Package org.nd4j.autodiff.samediff.ops

Class SDRNN

  • public class SDRNN
extends SDOps

    • Constructor Detail

      • SDRNN

        public SDRNN​(SameDiff sameDiff)

    • Method Detail

      • gru

        public SDVariable gru​(SDVariable x,
                      SDVariable hLast,
                      SDVariable Wx,
                      SDVariable Wh,
                      SDVariable biases)
        The GRU operation. Gated Recurrent Unit - Cho et al. 2014.
        Parameters:
        x - input [time, bS, nIn] (NUMERIC type)
        hLast - initial cell output (at time step = 0) [bS, nOut] (NUMERIC type)
        Wx - input-to-hidden weights, [nIn, 3*nOut] (NUMERIC type)
        Wh - hidden-to-hidden weights, [nOut, 3*nOut] (NUMERIC type)
        biases - biases, [3*nOut] (NUMERIC type)
        Returns:
        h cell outputs [time, bS, nOut], that is per each time step (NUMERIC type)

      • gru

        public SDVariable gru​(String name,
                      SDVariable x,
                      SDVariable hLast,
                      SDVariable Wx,
                      SDVariable Wh,
                      SDVariable biases)
        The GRU operation. Gated Recurrent Unit - Cho et al. 2014.
        Parameters:
        name - name May be null. Name for the output variable
        x - input [time, bS, nIn] (NUMERIC type)
        hLast - initial cell output (at time step = 0) [bS, nOut] (NUMERIC type)
        Wx - input-to-hidden weights, [nIn, 3*nOut] (NUMERIC type)
        Wh - hidden-to-hidden weights, [nOut, 3*nOut] (NUMERIC type)
        biases - biases, [3*nOut] (NUMERIC type)
        Returns:
        h cell outputs [time, bS, nOut], that is per each time step (NUMERIC type)

      • gruCell

        public SDVariable[] gruCell​(SDVariable x,
                            SDVariable hLast,
                            GRUWeights GRUWeights)
        The GRU cell. Does a single time step operation
        Parameters:
        x - Input, with shape [batchSize, inSize] (NUMERIC type)
        hLast - Output of the previous cell/time step, with shape [batchSize, numUnits] (NUMERIC type)
        GRUWeights - Configuration Object

      • gruCell

        public SDVariable[] gruCell​(String[] names,
                            SDVariable x,
                            SDVariable hLast,
                            GRUWeights GRUWeights)
        The GRU cell. Does a single time step operation
        Parameters:
        names - names May be null. Arrays of names for the output variables.
        x - Input, with shape [batchSize, inSize] (NUMERIC type)
        hLast - Output of the previous cell/time step, with shape [batchSize, numUnits] (NUMERIC type)
        GRUWeights - Configuration Object

      • lstmCell

        public SDVariable[] lstmCell​(SDVariable x,
                             SDVariable cLast,
                             SDVariable yLast,
                             LSTMWeights LSTMWeights,
                             LSTMConfiguration LSTMConfiguration)
        The LSTM cell. Does a single time step operation.
        Parameters:
        x - Input, with shape [batchSize, inSize] (NUMERIC type)
        cLast - Previous cell state, with shape [batchSize, numUnits] (NUMERIC type)
        yLast - revious cell output, with shape [batchSize, numUnits] (NUMERIC type)
        LSTMWeights - Configuration Object
        LSTMConfiguration - Configuration Object

      • lstmCell

        public SDVariable[] lstmCell​(String[] names,
                             SDVariable x,
                             SDVariable cLast,
                             SDVariable yLast,
                             LSTMWeights LSTMWeights,
                             LSTMConfiguration LSTMConfiguration)
        The LSTM cell. Does a single time step operation.
        Parameters:
        names - names May be null. Arrays of names for the output variables.
        x - Input, with shape [batchSize, inSize] (NUMERIC type)
        cLast - Previous cell state, with shape [batchSize, numUnits] (NUMERIC type)
        yLast - revious cell output, with shape [batchSize, numUnits] (NUMERIC type)
        LSTMWeights - Configuration Object
        LSTMConfiguration - Configuration Object

