Package org.deeplearning4j.nn.layers.convolution.subsampling

Class SubsamplingLayer

    • Method Detail

      • calcRegularizationScore

        public double calcRegularizationScore​(boolean backpropOnlyParams)
        Description copied from interface: Layer
        Calculate the regularization component of the score, for the parameters in this layer
        For example, the L1, L2 and/or weight decay components of the loss function
        Specified by:
        calcRegularizationScore in interface Layer
        Overrides:
        calcRegularizationScore in class AbstractLayer<SubsamplingLayer>
        Parameters:
        backpropOnlyParams - If true: calculate regularization score based on backprop params only. If false: calculate based on all params (including pretrain params, if any)
        Returns:
        the regularization score of

      • 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
        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

      • 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
        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

      • isPretrainLayer

        public boolean isPretrainLayer()
        Description copied from interface: Layer
        Returns true if the layer can be trained in an unsupervised/pretrain manner (AE, VAE, etc)
        Returns:
        true if the layer can be pretrained (using fit(INDArray), false otherwise

      • clearNoiseWeightParams

        public void clearNoiseWeightParams()

      • setParams

        public void setParams​(INDArray params)
        Description copied from interface: Model
        Set the parameters for this model. This expects a linear ndarray which then be unpacked internally relative to the expected ordering of the model
        Specified by:
        setParams in interface Model
        Overrides:
        setParams in class AbstractLayer<SubsamplingLayer>
        Parameters:
        params - the parameters for the model

      • 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<SubsamplingLayer>
        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.