Python源码示例：tensorflow.core.protobuf.meta.SignatureDef()
示例1
def build_signature_def(inputs=None, outputs=None, method_name=None):
"""Utility function to build a SignatureDef protocol buffer.
Args:
inputs: Inputs of the SignatureDef defined as a proto map of string to
tensor info.
outputs: Outputs of the SignatureDef defined as a proto map of string to
tensor info.
method_name: Method name of the SignatureDef as a string.
Returns:
A SignatureDef protocol buffer constructed based on the supplied arguments.
"""
signature_def = meta_graph_pb2.SignatureDef()
if inputs is not None:
for item in inputs:
signature_def.inputs[item].CopyFrom(inputs[item])
if outputs is not None:
for item in outputs:
signature_def.outputs[item].CopyFrom(outputs[item])
if method_name is not None:
signature_def.method_name = method_name
return signature_def
示例2
def build_signature_def(inputs=None, outputs=None, method_name=None):
"""Utility function to build a SignatureDef protocol buffer.
Args:
inputs: Inputs of the SignatureDef defined as a proto map of string to
tensor info.
outputs: Outputs of the SignatureDef defined as a proto map of string to
tensor info.
method_name: Method name of the SignatureDef as a string.
Returns:
A SignatureDef protocol buffer constructed based on the supplied arguments.
"""
signature_def = meta_graph_pb2.SignatureDef()
if inputs is not None:
for item in inputs:
signature_def.inputs[item].CopyFrom(inputs[item])
if outputs is not None:
for item in outputs:
signature_def.outputs[item].CopyFrom(outputs[item])
if method_name is not None:
signature_def.method_name = method_name
return signature_def
示例3
def build_signature_def(inputs=None, outputs=None, method_name=None):
"""Utility function to build a SignatureDef protocol buffer.
Args:
inputs: Inputs of the SignatureDef defined as a proto map of string to
tensor info.
outputs: Outputs of the SignatureDef defined as a proto map of string to
tensor info.
method_name: Method name of the SignatureDef as a string.
Returns:
A SignatureDef protocol buffer constructed based on the supplied arguments.
"""
signature_def = meta_graph_pb2.SignatureDef()
if inputs is not None:
for item in inputs:
signature_def.inputs[item].CopyFrom(inputs[item])
if outputs is not None:
for item in outputs:
signature_def.outputs[item].CopyFrom(outputs[item])
if method_name is not None:
signature_def.method_name = method_name
return signature_def
示例4
def _build_signature_def(graph: tf.Graph,
input_nodes: list,
output_nodes: list) -> SignatureDef:
"""Build model signature (input- and output descriptions) for a graph"""
signature_def = SignatureDef()
def add_tensor(nodes, info):
nodes[info.name].name = info.name
if info.dtype is not None:
dtype = dtypes.as_dtype(info.dtype)
shape = tf.TensorShape(info.shape)
nodes[info.name].dtype = dtype.as_datatype_enum
nodes[info.name].tensor_shape.CopyFrom(shape.as_proto())
for input_info in input_nodes:
op = graph.get_operation_by_name(input_info.name)
if op.type != c.TFJS_NODE_CONST_KEY:
add_tensor(signature_def.inputs, input_info)
for output_info in output_nodes:
add_tensor(signature_def.outputs, output_info)
return signature_def
示例5
def build_signature_def(inputs=None, outputs=None, method_name=None):
"""Utility function to build a SignatureDef protocol buffer.
Args:
inputs: Inputs of the SignatureDef defined as a proto map of string to
tensor info.
outputs: Outputs of the SignatureDef defined as a proto map of string to
tensor info.
method_name: Method name of the SignatureDef as a string.
Returns:
A SignatureDef protocol buffer constructed based on the supplied arguments.
"""
signature_def = meta_graph_pb2.SignatureDef()
if inputs is not None:
for item in inputs:
signature_def.inputs[item].CopyFrom(inputs[item])
if outputs is not None:
for item in outputs:
signature_def.outputs[item].CopyFrom(outputs[item])
if method_name is not None:
signature_def.method_name = method_name
return signature_def
示例6
def _is_valid_regression_signature(signature_def):
"""Determine whether the argument is a servable 'regress' SignatureDef."""
if signature_def.method_name != signature_constants.REGRESS_METHOD_NAME:
return False
if (set(signature_def.inputs.keys())
!= set([signature_constants.REGRESS_INPUTS])):
return False
if (signature_def.inputs[signature_constants.REGRESS_INPUTS].dtype !=
types_pb2.DT_STRING):
return False
if (set(signature_def.outputs.keys())
!= set([signature_constants.REGRESS_OUTPUTS])):
return False
if (signature_def.outputs[signature_constants.REGRESS_OUTPUTS].dtype !=
types_pb2.DT_FLOAT):
return False
return True
示例7
def build_signature_def(inputs=None, outputs=None, method_name=None):
"""Utility function to build a SignatureDef protocol buffer.
