Retrieves CudnnRNN params in canonical form. It supports the projection in LSTM.
Retrieves a set of weights from the opaque params buffer that can be saved and restored in a way compatible with future runs.
Note that the params buffer may not be compatible across different GPUs. So any save and restoration should be converted to and from the canonical weights and biases.
num_layers: Specifies the number of layers in the RNN model. num_units: Specifies the size of the hidden state. input_size: Specifies the size of the input state. num_params_weights: number of weight parameter matrix for all layers. num_params_biases: number of bias parameter vector for all layers. weights: the canonical form of weights that can be used for saving and restoration. They are more likely to be compatible across different generations. biases: the canonical form of biases that can be used for saving and restoration. They are more likely to be compatible across different generations. rnn_mode: Indicates the type of the RNN model. input_mode: Indicate whether there is a linear projection between the input and The actual computation before the first layer. 'skip_input' is only allowed when input_size == num_units; 'auto_select' implies 'skip_input' when input_size == num_units; otherwise, it implies 'linear_input'. direction: Indicates whether a bidirectional model will be used. dir = (direction == bidirectional) ? 2 : 1 dropout: dropout probability. When set to 0., dropout is disabled. seed: the 1st part of a seed to initialize dropout. seed2: the 2nd part of a seed to initialize dropout. num_proj: The output dimensionality for the projection matrices. If None or 0, no projection is performed.
Nested Classes
class | CudnnRNNParamsToCanonical.Options | Optional attributes for CudnnRNNParamsToCanonical
|
Constants
String | OP_NAME | The name of this op, as known by TensorFlow core engine |
Public Methods
List<Output<T>> |
biases()
|
static <T extends TNumber> CudnnRNNParamsToCanonical<T> | |
static CudnnRNNParamsToCanonical.Options |
direction(String direction)
|
static CudnnRNNParamsToCanonical.Options |
dropout(Float dropout)
|
static CudnnRNNParamsToCanonical.Options |
inputMode(String inputMode)
|
static CudnnRNNParamsToCanonical.Options |
numProj(Long numProj)
|
static CudnnRNNParamsToCanonical.Options |
rnnMode(String rnnMode)
|
static CudnnRNNParamsToCanonical.Options |
seed(Long seed)
|
static CudnnRNNParamsToCanonical.Options |
seed2(Long seed2)
|
List<Output<T>> |
weights()
|
Inherited Methods
Constants
public static final String OP_NAME
The name of this op, as known by TensorFlow core engine
Public Methods
public static CudnnRNNParamsToCanonical<T> create (Scope scope, Operand<TInt32> numLayers, Operand<TInt32> numUnits, Operand<TInt32> inputSize, Operand<T> params, Long numParamsWeights, Long numParamsBiases, Options... options)
Factory method to create a class wrapping a new CudnnRNNParamsToCanonical operation.
Parameters
scope | current scope |
---|---|
options | carries optional attributes values |
Returns
- a new instance of CudnnRNNParamsToCanonical