Uses of Interface
org.deeplearning4j.nn.layers.recurrent.LSTMHelper
-
Packages that use LSTMHelper Package Description org.deeplearning4j.nn.layers.recurrent -
-
Uses of LSTMHelper in org.deeplearning4j.nn.layers.recurrent
Fields in org.deeplearning4j.nn.layers.recurrent declared as LSTMHelper Modifier and Type Field Description protected LSTMHelper
LSTM. helper
Methods in org.deeplearning4j.nn.layers.recurrent with parameters of type LSTMHelper Modifier and Type Method Description static FwdPassReturn
LSTMHelpers. activateHelper(BaseRecurrentLayer layer, NeuralNetConfiguration conf, IActivation gateActivationFn, INDArray input, INDArray recurrentWeights, INDArray originalInputWeights, INDArray biases, boolean training, INDArray originalPrevOutputActivations, INDArray originalPrevMemCellState, boolean forBackprop, boolean forwards, String inputWeightKey, INDArray maskArray, boolean hasPeepholeConnections, LSTMHelper helper, CacheMode cacheMode, LayerWorkspaceMgr workspaceMgr, boolean isHelperAllowFallback)
Returns FwdPassReturn object with activations/INDArrays.static Pair<Gradient,INDArray>
LSTMHelpers. backpropGradientHelper(BaseRecurrentLayer layer, NeuralNetConfiguration conf, IActivation gateActivationFn, INDArray input, INDArray recurrentWeights, INDArray inputWeights, INDArray epsilon, boolean truncatedBPTT, int tbpttBackwardLength, FwdPassReturn fwdPass, boolean forwards, String inputWeightKey, String recurrentWeightKey, String biasWeightKey, Map<String,INDArray> gradientViews, INDArray maskArray, boolean hasPeepholeConnections, LSTMHelper helper, LayerWorkspaceMgr workspaceMgr, boolean isHelperAllowFallback)
-