def deserialize(name, custom_objects=None):
"""Returns activation function given a string identifier.
Args:
name: The name of the activation function.
custom_objects: Optional `{function_name: function_obj}`
dictionary listing user-provided activation functions.
Returns:
Corresponding activation function.
For example:
>>> tf.keras.activations.deserialize('linear')
<function linear at 0x1239596a8>
>>> tf.keras.activations.deserialize('sigmoid')
<function sigmoid at 0x123959510>
>>> tf.keras.activations.deserialize('abcd')
Traceback (most recent call last):
...
ValueError: Unknown activation function:abcd
Raises:
ValueError: `Unknown activation function` if the input string does not
denote any defined Tensorflow activation function.
"""
activation_functions = {}
current_module = sys.modules[__name__]
# we put 'current_module' after 'activation_layers' to prefer the local one
# if there is a collision
generic_utils.populate_dict_with_module_objects(
activation_functions,
(activation_layers, current_module),
obj_filter=callable,
)
return generic_utils.deserialize_keras_object(
name,
module_objects=activation_functions,
custom_objects=custom_objects,
printable_module_name="activation function",
)
def populate_deserializable_objects():
"""Populates dict ALL_OBJECTS with every built-in layer.
"""
global LOCAL
if not hasattr(LOCAL, 'ALL_OBJECTS'):
LOCAL.ALL_OBJECTS = {}
LOCAL.GENERATED_WITH_V2 = None
if LOCAL.ALL_OBJECTS and LOCAL.GENERATED_WITH_V2 == tf.__internal__.tf2.enabled(
):
# Objects dict is already generated for the proper TF version:
# do nothing.
return
LOCAL.ALL_OBJECTS = {}
LOCAL.GENERATED_WITH_V2 = tf.__internal__.tf2.enabled()
base_cls = base_layer.Layer
generic_utils.populate_dict_with_module_objects(
LOCAL.ALL_OBJECTS,
ALL_MODULES,
obj_filter=lambda x: inspect.isclass(x) and issubclass(x, base_cls))
# Overwrite certain V1 objects with V2 versions
if tf.__internal__.tf2.enabled():
generic_utils.populate_dict_with_module_objects(
LOCAL.ALL_OBJECTS,
ALL_V2_MODULES,
obj_filter=lambda x: inspect.isclass(x) and issubclass(
x, base_cls))
# These deserialization aliases are added for backward compatibility,
# as in TF 1.13, "BatchNormalizationV1" and "BatchNormalizationV2"
# were used as class name for v1 and v2 version of BatchNormalization,
# respectively. Here we explicitly convert them to their canonical names.
LOCAL.ALL_OBJECTS[
'BatchNormalizationV1'] = normalization.BatchNormalization
LOCAL.ALL_OBJECTS[
'BatchNormalizationV2'] = normalization_v2.BatchNormalization
# Prevent circular dependencies.
from keras import models # pylint: disable=g-import-not-at-top
from keras.premade.linear import LinearModel # pylint: disable=g-import-not-at-top
from keras.premade.wide_deep import WideDeepModel # pylint: disable=g-import-not-at-top
from keras.feature_column.sequence_feature_column import SequenceFeatures # pylint: disable=g-import-not-at-top
LOCAL.ALL_OBJECTS['Input'] = input_layer.Input
LOCAL.ALL_OBJECTS['InputSpec'] = input_spec.InputSpec
LOCAL.ALL_OBJECTS['Functional'] = models.Functional
LOCAL.ALL_OBJECTS['Model'] = models.Model
LOCAL.ALL_OBJECTS['SequenceFeatures'] = SequenceFeatures
LOCAL.ALL_OBJECTS['Sequential'] = models.Sequential
LOCAL.ALL_OBJECTS['LinearModel'] = LinearModel
LOCAL.ALL_OBJECTS['WideDeepModel'] = WideDeepModel
if tf.__internal__.tf2.enabled():
from keras.feature_column.dense_features_v2 import DenseFeatures # pylint: disable=g-import-not-at-top
LOCAL.ALL_OBJECTS['DenseFeatures'] = DenseFeatures
else:
from keras.feature_column.dense_features import DenseFeatures # pylint: disable=g-import-not-at-top
LOCAL.ALL_OBJECTS['DenseFeatures'] = DenseFeatures
# Merge layers, function versions.
LOCAL.ALL_OBJECTS['add'] = merge.add
LOCAL.ALL_OBJECTS['subtract'] = merge.subtract
LOCAL.ALL_OBJECTS['multiply'] = merge.multiply
LOCAL.ALL_OBJECTS['average'] = merge.average
LOCAL.ALL_OBJECTS['maximum'] = merge.maximum
LOCAL.ALL_OBJECTS['minimum'] = merge.minimum
LOCAL.ALL_OBJECTS['concatenate'] = merge.concatenate
LOCAL.ALL_OBJECTS['dot'] = merge.dot
def populate_deserializable_objects():
"""Populates dict ALL_OBJECTS with every built-in layer."""