      • lstmLayer

        public SDVariable[] lstmLayer​(SDVariable x,
                              SDVariable cLast,
                              SDVariable yLast,
                              SDVariable maxTSLength,
                              LSTMLayerWeights LSTMLayerWeights,
                              LSTMLayerConfig LSTMLayerConfig)
        Long Short-Term Memory layer - Hochreiter 1997.
        SUPPORTS following data formats:
        for unidirectional:
        TNS: shapes [timeLength, numExamples, inOutSize]
        NST: shapes [numExamples, inOutSize, timeLength]
        NTS: shapes [numExamples, timeLength, inOutSize]
        for bidirectional:
        T2NS: shapes [timeLength, 2, numExamples, inOutSize] (for ONNX)
        SUPPORTS following direction modes:
        FWD: forward
        BWD: backward
        BIDIR_SUM: bidirectional sum
        BIDIR_CONCAT: bidirectional concat
        BIDIR_EXTRA_DIM: bidirectional extra output dim (in conjunction with format dataFormat - T2NS)
        You may use different gate configurations:
        specify gate/cell/out aplha/beta and numbers of activations for gate/cell/out described in activations enum
        ("RELU","SIGMOID","AFFINE","LEAKY_RELU","THRESHHOLD_RELU","SCALED_TAHN","HARD_SIGMOID","ELU","SOFTSIGN","SOFTPLUS")
        Also this layer supports MKLDNN (DNNL) and cuDNN acceleration
        Parameters:
        x - Input, with shape dependent on the data format (in config). (NUMERIC type)
        cLast - Previous/initial cell state, with shape [batchSize, numUnits] (NUMERIC type)
        yLast - Previous/initial cell output, with shape [batchSize, numUnits] (NUMERIC type)
        maxTSLength - maxTSLength with shape [batchSize] (NUMERIC type)
        LSTMLayerWeights - Configuration Object
        LSTMLayerConfig - Configuration Object

      • lstmLayer

        public SDVariable[] lstmLayer​(String[] names,
                              SDVariable x,
                              SDVariable cLast,
                              SDVariable yLast,
                              SDVariable maxTSLength,
                              LSTMLayerWeights LSTMLayerWeights,
                              LSTMLayerConfig LSTMLayerConfig)
        Long Short-Term Memory layer - Hochreiter 1997.
        SUPPORTS following data formats:
        for unidirectional:
        TNS: shapes [timeLength, numExamples, inOutSize]
        NST: shapes [numExamples, inOutSize, timeLength]
        NTS: shapes [numExamples, timeLength, inOutSize]
        for bidirectional:
        T2NS: shapes [timeLength, 2, numExamples, inOutSize] (for ONNX)
        SUPPORTS following direction modes:
        FWD: forward
        BWD: backward
        BIDIR_SUM: bidirectional sum
        BIDIR_CONCAT: bidirectional concat
        BIDIR_EXTRA_DIM: bidirectional extra output dim (in conjunction with format dataFormat - T2NS)
        You may use different gate configurations:
        specify gate/cell/out aplha/beta and numbers of activations for gate/cell/out described in activations enum
        ("RELU","SIGMOID","AFFINE","LEAKY_RELU","THRESHHOLD_RELU","SCALED_TAHN","HARD_SIGMOID","ELU","SOFTSIGN","SOFTPLUS")
        Also this layer supports MKLDNN (DNNL) and cuDNN acceleration
        Parameters:
        names - names May be null. Arrays of names for the output variables.
        x - Input, with shape dependent on the data format (in config). (NUMERIC type)
        cLast - Previous/initial cell state, with shape [batchSize, numUnits] (NUMERIC type)
        yLast - Previous/initial cell output, with shape [batchSize, numUnits] (NUMERIC type)
        maxTSLength - maxTSLength with shape [batchSize] (NUMERIC type)
        LSTMLayerWeights - Configuration Object
        LSTMLayerConfig - Configuration Object

