tf.contrib.cudnn_rnn.CudnnRNNRelu

Class CudnnRNNRelu

Defined in tensorflow/contrib/cudnn_rnn/python/layers/cudnn_rnn.py.

Cudnn implementation of the RNN-relu layer.

Properties

activity_regularizer

Optional regularizer function for the output of this layer.

canonical_bias_shapes

Shapes of Cudnn canonical bias tensors.

canonical_weight_shapes

Shapes of Cudnn canonical weight tensors.

direction

Returns unidirectional or bidirectional.

dtype

graph

input

Retrieves the input tensor(s) of a layer.

Only applicable if the layer has exactly one input, i.e. if it is connected to one incoming layer.

Returns:

Input tensor or list of input tensors.

Raises:

• AttributeError: if the layer is connected to more than one incoming layers.

Raises:

• RuntimeError: If called in Eager mode.
• AttributeError: If no inbound nodes are found.

input_mode

Input mode of first layer.

Indicates whether there is a linear projection between the input and the actual computation before the first layer. It can be 'linear_input': (default) always applies a linear projection of input onto RNN hidden state. (standard RNN behavior) 'skip_input': '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'.

Returns:

'linear_input', 'skip_input' or 'auto_select'.

input_shape

Retrieves the input shape(s) of a layer.

Only applicable if the layer has exactly one input, i.e. if it is connected to one incoming layer, or if all inputs have the same shape.

Returns:

Input shape, as an integer shape tuple (or list of shape tuples, one tuple per input tensor).

Raises:

• AttributeError: if the layer has no defined input_shape.
• RuntimeError: if called in Eager mode.

input_size

losses

Losses which are associated with this Layer.

Note that when executing eagerly, getting this property evaluates regularizers. When using graph execution, variable regularization ops have already been created and are simply returned here.

Returns:

A list of tensors.

name

non_trainable_variables

non_trainable_weights

num_dirs

num_layers

num_units

output

Retrieves the output tensor(s) of a layer.

Only applicable if the layer has exactly one output, i.e. if it is connected to one incoming layer.

Returns:

Output tensor or list of output tensors.

Raises:

• AttributeError: if the layer is connected to more than one incoming layers.
• RuntimeError: if called in Eager mode.

output_shape

Retrieves the output shape(s) of a layer.

Only applicable if the layer has one output, or if all outputs have the same shape.

Returns:

Output shape, as an integer shape tuple (or list of shape tuples, one tuple per output tensor).

Raises:

• AttributeError: if the layer has no defined output shape.
• RuntimeError: if called in Eager mode.

rnn_mode

Type of RNN cell used.

Returns:

lstm, gru, rnn_relu or rnn_tanh.

saveable

scope_name

trainable_variables

trainable_weights

updates

variables

Returns the list of all layer variables/weights.

Returns:

A list of variables.

weights

Returns the list of all layer variables/weights.

Returns:

A list of variables.

Methods

__init__

__init__(
    num_layers,
    num_units,
    input_mode=CUDNN_INPUT_LINEAR_MODE,
    direction=CUDNN_RNN_UNIDIRECTION,
    dropout=0.0,
    seed=None,
    dtype=tf.float32,
    kernel_initializer=None,
    bias_initializer=None,
    name=None
)

Creates a CudnnRNN model from model spec.

Args:

• num_layers: the number of layers for the RNN model.
• num_units: the number of units within the RNN model.
• input_mode: indicate whether there is a linear projection between the input and the actual computation before the first layer. It can be 'linear_input', 'skip_input' or 'auto_select'. 'linear_input' (default) always applies a linear projection of input onto RNN hidden state. (standard RNN behavior). '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: the direction model that the model operates. Can be either 'unidirectional' or 'bidirectional'
• dropout: dropout rate, a number between [0, 1]. Dropout is applied between each layer (no dropout is applied for a model with a single layer). When set to 0, dropout is disabled.
• seed: the op seed used for initializing dropout. See tf.set_random_seed for behavior.
• dtype: tf.float16, tf.float32 or tf.float64
• kernel_initializer: starting value to initialize the weight.
• bias_initializer: starting value to initialize the bias (default is all zeros).
• name: VariableScope for the created subgraph; defaults to class name. This only serves the default scope if later no scope is specified when invoking call().

