Uses of Class
org.nd4j.linalg.api.ops.impl.layers.recurrent.config.LSTMLayerConfig

Packages that use LSTMLayerConfig

Package	Description
org.nd4j.autodiff.samediff.ops
org.nd4j.linalg.api.ops.impl.layers.recurrent
org.nd4j.linalg.api.ops.impl.layers.recurrent.outputs
org.nd4j.linalg.factory.ops

Uses of LSTMLayerConfig in org.nd4j.autodiff.samediff.ops

Methods in org.nd4j.autodiff.samediff.ops with parameters of type LSTMLayerConfig

Modifier and Type	Method and Description
SDVariable[]	SDRNN.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
SDVariable[]	SDRNN.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
SDVariable[]	SDRNN.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
SDVariable[]	SDRNN.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

Uses of LSTMLayerConfig in org.nd4j.linalg.api.ops.impl.layers.recurrent

Constructors in org.nd4j.linalg.api.ops.impl.layers.recurrent with parameters of type LSTMLayerConfig

Constructor and Description
LSTMLayer(INDArray x, INDArray cLast, INDArray yLast, INDArray maxTSLength, LSTMLayerWeights lstmWeights, LSTMLayerConfig LSTMLayerConfig)
LSTMLayer(@NonNull SameDiff sameDiff, SDVariable x, SDVariable cLast, SDVariable yLast, SDVariable maxTSLength, LSTMLayerWeights weights, LSTMLayerConfig configuration)
LSTMLayerBp(@NonNull SameDiff sameDiff, @NonNull SDVariable x, SDVariable cLast, SDVariable yLast, SDVariable maxTSLength, @NonNull LSTMLayerWeights weights, @NonNull LSTMLayerConfig configuration, SDVariable dLdh, SDVariable dLdhL, SDVariable dLdcL)

Uses of LSTMLayerConfig in org.nd4j.linalg.api.ops.impl.layers.recurrent.outputs

Constructors in org.nd4j.linalg.api.ops.impl.layers.recurrent.outputs with parameters of type LSTMLayerConfig

Constructor and Description
LSTMLayerOutputs(SDVariable[] outputs, LSTMLayerConfig lstmLayerConfig)

Uses of LSTMLayerConfig in org.nd4j.linalg.factory.ops

Methods in org.nd4j.linalg.factory.ops with parameters of type LSTMLayerConfig

Modifier and Type	Method and Description
INDArray[]	NDRNN.lstmLayer(INDArray x, INDArray cLast, INDArray yLast, INDArray 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
INDArray[]	NDRNN.lstmLayer(INDArray 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