      • lstmLayer

        public SDVariable[] lstmLayer​(SDVariable x,
                              LSTMLayerWeights LSTMLayerWeights,
                              LSTMLayerConfig LSTMLayerConfig)
        Long Short-Term Memory layer - Hochreiter 1997.
        SUPPORTS following data formats:
        for unidirectional:
        TNS: shapes [timeLength, numExamples, inOutSize]
        NST: shapes [numExamples, inOutSize, timeLength]
        NTS: shapes [numExamples, timeLength, inOutSize]
        for bidirectional:
        T2NS: shapes [timeLength, 2, numExamples, inOutSize] (for ONNX)
        SUPPORTS following direction modes:
        FWD: forward
        BWD: backward
        BIDIR_SUM: bidirectional sum
        BIDIR_CONCAT: bidirectional concat
        BIDIR_EXTRA_DIM: bidirectional extra output dim (in conjunction with format dataFormat - T2NS)
        You may use different gate configurations:
        specify gate/cell/out aplha/beta and numbers of activations for gate/cell/out described in activations enum
        ("RELU","SIGMOID","AFFINE","LEAKY_RELU","THRESHHOLD_RELU","SCALED_TAHN","HARD_SIGMOID","ELU","SOFTSIGN","SOFTPLUS")
        Also this layer supports MKLDNN (DNNL) and cuDNN acceleration
        Parameters:
        x - Input, with shape dependent on the data format (in config). (NUMERIC type)
        LSTMLayerWeights - Configuration Object
        LSTMLayerConfig - Configuration Object

      • lstmLayer

        public SDVariable[] lstmLayer​(String[] names,
                              SDVariable x,
                              LSTMLayerWeights LSTMLayerWeights,
                              LSTMLayerConfig LSTMLayerConfig)
        Long Short-Term Memory layer - Hochreiter 1997.
        SUPPORTS following data formats:
        for unidirectional:
        TNS: shapes [timeLength, numExamples, inOutSize]
        NST: shapes [numExamples, inOutSize, timeLength]
        NTS: shapes [numExamples, timeLength, inOutSize]
        for bidirectional:
        T2NS: shapes [timeLength, 2, numExamples, inOutSize] (for ONNX)
        SUPPORTS following direction modes:
        FWD: forward
        BWD: backward
        BIDIR_SUM: bidirectional sum
        BIDIR_CONCAT: bidirectional concat
        BIDIR_EXTRA_DIM: bidirectional extra output dim (in conjunction with format dataFormat - T2NS)
        You may use different gate configurations:
        specify gate/cell/out aplha/beta and numbers of activations for gate/cell/out described in activations enum
        ("RELU","SIGMOID","AFFINE","LEAKY_RELU","THRESHHOLD_RELU","SCALED_TAHN","HARD_SIGMOID","ELU","SOFTSIGN","SOFTPLUS")
        Also this layer supports MKLDNN (DNNL) and cuDNN acceleration
        Parameters:
        names - names May be null. Arrays of names for the output variables.
        x - Input, with shape dependent on the data format (in config). (NUMERIC type)
        LSTMLayerWeights - Configuration Object
        LSTMLayerConfig - Configuration Object

      • lstmblock

        public SDVariable lstmblock​(SDVariable maxTSLength,
                            SDVariable x,
                            SDVariable cLast,
                            SDVariable yLast,
                            LSTMWeights LSTMWeights,
                            LSTMConfiguration LSTMConfiguration)
        The LSTM block
        Parameters:
        maxTSLength - (NUMERIC type)
        x - Input, with shape dependent on the data format (in config). (NUMERIC type)
        cLast - Previous/initial cell state, with shape [batchSize, numUnits] (NUMERIC type)
        yLast - Previous/initial cell output, with shape [batchSize, numUnits] (NUMERIC type)
        LSTMWeights - Configuration Object
        LSTMConfiguration - Configuration Object
        Returns:
        output The layer's outputs. (NUMERIC type)

      • lstmblock

        public SDVariable lstmblock​(String name,
                            SDVariable maxTSLength,
                            SDVariable x,
                            SDVariable cLast,
                            SDVariable yLast,
                            LSTMWeights LSTMWeights,
                            LSTMConfiguration LSTMConfiguration)
        The LSTM block
        Parameters:
        name - name May be null. Name for the output variable
        maxTSLength - (NUMERIC type)
        x - Input, with shape dependent on the data format (in config). (NUMERIC type)
        cLast - Previous/initial cell state, with shape [batchSize, numUnits] (NUMERIC type)
        yLast - Previous/initial cell output, with shape [batchSize, numUnits] (NUMERIC type)
        LSTMWeights - Configuration Object
        LSTMConfiguration - Configuration Object
        Returns:
        output The layer's outputs. (NUMERIC type)