Raises:

• ValueError: if direction is invalid. Or dtype is not supported.

__call__

__call__(
    inputs,
    *args,
    **kwargs
)

Wraps call, applying pre- and post-processing steps.

Arguments:

• inputs: input tensor(s).
• *args: additional positional arguments to be passed to self.call.
• **kwargs: additional keyword arguments to be passed to self.call. Note: kwarg scope is reserved for use by the layer.

Returns:

Output tensor(s).

Note: - If the layer's call method takes a scope keyword argument, this argument will be automatically set to the current variable scope. - If the layer's call method takes a mask argument (as some Keras layers do), its default value will be set to the mask generated for inputs by the previous layer (if input did come from a layer that generated a corresponding mask, i.e. if it came from a Keras layer with masking support.

Raises:

• ValueError: if the layer's call method returns None (an invalid value).

__deepcopy__

__deepcopy__(memo)

add_loss

add_loss(
    losses,
    inputs=None
)

Add loss tensor(s), potentially dependent on layer inputs.

Some losses (for instance, activity regularization losses) may be dependent on the inputs passed when calling a layer. Hence, when reusing the same layer on different inputs a and b, some entries in layer.losses may be dependent on a and some on b. This method automatically keeps track of dependencies.

The get_losses_for method allows to retrieve the losses relevant to a specific set of inputs.

Note that add_loss is not supported when executing eagerly. Instead, variable regularizers may be added through add_variable. Activity regularization is not supported directly (but such losses may be returned from Layer.call()).

Arguments:

• losses: Loss tensor, or list/tuple of tensors.
• inputs: If anything other than None is passed, it signals the losses are conditional on some of the layer's inputs, and thus they should only be run where these inputs are available. This is the case for activity regularization losses, for instance. If None is passed, the losses are assumed to be unconditional, and will apply across all dataflows of the layer (e.g. weight regularization losses).

Raises:

• RuntimeError: If called in Eager mode.

add_update

add_update(
    updates,
    inputs=None
)

Add update op(s), potentially dependent on layer inputs.

Weight updates (for instance, the updates of the moving mean and variance in a BatchNormalization layer) may be dependent on the inputs passed when calling a layer. Hence, when reusing the same layer on different inputs a and b, some entries in layer.updates may be dependent on a and some on b. This method automatically keeps track of dependencies.

The get_updates_for method allows to retrieve the updates relevant to a specific set of inputs.

This call is ignored in Eager mode.

Arguments:

• updates: Update op, or list/tuple of update ops.
• inputs: If anything other than None is passed, it signals the updates are conditional on some of the layer's inputs, and thus they should only be run where these inputs are available. This is the case for BatchNormalization updates, for instance. If None, the updates will be taken into account unconditionally, and you are responsible for making sure that any dependency they might have is available at runtime. A step counter might fall into this category.

add_variable

add_variable(
    name,
    shape,
    dtype=None,
    initializer=None,
    regularizer=None,
    trainable=True,
    constraint=None,
    partitioner=None
)

Adds a new variable to the layer, or gets an existing one; returns it.

Arguments:

• name: variable name.
• shape: variable shape.
• dtype: The type of the variable. Defaults to self.dtype or float32.
• initializer: initializer instance (callable).
• regularizer: regularizer instance (callable).
• trainable: whether the variable should be part of the layer's "trainable_variables" (e.g. variables, biases) or "non_trainable_variables" (e.g. BatchNorm mean, stddev). Note, if the current variable scope is marked as non-trainable then this parameter is ignored and any added variables are also marked as non-trainable.
• constraint: constraint instance (callable).
• partitioner: (optional) partitioner instance (callable). If provided, when the requested variable is created it will be split into multiple partitions according to partitioner. In this case, an instance of PartitionedVariable is returned. Available partitioners include tf.fixed_size_partitioner and tf.variable_axis_size_partitioner. For more details, see the documentation of tf.get_variable and the "Variable Partitioners and Sharding" section of the API guide.

Returns:

The created variable. Usually either a Variable or ResourceVariable instance. If partitioner is not None, a PartitionedVariable instance is returned.

Raises:

• RuntimeError: If called with partioned variable regularization and eager execution is enabled.

apply

apply(
    inputs,
    *args,
    **kwargs
)

Apply the layer on a input.

This simply wraps self.__call__.