global LOCAL
if not hasattr(LOCAL, "ALL_OBJECTS"):
LOCAL.ALL_OBJECTS = {}
LOCAL.GENERATED_WITH_V2 = None
if (
LOCAL.ALL_OBJECTS
and LOCAL.GENERATED_WITH_V2 == tf.__internal__.tf2.enabled()
):
# Objects dict is already generated for the proper TF version:
# do nothing.
return
LOCAL.ALL_OBJECTS = {}
LOCAL.GENERATED_WITH_V2 = tf.__internal__.tf2.enabled()
base_cls = base_layer.Layer
generic_utils.populate_dict_with_module_objects(
LOCAL.ALL_OBJECTS,
ALL_MODULES,
obj_filter=lambda x: inspect.isclass(x) and issubclass(x, base_cls),
)
# Overwrite certain V1 objects with V2 versions
if tf.__internal__.tf2.enabled():
generic_utils.populate_dict_with_module_objects(
LOCAL.ALL_OBJECTS,
ALL_V2_MODULES,
obj_filter=lambda x: inspect.isclass(x) and issubclass(x, base_cls),
)
# These deserialization aliases are added for backward compatibility,
# as in TF 1.13, "BatchNormalizationV1" and "BatchNormalizationV2"
# were used as class name for v1 and v2 version of BatchNormalization,
# respectively. Here we explicitly convert them to their canonical names.
LOCAL.ALL_OBJECTS[
"BatchNormalizationV1"
] = batch_normalization_v1.BatchNormalization
LOCAL.ALL_OBJECTS[
"BatchNormalizationV2"
] = batch_normalization.BatchNormalization
# Prevent circular dependencies.
from keras import models
from keras.feature_column.sequence_feature_column import (
SequenceFeatures,
)
from keras.premade_models.linear import (
LinearModel,
)
from keras.premade_models.wide_deep import (
WideDeepModel,
)
LOCAL.ALL_OBJECTS["Input"] = input_layer.Input
LOCAL.ALL_OBJECTS["InputSpec"] = input_spec.InputSpec
LOCAL.ALL_OBJECTS["Functional"] = models.Functional
LOCAL.ALL_OBJECTS["Model"] = models.Model
LOCAL.ALL_OBJECTS["SequenceFeatures"] = SequenceFeatures
LOCAL.ALL_OBJECTS["Sequential"] = models.Sequential
LOCAL.ALL_OBJECTS["LinearModel"] = LinearModel
LOCAL.ALL_OBJECTS["WideDeepModel"] = WideDeepModel
if tf.__internal__.tf2.enabled():
from keras.feature_column.dense_features_v2 import (
DenseFeatures,
)
LOCAL.ALL_OBJECTS["DenseFeatures"] = DenseFeatures
else:
from keras.feature_column.dense_features import (
DenseFeatures,
)
LOCAL.ALL_OBJECTS["DenseFeatures"] = DenseFeatures
# Merging layers, function versions.
LOCAL.ALL_OBJECTS["add"] = merging.add
LOCAL.ALL_OBJECTS["subtract"] = merging.subtract
LOCAL.ALL_OBJECTS["multiply"] = merging.multiply
LOCAL.ALL_OBJECTS["average"] = merging.average
LOCAL.ALL_OBJECTS["maximum"] = merging.maximum
LOCAL.ALL_OBJECTS["minimum"] = merging.minimum
LOCAL.ALL_OBJECTS["concatenate"] = merging.concatenate
LOCAL.ALL_OBJECTS["dot"] = merging.dot
def populate_deserializable_objects():
"""Populates dict ALL_OBJECTS with every built-in initializer."""
