). So for standard feed-forward layer, if this layer is L, then return.getSecond() == dL/dIn = (w^(L)*(delta^(L))^T)^T. Note that the returned array should be placed in the ArrayType.ACTIVATION_GRAD workspace via the workspace manager

      • f1Score

        public double f1Score​(INDArray examples,
                      INDArray labels)
        Returns the f1 score for the given examples.
        Specified by:
        f1Score in interface Classifier
        Overrides:
        f1Score in class BaseOutputLayer<RnnOutputLayer>
        Parameters:
        examples - te the examples to classify (one example in each row)
        labels - the true labels
        Returns:
        the scores for each ndarray

      • activate

        public INDArray activate​(boolean training,
                         LayerWorkspaceMgr workspaceMgr)
        Description copied from interface: Layer
        Perform forward pass and return the activations array with the last set input
        Specified by:
        activate in interface Layer
        Overrides:
        activate in class BaseLayer<RnnOutputLayer>
        Parameters:
        training - training or test mode
        workspaceMgr - Workspace manager
        Returns:
        the activation (layer output) of the last specified input. Note that the returned array should be placed in the ArrayType.ACTIVATIONS workspace via the workspace manager

      • feedForwardMaskArray

        public Pair<INDArray,​MaskState> feedForwardMaskArray​(INDArray maskArray,
                                                           MaskState currentMaskState,
                                                           int minibatchSize)
        Description copied from interface: Layer
        Feed forward the input mask array, setting in the layer as appropriate. This allows different layers to handle masks differently - for example, bidirectional RNNs and normal RNNs operate differently with masks (the former sets activations to 0 outside of the data present region (and keeps the mask active for future layers like dense layers), whereas normal RNNs don't zero out the activations/errors )instead relying on backpropagated error arrays to handle the variable length case.
        This is also used for example for networks that contain global pooling layers, arbitrary preprocessors, etc.
        Specified by:
        feedForwardMaskArray in interface Layer
        Overrides:
        feedForwardMaskArray in class AbstractLayer<RnnOutputLayer>
        Parameters:
        maskArray - Mask array to set
        currentMaskState - Current state of the mask - see MaskState
        minibatchSize - Current minibatch size. Needs to be known as it cannot always be inferred from the activations array due to reshaping (such as a DenseLayer within a recurrent neural network)
        Returns:
        New mask array after this layer, along with the new mask state.

      • computeScoreForExamples

        public INDArray computeScoreForExamples​(double fullNetRegTerm,
                                        LayerWorkspaceMgr workspaceMgr)
        Compute the score for each example individually, after labels and input have been set.
        Specified by:
        computeScoreForExamples in interface IOutputLayer
        Overrides:
        computeScoreForExamples in class BaseOutputLayer<RnnOutputLayer>
        Parameters:
        fullNetRegTerm - Regularization score term for the entire network (or, 0.0 to not include regularization)
        Returns:
        A column INDArray of shape [numExamples,1], where entry i is the score of the ith example