      • lstmblock

        public SDVariable lstmblock​(SDVariable x,
                            LSTMWeights LSTMWeights,
                            LSTMConfiguration LSTMConfiguration)
        The LSTM block
        Parameters:
        x - Input, with shape dependent on the data format (in config). (NUMERIC type)
        LSTMWeights - Configuration Object
        LSTMConfiguration - Configuration Object
        Returns:
        output The layer's outputs. (NUMERIC type)

      • lstmblock

        public SDVariable lstmblock​(String name,
                            SDVariable x,
                            LSTMWeights LSTMWeights,
                            LSTMConfiguration LSTMConfiguration)
        The LSTM block
        Parameters:
        name - name May be null. Name for the output variable
        x - Input, with shape dependent on the data format (in config). (NUMERIC type)
        LSTMWeights - Configuration Object
        LSTMConfiguration - Configuration Object
        Returns:
        output The layer's outputs. (NUMERIC type)

      • sru

        public SDVariable sru​(SDVariable x,
                      SDVariable initialC,
                      SDVariable mask,
                      SRUWeights SRUWeights)
        The SRU layer. Does a single time step operation.
        Parameters:
        x - Input, with shape [batchSize, inSize] (NUMERIC type)
        initialC - Initial cell state, with shape [batchSize, inSize] (NUMERIC type)
        mask - An optional dropout mask, with shape [batchSize, inSize] (NUMERIC type)
        SRUWeights - Configuration Object
        Returns:
        output The cell's outputs.. (NUMERIC type)

      • sru

        public SDVariable sru​(String name,
                      SDVariable x,
                      SDVariable initialC,
                      SDVariable mask,
                      SRUWeights SRUWeights)
        The SRU layer. Does a single time step operation.
        Parameters:
        name - name May be null. Name for the output variable
        x - Input, with shape [batchSize, inSize] (NUMERIC type)
        initialC - Initial cell state, with shape [batchSize, inSize] (NUMERIC type)
        mask - An optional dropout mask, with shape [batchSize, inSize] (NUMERIC type)
        SRUWeights - Configuration Object
        Returns:
        output The cell's outputs.. (NUMERIC type)

      • sru

        public SDVariable sru​(SDVariable x,
                      SDVariable initialC,
                      SRUWeights SRUWeights)
        The SRU layer. Does a single time step operation.
        Parameters:
        x - Input, with shape [batchSize, inSize] (NUMERIC type)
        initialC - Initial cell state, with shape [batchSize, inSize] (NUMERIC type)
        SRUWeights - Configuration Object
        Returns:
        output The cell's outputs.. (NUMERIC type)

      • sru

        public SDVariable sru​(String name,
                      SDVariable x,
                      SDVariable initialC,
                      SRUWeights SRUWeights)
        The SRU layer. Does a single time step operation.
        Parameters:
        name - name May be null. Name for the output variable
        x - Input, with shape [batchSize, inSize] (NUMERIC type)
        initialC - Initial cell state, with shape [batchSize, inSize] (NUMERIC type)
        SRUWeights - Configuration Object
        Returns:
        output The cell's outputs.. (NUMERIC type)

      • sruCell

        public SDVariable sruCell​(SDVariable x,
                          SDVariable cLast,
                          SRUWeights SRUWeights)
        The SRU layer. Does a single time step operation.
        Parameters:
        x - Input, with shape [batchSize, inSize] (NUMERIC type)
        cLast - Previous cell state, with shape [batchSize, inSize] (NUMERIC type)
        SRUWeights - Configuration Object
        Returns:
        output The cell's outputs. (NUMERIC type)

      • sruCell

        public SDVariable sruCell​(String name,
                          SDVariable x,
                          SDVariable cLast,
                          SRUWeights SRUWeights)
        The SRU layer. Does a single time step operation.
        Parameters:
        name - name May be null. Name for the output variable
        x - Input, with shape [batchSize, inSize] (NUMERIC type)
        cLast - Previous cell state, with shape [batchSize, inSize] (NUMERIC type)
        SRUWeights - Configuration Object
        Returns:
        output The cell's outputs. (NUMERIC type)