Modifier and Type | Method and Description |
---|---|
static RNNFormat |
RNNFormat.valueOf(String name)
Returns the enum constant of this type with the specified name.
|
static RNNFormat[] |
RNNFormat.values()
Returns an array containing the constants of this enum type, in
the order they are declared.
|
Modifier and Type | Method and Description |
---|---|
static InputType |
InputType.recurrent(long size,
long timeSeriesLength,
RNNFormat format) |
static InputType |
InputType.recurrent(long size,
RNNFormat format) |
Constructor and Description |
---|
InputTypeRecurrent(long size,
long timeSeriesLength,
RNNFormat format) |
InputTypeRecurrent(long size,
RNNFormat format) |
Modifier and Type | Field and Description |
---|---|
protected RNNFormat |
BaseRecurrentLayer.rnnDataFormat |
protected RNNFormat |
BaseRecurrentLayer.Builder.rnnDataFormat
Set the format of data expected by the RNN.
|
Modifier and Type | Method and Description |
---|---|
RnnLossLayer.Builder |
RnnLossLayer.Builder.dataFormat(RNNFormat rnnDataFormat) |
RnnOutputLayer.Builder |
RnnOutputLayer.Builder.dataFormat(RNNFormat rnnDataFormat) |
T |
BaseRecurrentLayer.Builder.dataFormat(RNNFormat rnnDataFormat) |
static InputPreProcessor |
InputTypeUtil.getPreprocessorForInputTypeRnnLayers(InputType inputType,
RNNFormat rnnDataFormat,
String layerName) |
EmbeddingSequenceLayer.Builder |
EmbeddingSequenceLayer.Builder.outputDataFormat(RNNFormat format) |
Convolution1DLayer.Builder |
Convolution1DLayer.Builder.rnnDataFormat(RNNFormat rnnDataFormat) |
Modifier and Type | Method and Description |
---|---|
RNNFormat |
RepeatVector.Builder.getDataFormat() |
Modifier and Type | Method and Description |
---|---|
RepeatVector.Builder |
RepeatVector.Builder.dataFormat(RNNFormat dataFormat) |
Modifier and Type | Method and Description |
---|---|
RNNFormat |
Bidirectional.getRNNDataFormat() |
Constructor and Description |
---|
TimeDistributed(@NonNull Layer underlying,
RNNFormat rnnDataFormat) |
Constructor and Description |
---|
CnnToRnnPreProcessor(long inputHeight,
long inputWidth,
long numChannels,
RNNFormat rnnDataFormat) |
FeedForwardToRnnPreProcessor(RNNFormat rnnDataFormat) |
RnnToCnnPreProcessor(int inputHeight,
int inputWidth,
int numChannels,
RNNFormat rnnDataFormat) |
RnnToFeedForwardPreProcessor(RNNFormat rnnDataFormat) |
Modifier and Type | Method and Description |
---|---|
RNNFormat |
RepeatVector.getDataFormat() |
Modifier and Type | Method and Description |
---|---|
RNNFormat |
BaseRecurrentLayer.getDataFormat() |
Constructor and Description |
---|
TimeDistributedLayer(Layer underlying,
RNNFormat rnnDataFormat) |
Modifier and Type | Method and Description |
---|---|
static RNNFormat |
TimeSeriesUtils.getFormatFromRnnLayer(Layer layer)
Get the
RNNFormat from the RNN layer, accounting for the presence of wrapper layers like Bidirectional,
LastTimeStep, etc |
static RNNFormat |
Convolution1DUtils.getRnnFormatFromLayer(Layer layer)
Get the
RNNFormat for the given layer. |
Modifier and Type | Method and Description |
---|---|
static INDArray |
Convolution1DUtils.reshapeWeightArrayOrGradientForFormat(INDArray w,
RNNFormat rnnFormat)
Reshapes the given weight
array or weight gradient
to work with the specified
RNNFormat |
static INDArray |
TimeSeriesUtils.reverseTimeSeries(INDArray in,
LayerWorkspaceMgr workspaceMgr,
ArrayType arrayType,
RNNFormat dataFormat) |
Copyright © 2022. All rights reserved.