global LOCAL
if not hasattr(LOCAL, "ALL_OBJECTS"):
LOCAL.ALL_OBJECTS = {}
LOCAL.GENERATED_WITH_V2 = None
if (LOCAL.ALL_OBJECTS
and LOCAL.GENERATED_WITH_V2 == tf.__internal__.tf2.enabled()):
# Objects dict is already generated for the proper TF version:
# do nothing.
return
LOCAL.ALL_OBJECTS = {}
LOCAL.GENERATED_WITH_V2 = tf.__internal__.tf2.enabled()
# Compatibility aliases (need to exist in both V1 and V2).
LOCAL.ALL_OBJECTS["ConstantV2"] = initializers_v2.Constant
LOCAL.ALL_OBJECTS["GlorotNormalV2"] = initializers_v2.GlorotNormal
LOCAL.ALL_OBJECTS["GlorotUniformV2"] = initializers_v2.GlorotUniform
LOCAL.ALL_OBJECTS["HeNormalV2"] = initializers_v2.HeNormal
LOCAL.ALL_OBJECTS["HeUniformV2"] = initializers_v2.HeUniform
LOCAL.ALL_OBJECTS["IdentityV2"] = initializers_v2.Identity
LOCAL.ALL_OBJECTS["LecunNormalV2"] = initializers_v2.LecunNormal
LOCAL.ALL_OBJECTS["LecunUniformV2"] = initializers_v2.LecunUniform
LOCAL.ALL_OBJECTS["OnesV2"] = initializers_v2.Ones
LOCAL.ALL_OBJECTS["OrthogonalV2"] = initializers_v2.Orthogonal
LOCAL.ALL_OBJECTS["RandomNormalV2"] = initializers_v2.RandomNormal
LOCAL.ALL_OBJECTS["RandomUniformV2"] = initializers_v2.RandomUniform
LOCAL.ALL_OBJECTS["TruncatedNormalV2"] = initializers_v2.TruncatedNormal
LOCAL.ALL_OBJECTS["VarianceScalingV2"] = initializers_v2.VarianceScaling
LOCAL.ALL_OBJECTS["ZerosV2"] = initializers_v2.Zeros
# Out of an abundance of caution we also include these aliases that have
# a non-zero probability of having been included in saved configs in the past.
LOCAL.ALL_OBJECTS["glorot_normalV2"] = initializers_v2.GlorotNormal
LOCAL.ALL_OBJECTS["glorot_uniformV2"] = initializers_v2.GlorotUniform
LOCAL.ALL_OBJECTS["he_normalV2"] = initializers_v2.HeNormal
LOCAL.ALL_OBJECTS["he_uniformV2"] = initializers_v2.HeUniform
LOCAL.ALL_OBJECTS["lecun_normalV2"] = initializers_v2.LecunNormal
LOCAL.ALL_OBJECTS["lecun_uniformV2"] = initializers_v2.LecunUniform
if tf.__internal__.tf2.enabled():
# For V2, entries are generated automatically based on the content of
# initializers_v2.py.
v2_objs = {}
base_cls = initializers_v2.Initializer
generic_utils.populate_dict_with_module_objects(
v2_objs,
[initializers_v2],
obj_filter=lambda x: inspect.isclass(x) and issubclass(
x, base_cls),
)
for key, value in v2_objs.items():
LOCAL.ALL_OBJECTS[key] = value
# Functional aliases.
LOCAL.ALL_OBJECTS[generic_utils.to_snake_case(key)] = value
else:
# V1 initializers.
v1_objs = {
"Constant": tf.compat.v1.constant_initializer,
"GlorotNormal": tf.compat.v1.glorot_normal_initializer,
"GlorotUniform": tf.compat.v1.glorot_uniform_initializer,
"Identity": tf.compat.v1.initializers.identity,
"Ones": tf.compat.v1.ones_initializer,
"Orthogonal": tf.compat.v1.orthogonal_initializer,
"VarianceScaling": tf.compat.v1.variance_scaling_initializer,
"Zeros": tf.compat.v1.zeros_initializer,
"HeNormal": initializers_v1.HeNormal,
"HeUniform": initializers_v1.HeUniform,
"LecunNormal": initializers_v1.LecunNormal,
"LecunUniform": initializers_v1.LecunUniform,
"RandomNormal": initializers_v1.RandomNormal,
"RandomUniform": initializers_v1.RandomUniform,
"TruncatedNormal": initializers_v1.TruncatedNormal,
}
for key, value in v1_objs.items():
LOCAL.ALL_OBJECTS[key] = value
# Functional aliases.
LOCAL.ALL_OBJECTS[generic_utils.to_snake_case(key)] = value
# More compatibility aliases.
LOCAL.ALL_OBJECTS["normal"] = LOCAL.ALL_OBJECTS["random_normal"]
LOCAL.ALL_OBJECTS["uniform"] = LOCAL.ALL_OBJECTS["random_uniform"]
LOCAL.ALL_OBJECTS["one"] = LOCAL.ALL_OBJECTS["ones"]
LOCAL.ALL_OBJECTS["zero"] = LOCAL.ALL_OBJECTS["zeros"]
