LostTech.TensorFlow : API Documentation

Type RNNCellDropoutWrapper

Namespace tensorflow.nn

Parent DropoutWrapperBase

Interfaces IRNNCellDropoutWrapper

Methods

Properties

Public instance methods

Tensor call(IGraphNodeBase inputs, IEnumerable<IGraphNodeBase> state, IDictionary<string, object> kwargs)

Tensor call(IGraphNodeBase inputs, PythonClassContainer state, IDictionary<string, object> kwargs)

Tensor call(IGraphNodeBase inputs, object state, IDictionary<string, object> kwargs)

Tensor call(IEnumerable<IGraphNodeBase> inputs, object state, IDictionary<string, object> kwargs)

Tensor call(IEnumerable<IGraphNodeBase> inputs, PythonClassContainer state, IDictionary<string, object> kwargs)

Tensor call(IEnumerable<IGraphNodeBase> inputs, IEnumerable<IGraphNodeBase> state, IDictionary<string, object> kwargs)

object call_dyn(object inputs, object state, IDictionary<string, object> kwargs)

object get_initial_state(IGraphNodeBase inputs, IGraphNodeBase batch_size, PythonClassContainer dtype)

object get_initial_state(IGraphNodeBase inputs, IGraphNodeBase batch_size, DType dtype)

object get_initial_state(IGraphNodeBase inputs, int batch_size, PythonClassContainer dtype)

object get_initial_state(IGraphNodeBase inputs, int batch_size, DType dtype)

object get_initial_state(IGraphNodeBase inputs, TensorShape batch_size, DType dtype)

object get_initial_state(IGraphNodeBase inputs, Dimension batch_size, PythonClassContainer dtype)

object get_initial_state(IGraphNodeBase inputs, TensorShape batch_size, PythonClassContainer dtype)

object get_initial_state(IEnumerable<object> inputs, IGraphNodeBase batch_size, PythonClassContainer dtype)

object get_initial_state(IEnumerable<object> inputs, Dimension batch_size, DType dtype)

object get_initial_state(IEnumerable<object> inputs, IGraphNodeBase batch_size, DType dtype)

object get_initial_state(IEnumerable<object> inputs, int batch_size, PythonClassContainer dtype)

object get_initial_state(IEnumerable<object> inputs, int batch_size, DType dtype)

object get_initial_state(IEnumerable<object> inputs, TensorShape batch_size, PythonClassContainer dtype)

object get_initial_state(IEnumerable<object> inputs, TensorShape batch_size, DType dtype)

object get_initial_state(IEnumerable<object> inputs, Dimension batch_size, PythonClassContainer dtype)

object get_initial_state(IGraphNodeBase inputs, Dimension batch_size, DType dtype)

object get_initial_state_dyn(object inputs, object batch_size, object dtype)

object zero_state(Dimension batch_size, DType dtype)

Return zero-filled state tensor(s).
Parameters
Dimension batch_size
int, float, or unit Tensor representing the batch size.
DType dtype
the data type to use for the state.
Returns
object
If `state_size` is an int or TensorShape, then the return value is a `N-D` tensor of shape `[batch_size, state_size]` filled with zeros.

If `state_size` is a nested list or tuple, then the return value is a nested list or tuple (of the same structure) of `2-D` tensors with the shapes `[batch_size, s]` for each s in `state_size`.

object zero_state(Dimension batch_size, PythonClassContainer dtype)

Return zero-filled state tensor(s).
Parameters
Dimension batch_size
int, float, or unit Tensor representing the batch size.
PythonClassContainer dtype
the data type to use for the state.
Returns
object
If `state_size` is an int or TensorShape, then the return value is a `N-D` tensor of shape `[batch_size, state_size]` filled with zeros.

If `state_size` is a nested list or tuple, then the return value is a nested list or tuple (of the same structure) of `2-D` tensors with the shapes `[batch_size, s]` for each s in `state_size`.

object zero_state(TensorShape batch_size, DType dtype)

Return zero-filled state tensor(s).
Parameters
TensorShape batch_size
int, float, or unit Tensor representing the batch size.
DType dtype
the data type to use for the state.
Returns
object
If `state_size` is an int or TensorShape, then the return value is a `N-D` tensor of shape `[batch_size, state_size]` filled with zeros.

If `state_size` is a nested list or tuple, then the return value is a nested list or tuple (of the same structure) of `2-D` tensors with the shapes `[batch_size, s]` for each s in `state_size`.

object zero_state(TensorShape batch_size, PythonClassContainer dtype)

Return zero-filled state tensor(s).
Parameters
TensorShape batch_size
int, float, or unit Tensor representing the batch size.
PythonClassContainer dtype
the data type to use for the state.
Returns
object
If `state_size` is an int or TensorShape, then the return value is a `N-D` tensor of shape `[batch_size, state_size]` filled with zeros.

If `state_size` is a nested list or tuple, then the return value is a nested list or tuple (of the same structure) of `2-D` tensors with the shapes `[batch_size, s]` for each s in `state_size`.

object zero_state(int batch_size, DType dtype)

Return zero-filled state tensor(s).
Parameters
int batch_size
int, float, or unit Tensor representing the batch size.
DType dtype
the data type to use for the state.
Returns
object
If `state_size` is an int or TensorShape, then the return value is a `N-D` tensor of shape `[batch_size, state_size]` filled with zeros.