Arguments:

• inputs: Input tensor(s).
• *args: additional positional arguments to be passed to self.call.
• **kwargs: additional keyword arguments to be passed to self.call.

Returns:

Output tensor(s).

build

build(input_shape)

Create variables of the Cudnn RNN.

It can be called manually before __call__() or automatically through __call__(). In the former case, subsequent __call__()s will skip creating variables.

Args:

• input_shape: network input tensor shape, a python list or a TensorShape object with 3 dimensions.

Raises:

• ValueError: if input_shape has wrong dimension or unknown 3rd dimension.

call

call(
    inputs,
    initial_state=None,
    training=True
)

Runs the forward step for the RNN model.

Args:

• inputs: 3-D tensor with shape [time_len, batch_size, input_size].
• initial_state: a tuple of tensor(s) of shape [num_layers * num_dirs, batch_size, num_units]. If not provided, use zero initial states. The tuple size is 2 for LSTM and 1 for other RNNs.
• training: whether this operation will be used in training or inference.

Returns:

• output: a tensor of shape [time_len, batch_size, num_dirs * num_units]. It is a concat([fwd_output, bak_output], axis=2).
• output_states: a tuple of tensor(s) of the same shape and structure as initial_state.

Raises:

• ValueError: initial_state is not a tuple.

compute_output_shape

compute_output_shape(input_shape)

Computes the output shape of the layer given the input shape.

Args:

• input_shape: A (possibly nested tuple of) TensorShape. It need not be fully defined (e.g. the batch size may be unknown).

Returns:

A (possibly nested tuple of) TensorShape.

Raises:

• TypeError: if input_shape is not a (possibly nested tuple of) TensorShape.
• ValueError: if input_shape is incomplete or is incompatible with the the layer.

count_params

count_params()

Count the total number of scalars composing the weights.

Returns:

An integer count.

Raises:

• ValueError: if the layer isn't yet built (in which case its weights aren't yet defined).

get_input_at

get_input_at(node_index)

Retrieves the input tensor(s) of a layer at a given node.

Arguments:

• node_index: Integer, index of the node from which to retrieve the attribute. E.g. node_index=0 will correspond to the first time the layer was called.

Returns:

A tensor (or list of tensors if the layer has multiple inputs).

Raises:

• RuntimeError: If called in Eager mode.

get_input_shape_at

get_input_shape_at(node_index)

Retrieves the input shape(s) of a layer at a given node.

Arguments:

• node_index: Integer, index of the node from which to retrieve the attribute. E.g. node_index=0 will correspond to the first time the layer was called.

Returns:

A shape tuple (or list of shape tuples if the layer has multiple inputs).

Raises:

• RuntimeError: If called in Eager mode.

get_losses_for

get_losses_for(inputs)

Retrieves losses relevant to a specific set of inputs.

Arguments:

• inputs: Input tensor or list/tuple of input tensors.

Returns:

List of loss tensors of the layer that depend on inputs.

Raises:

• RuntimeError: If called in Eager mode.

get_output_at

get_output_at(node_index)

Retrieves the output tensor(s) of a layer at a given node.

Arguments:

• node_index: Integer, index of the node from which to retrieve the attribute. E.g. node_index=0 will correspond to the first time the layer was called.

Returns:

A tensor (or list of tensors if the layer has multiple outputs).

Raises:

• RuntimeError: If called in Eager mode.

get_output_shape_at

get_output_shape_at(node_index)

Retrieves the output shape(s) of a layer at a given node.

Arguments:

• node_index: Integer, index of the node from which to retrieve the attribute. E.g. node_index=0 will correspond to the first time the layer was called.

Returns:

A shape tuple (or list of shape tuples if the layer has multiple outputs).

Raises:

• RuntimeError: If called in Eager mode.

get_updates_for

get_updates_for(inputs)

Retrieves updates relevant to a specific set of inputs.

Arguments:

• inputs: Input tensor or list/tuple of input tensors.

Returns:

List of update ops of the layer that depend on inputs.

Raises:

• RuntimeError: If called in Eager mode.

state_shape

state_shape(batch_size)

Shape of the state of Cudnn RNN cells w/o. input_c.

Shape is a 1-element tuple, [num_layers * num_dirs, batch_size, num_units]

Args:

• batch_size: an int

Returns:

a tuple of python arrays.