Class Network
Inherits From: Layer
Defined in tensorflow/contrib/eager/python/network.py
.
Represents the composition of a set of Layers.
Deprecated. Please inherit from tf.keras.Model
, and see its documentation
for details. tf.keras.Model
should be a drop-in replacement for
tfe.Network
in most cases, but note that track_layer
is no longer
necessary or supported. Instead, Layer
instances are tracked on attribute
assignment (see the section of tf.keras.Model
's documentation on
subclassing). Since the output of track_layer
is often assigned to an
attribute anyway, most code can be ported by simply removing the track_layer
calls.
tf.keras.Model
works with all TensorFlow Layer
instances, including those
from tf.layers
, but switching to the tf.keras.layers
versions along with
the migration to tf.keras.Model
is recommended, since it will preserve
variable names. Feel free to import it with an alias to avoid excess typing
:).
Network
implements the Layer
interface and adds convenience methods for
managing sub-Layer
s, such as listing variables.
Layer
s (including other Network
s) should be added via track_layer
. They
can then be used when overriding the Network.call
method:
class TwoLayerNetwork(tfe.Network):
def __init__(self, name):
super(TwoLayerNetwork, self).__init__(name=name)
self.layer_one = self.track_layer(tf.layers.Dense(16, input_shape=(8,)))
self.layer_two = self.track_layer(tf.layers.Dense(1, input_shape=(16,)))
def call(self, inputs):
return self.layer_two(self.layer_one(inputs))
After constructing an object and calling the Network
, a list of variables
created by tracked Layer
s is available via Network.variables
:
net = TwoLayerNetwork(name="net")
output = net(tf.ones([1, 8]))
print([v.name for v in net.variables])
This example prints variable names, one kernel and one bias per
tf.layers.Dense
layer:
['net/dense/kernel:0',
'net/dense/bias:0',
'net/dense_1/kernel:0',
'net/dense_1/bias:0']
These variables can be passed to a Saver
(tf.train.Saver
, or
tf.contrib.eager.Saver
when executing eagerly) to save or restore the
Network
, typically alongside a global step and tf.train.Optimizer
variables when checkpointing during training.
Note that the semantics of calling a Network
with graph execution (i.e. not
executing eagerly) may change slightly in the future. Currently stateful ops
are pruned from the graph unless they or something that depends on them is
executed in a session, but this behavior is not consistent with eager
execution (where stateful ops are executed eagerly). Layer
s from tf.layers
do not depend on this pruning and so will not be affected, but Network
s
which rely on stateful ops being added to the graph but not executed (e.g. via
custom Layer
s which manage stateful ops) may break with this change.
__init__
__init__(name=None)
Configure the Network
. (deprecated)
tf.keras.Model
works with all TensorFlow Layer
instances, including those from tf.layers
, but switching to the tf.keras.layers
versions along with the migration to tf.keras.Model
is recommended, since it will preserve variable names. Feel free to import it with an alias to avoid excess typing :).
Args:
name
: The name to use for thisNetwork
. If specified, it must be unique in the context where thisNetwork
is first (1) added to anotherNetwork
(in which case it must not share a name with otherLayers
added to thatNetwork
), or (2) built/called (in which case no other 'top-level'Network
s may share this name). If unspecified or None, theNetwork
will be named using its class name, with a number appended if necessary for uniqueness (e.g. MyNetwork -> 'my_network_1').
Raises:
ValueError
: Ifname
is not valid. Note that some naming errors will instead be raised when theNetwork
is called.
Properties
activity_regularizer
Optional regularizer function for the output of this layer.
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_mask
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.
Returns:
Input mask tensor (potentially None) or list of input mask tensors.
Raises:
AttributeError
: if the layer is connected to more than one incoming layers.
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.
layers
losses
Gather losses from Layer
s in the Network
.
Note that when executing eagerly, Layer.losses
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
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_mask
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.
Returns:
Output mask tensor (potentially None) or list of output mask tensors.
Raises:
AttributeError
: if the layer is connected to more than one incoming layers.
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.
scope_name
trainable
trainable_variables
trainable_weights
updates
variables
Returns the list of all layer variables/weights.
Alias of self.weights
.
Returns:
A list of variables.
weights
Returns the list of all layer variables/weights.
Returns:
A list of variables.
Methods
tf.contrib.eager.Network.__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 toself.call
.**kwargs
: additional keyword arguments to be passed toself.call
. Note: kwargscope
is reserved for use by the layer.
Returns:
Output tensor(s).