If `state_size` is a nested list or tuple, then the return value is a nested list or tuple (of the same structure) of `2-D` tensors with the shapes `[batch_size, s]` for each s in `state_size`.

object zero_state(int batch_size, PythonClassContainer dtype)

Return zero-filled state tensor(s).
Parameters
int batch_size
int, float, or unit Tensor representing the batch size.
PythonClassContainer dtype
the data type to use for the state.
Returns
object
If `state_size` is an int or TensorShape, then the return value is a `N-D` tensor of shape `[batch_size, state_size]` filled with zeros.

If `state_size` is a nested list or tuple, then the return value is a nested list or tuple (of the same structure) of `2-D` tensors with the shapes `[batch_size, s]` for each s in `state_size`.

object zero_state_dyn(object batch_size, object dtype)

Return zero-filled state tensor(s).
Parameters
object batch_size
int, float, or unit Tensor representing the batch size.
object dtype
the data type to use for the state.
Returns
object
If `state_size` is an int or TensorShape, then the return value is a `N-D` tensor of shape `[batch_size, state_size]` filled with zeros.

If `state_size` is a nested list or tuple, then the return value is a nested list or tuple (of the same structure) of `2-D` tensors with the shapes `[batch_size, s]` for each s in `state_size`.

Public properties

PythonFunctionContainer activity_regularizer get; set;

Optional regularizer function for the output of this layer.

object activity_regularizer_dyn get; set;

Optional regularizer function for the output of this layer.

bool built get; set;

object cell get; set;

object dtype get;

object dtype_dyn get;

bool dynamic get;

object dynamic_dyn get;

IList<Node> inbound_nodes get;

object inbound_nodes_dyn get;

IList<object> input get;

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.

object input_dyn get;

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.

object input_mask get;

Retrieves the input mask tensor(s) of a layer.

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

object input_mask_dyn get;

Retrieves the input mask tensor(s) of a layer.

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

IList<object> input_shape get;

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.

object input_shape_dyn get;

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.

object input_spec get; set;

object input_spec_dyn get; set;

IList<object> losses get;

Losses which are associated with this `Layer`.

Variable regularization tensors are created when this property is accessed, so it is eager safe: accessing `losses` under a tf.GradientTape will propagate gradients back to the corresponding variables.

object losses_dyn get;

Losses which are associated with this `Layer`.

Variable regularization tensors are created when this property is accessed, so it is eager safe: accessing `losses` under a tf.GradientTape will propagate gradients back to the corresponding variables.

IList<object> metrics get;

object metrics_dyn get;

object name get;

Returns the name of this module as passed or determined in the ctor.

NOTE: This is not the same as the `self.name_scope.name` which includes parent module names.

object name_dyn get;

Returns the name of this module as passed or determined in the ctor.

NOTE: This is not the same as the `self.name_scope.name` which includes parent module names.

object name_scope get;

Returns a tf.name_scope instance for this class.

object name_scope_dyn get;

Returns a tf.name_scope instance for this class.

IList<object> non_trainable_variables get;

object non_trainable_variables_dyn get;

IList<object> non_trainable_weights get;

object non_trainable_weights_dyn get;

IList<object> outbound_nodes get;

object outbound_nodes_dyn get;

IList<object> output get;

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.

object output_dyn get;

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.

object output_mask get;

Retrieves the output mask tensor(s) of a layer.

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

object output_mask_dyn get;

Retrieves the output mask tensor(s) of a layer.

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

object output_shape get;

Retrieves the output shape(s) of a layer.

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

object output_shape_dyn get;

Retrieves the output shape(s) of a layer.

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

object output_size get;

object output_size_dyn get;

object PythonObject get;

object state_size get;

object state_size_dyn get;

bool stateful get; set;

ValueTuple<object> submodules get;

Sequence of all sub-modules.

Submodules are modules which are properties of this module, or found as properties of modules which are properties of this module (and so on).

``` a = tf.Module() b = tf.Module() c = tf.Module() a.b = b b.c = c assert list(a.submodules) == [b, c] assert list(b.submodules) == [c] assert list(c.submodules) == [] ```

object submodules_dyn get;

Sequence of all sub-modules.

Submodules are modules which are properties of this module, or found as properties of modules which are properties of this module (and so on).

``` a = tf.Module() b = tf.Module() c = tf.Module() a.b = b b.c = c assert list(a.submodules) == [b, c] assert list(b.submodules) == [c] assert list(c.submodules) == [] ```

bool supports_masking get; set;

bool trainable get; set;

object trainable_dyn get; set;

object trainable_variables get;

Sequence of variables owned by this module and it's submodules.

Note: this method uses reflection to find variables on the current instance and submodules. For performance reasons you may wish to cache the result of calling this method if you don't expect the return value to change.

object trainable_variables_dyn get;

Sequence of variables owned by this module and it's submodules.

Note: this method uses reflection to find variables on the current instance and submodules. For performance reasons you may wish to cache the result of calling this method if you don't expect the return value to change.

IList<object> trainable_weights get;

object trainable_weights_dyn get;

IList<object> updates get;

object updates_dyn get;

object variables get;

Returns the list of all layer variables/weights.

Alias of `self.weights`.

object variables_dyn get;

Returns the list of all layer variables/weights.

Alias of `self.weights`.

IList<object> weights get;

Returns the list of all layer variables/weights.

object weights_dyn get;

Returns the list of all layer variables/weights.

object wrapped_cell get;

object wrapped_cell_dyn get;