GDN
Inherits From: Layer
Defined in tensorflow/contrib/layers/python/layers/layers.py
.
Generalized divisive normalization layer.
Based on the papers:
"Density Modeling of Images using a Generalized Normalization Transformation"
Johannes Ballé, Valero Laparra, Eero P. Simoncelli
https://arxiv.org/abs/1511.06281
"End-to-end Optimized Image Compression"
Johannes Ballé, Valero Laparra, Eero P. Simoncelli
https://arxiv.org/abs/1611.01704
Implements an activation function that is essentially a multivariate generalization of a particular sigmoid-type function:
y[i] = x[i] / sqrt(beta[i] + sum_j(gamma[j, i] * x[j]))
where i
and j
run over channels. This implementation never sums across spatial dimensions. It is similar to local response normalization, but much more flexible, as beta
and gamma
are trainable parameters.
inverse
: If False
(default), compute GDN response. If True
, compute IGDN response (one step of fixed point iteration to invert GDN; the division is replaced by multiplication).beta_min
: Lower bound for beta, to prevent numerical error from causing square root of zero or negative values.gamma_init
: The gamma matrix will be initialized as the identity matrix multiplied with this value. If set to zero, the layer is effectively initialized to the identity operation, since beta is initialized as one. A good default setting is somewhere between 0 and 0.5.reparam_offset
: Offset added to the reparameterization of beta and gamma. The reparameterization of beta and gamma as their square roots lets the training slow down when their values are close to zero, which is desirable as small values in the denominator can lead to a situation where gradient noise on beta/gamma leads to extreme amounts of noise in the GDN activations. However, without the offset, we would get zero gradients if any elements of beta or gamma were exactly zero, and thus the training could get stuck. To prevent this, we add this small constant. The default value was empirically determined as a good starting point. Making it bigger potentially leads to more gradient noise on the activations, making it too small may lead to numerical precision issues.data_format
: Format of input tensor. Currently supports 'channels_first'
and 'channels_last'
.activity_regularizer
: Regularizer function for the output.trainable
: Boolean, if True
, also add variables to the graph collection GraphKeys.TRAINABLE_VARIABLES
(see tf.Variable
).name
: String, the name of the layer. Layers with the same name will share weights, but to avoid mistakes we require reuse=True
in such cases.Properties: inverse
: Boolean, whether GDN is computed (True
) or IGDN (False
). data_format
: Format of input tensor. Currently supports 'channels_first'
and 'channels_last'
. beta
: The beta parameter as defined above (1D Tensor
). gamma
: The gamma parameter as defined above (2D Tensor
).
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.
Input tensor or list of input tensors.
AttributeError
: if the layer is connected to more than one incoming layers.RuntimeError
: If called in Eager mode.AttributeError
: If no inbound nodes are found.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.
Input shape, as an integer shape tuple (or list of shape tuples, one tuple per input tensor).
AttributeError
: if the layer has no defined input_shape.RuntimeError
: if called in Eager mode.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.
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.
Output tensor or list of output tensors.
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.
Output shape, as an integer shape tuple (or list of shape tuples, one tuple per output tensor).
AttributeError
: if the layer has no defined output shape.RuntimeError
: if called in Eager mode.scope_name
trainable_variables
trainable_weights
updates
variables
Returns the list of all layer variables/weights.
A list of variables.
weights
Returns the list of all layer variables/weights.
A list of variables.
__init__
__init__( inverse=False, beta_min=1e-06, gamma_init=0.1, reparam_offset=(2 ** -18), data_format='channels_last', activity_regularizer=None, trainable=True, name=None, **kwargs )
Initialize self. See help(type(self)) for accurate signature.
__call__
__call__( inputs, *args, **kwargs )
Wraps call
, applying pre- and post-processing steps.
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.Output tensor(s).
Note: - If the layer'scall
method takes ascope
keyword argument, this argument will be automatically set to the current variable scope. - If the layer'scall
method takes amask
argument (as some Keras layers do), its default value will be set to the mask generated forinputs
by the previous layer (ifinput
did come from a layer that generated a corresponding mask, i.e. if it came from a Keras layer with masking support.
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()
).
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).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.
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.
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.The created variable. Usually either a Variable
or ResourceVariable
instance. If partitioner
is not None
, a PartitionedVariable
instance is returned.
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__
.
inputs
: Input tensor(s).*args
: additional positional arguments to be passed to self.call
.**kwargs
: additional keyword arguments to be passed to self.call
.Output tensor(s).
build
build(input_shape)
Creates the variables of the layer.
call
call(inputs)
The logic of the layer lives here.
inputs
: input tensor(s).**kwargs
: additional keyword arguments.Output tensor(s).
compute_output_shape
compute_output_shape(input_shape)
Computes the output shape of the layer given the input shape.
input_shape
: A (possibly nested tuple of) TensorShape
. It need not be fully defined (e.g. the batch size may be unknown).A (possibly nested tuple of) TensorShape
.
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.
An integer count.
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.
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.A tensor (or list of tensors if the layer has multiple inputs).
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.
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.A shape tuple (or list of shape tuples if the layer has multiple inputs).
RuntimeError
: If called in Eager mode.get_losses_for
get_losses_for(inputs)
Retrieves losses relevant to a specific set of inputs.
inputs
: Input tensor or list/tuple of input tensors.List of loss tensors of the layer that depend on inputs
.
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.
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.A tensor (or list of tensors if the layer has multiple outputs).
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.
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.A shape tuple (or list of shape tuples if the layer has multiple outputs).
RuntimeError
: If called in Eager mode.get_updates_for
get_updates_for(inputs)
Retrieves updates relevant to a specific set of inputs.
inputs
: Input tensor or list/tuple of input tensors.List of update ops of the layer that depend on inputs
.
RuntimeError
: If called in Eager mode.
© 2018 The TensorFlow Authors. All rights reserved.
Licensed under the Creative Commons Attribution License 3.0.
Code samples licensed under the Apache 2.0 License.
https://www.tensorflow.org/api_docs/python/tf/contrib/layers/GDN