Raises:
ValueError
: if the layer'scall
method returns None (an invalid value).
tf.contrib.eager.Network.__deepcopy__
__deepcopy__(memo)
tf.contrib.eager.Network.__setattr__
__setattr__(
name,
value
)
Implement setattr(self, name, value).
tf.contrib.eager.Network.apply
apply(
inputs,
*args,
**kwargs
)
Apply the layer on a input.
This is an alias of self.__call__
.
Arguments:
inputs
: Input tensor(s).*args
: additional positional arguments to be passed toself.call
.**kwargs
: additional keyword arguments to be passed toself.call
.
Returns:
Output tensor(s).
tf.contrib.eager.Network.build
build(input_shape)
Creates the variables of the layer (optional, for subclass implementers).
This is a method that implementers of subclasses of Layer
or Model
can override if they need a state-creation step in-between
layer instantiation and layer call.
This is typically used to create the weights of Layer
subclasses.
Arguments:
input_shape
: Instance ofTensorShape
, or list of instances ofTensorShape
if the layer expects a list of inputs (one instance per input).
tf.contrib.eager.Network.compute_mask
compute_mask(
inputs,
mask=None
)
Computes an output mask tensor.
Arguments:
inputs
: Tensor or list of tensors.mask
: Tensor or list of tensors.
Returns:
None or a tensor (or list of tensors, one per output tensor of the layer).
tf.contrib.eager.Network.compute_output_shape
compute_output_shape(input_shape)
Computes the output shape of the layer.
Assumes that the layer will be built to match that input shape provided.
Arguments:
input_shape
: Shape tuple (tuple of integers) or list of shape tuples (one per output tensor of the layer). Shape tuples can include None for free dimensions, instead of an integer.
Returns:
An input shape tuple.
tf.contrib.eager.Network.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).
tf.contrib.eager.Network.from_config
from_config(
cls,
config
)
Creates a layer from its config.
This method is the reverse of get_config
,
capable of instantiating the same layer from the config
dictionary. It does not handle layer connectivity
(handled by Network), nor weights (handled by set_weights
).
Arguments:
config
: A Python dictionary, typically the output of get_config.
Returns:
A layer instance.
tf.contrib.eager.Network.get_config
get_config()
Returns the config of the layer.
A layer config is a Python dictionary (serializable) containing the configuration of a layer. The same layer can be reinstantiated later (without its trained weights) from this configuration.
The config of a layer does not include connectivity
information, nor the layer class name. These are handled
by Network
(one layer of abstraction above).
Returns:
Python dictionary.
tf.contrib.eager.Network.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.
tf.contrib.eager.Network.get_input_mask_at
get_input_mask_at(node_index)
Retrieves the input mask 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 mask tensor (or list of tensors if the layer has multiple inputs).
tf.contrib.eager.Network.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.
tf.contrib.eager.Network.get_layer
get_layer(
name=None,
index=None
)
Get a contained tf.layers.Layer
either by name or index.
Args:
name
: String matching one of the names of a containedLayer
. Note that the names ofLayer
s added toNetwork
s may not be unique when doing layer sharing (i.e. adding aLayer
to thisNetwork
which was already added to anotherNetwork
). The lowest indexLayer
with a matching name will be returned.index
: Integer in [0, number of layers). Layers are assigned an index by the order they are added.
Returns:
A tf.layers.Layer
object.
Raises:
ValueError
: If neither or both of 'index' or 'name' is specified, or the lookup failed.
tf.contrib.eager.Network.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.
tf.contrib.eager.Network.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.
tf.contrib.eager.Network.get_output_mask_at
get_output_mask_at(node_index)
Retrieves the output mask 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 mask tensor (or list of tensors if the layer has multiple outputs).
tf.contrib.eager.Network.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.
tf.contrib.eager.Network.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.
tf.contrib.eager.Network.get_weights
get_weights()
Returns the current weights of the layer.
Returns:
Weights values as a list of numpy arrays.
tf.contrib.eager.Network.set_weights
set_weights(weights)
Sets the weights of the layer, from Numpy arrays.
Arguments:
weights
: a list of Numpy arrays. The number of arrays and their shape must match number of the dimensions of the weights of the layer (i.e. it should match the output ofget_weights
).
Raises:
ValueError
: If the provided weights list does not match the layer's specifications.
tf.contrib.eager.Network.track_layer
track_layer(layer)
Track a Layer in this Network.
Network
requires that all Layer
s used in call()
be tracked so that the
Network
can export a complete list of variables.
Args:
layer
: Atf.layers.Layer
object.
Returns:
The passed in layer
.
Raises:
RuntimeError
: If init has not been called.TypeError
: Iflayer
is the wrong type.ValueError
: If aLayer
with the same name has already been added.