Args:
inputs: Inputs of the SignatureDef defined as a proto map of string to
tensor info.
outputs: Outputs of the SignatureDef defined as a proto map of string to
tensor info.
method_name: Method name of the SignatureDef as a string.
Returns:
A SignatureDef protocol buffer constructed based on the supplied arguments.
"""
signature_def = meta_graph_pb2.SignatureDef()
if inputs is not None:
for item in inputs:
signature_def.inputs[item].CopyFrom(inputs[item])
if outputs is not None:
for item in outputs:
signature_def.outputs[item].CopyFrom(outputs[item])
if method_name is not None:
signature_def.method_name = method_name
return signature_def
示例8
def _add_input_to_signature_def(tensor_name, map_key, signature_def):
"""Add input tensor to signature_def.
Args:
tensor_name: string name of tensor to add to signature_def inputs
map_key: string key to key into signature_def inputs map
signature_def: object of type meta_graph_pb2.SignatureDef()
Sideffect:
adds a TensorInfo with tensor_name to signature_def inputs map keyed with
map_key
"""
tensor_info = meta_graph_pb2.TensorInfo(name=tensor_name)
signature_def.inputs[map_key].CopyFrom(tensor_info)
示例9
def _add_output_to_signature_def(tensor_name, map_key, signature_def):
"""Add output tensor to signature_def.
Args:
tensor_name: string name of tensor to add to signature_def outputs
map_key: string key to key into signature_def outputs map
signature_def: object of type meta_graph_pb2.SignatureDef()
Sideffect:
adds a TensorInfo with tensor_name to signature_def outputs map keyed with
map_key
"""
tensor_info = meta_graph_pb2.TensorInfo(name=tensor_name)
signature_def.outputs[map_key].CopyFrom(tensor_info)
示例10
def _convert_named_signatures_to_signature_def(signatures):
"""Convert named signatures to object of type SignatureDef.
Args:
signatures: object of type manifest_pb2.Signatures()
Returns:
object of type SignatureDef which contains a converted version of named
signatures from input signatures object
Raises:
RuntimeError: if input and output named signatures are not of type
GenericSignature
"""
signature_def = meta_graph_pb2.SignatureDef()
input_signature = signatures.named_signatures[
signature_constants.PREDICT_INPUTS]
output_signature = signatures.named_signatures[
signature_constants.PREDICT_OUTPUTS]
# TODO(pdudnik): what if there are other signatures? Mimic cr/140900781 once
# it is submitted.
if (input_signature.WhichOneof("type") != "generic_signature" or
output_signature.WhichOneof("type") != "generic_signature"):
raise RuntimeError("Named input and output signatures can only be "
"up-converted if they are generic signature. "
"Input signature type is %s, output signature type is "
"%s" % (input_signature.WhichOneof("type"),
output_signature.WhichOneof("type")))
signature_def.method_name = signature_constants.PREDICT_METHOD_NAME
for key, val in input_signature.generic_signature.map.items():
_add_input_to_signature_def(val.tensor_name, key, signature_def)
for key, val in output_signature.generic_signature.map.items():
_add_output_to_signature_def(val.tensor_name, key, signature_def)
return signature_def
示例11
def _add_input_to_signature_def(tensor_name, map_key, signature_def):
"""Add input tensor to signature_def.
Args:
tensor_name: string name of tensor to add to signature_def inputs
map_key: string key to key into signature_def inputs map
signature_def: object of type meta_graph_pb2.SignatureDef()
Sideffect:
adds a TensorInfo with tensor_name to signature_def inputs map keyed with
map_key
"""
tensor_info = meta_graph_pb2.TensorInfo(name=tensor_name)
signature_def.inputs[map_key].CopyFrom(tensor_info)
示例12
def _add_output_to_signature_def(tensor_name, map_key, signature_def):
"""Add output tensor to signature_def.
Args:
tensor_name: string name of tensor to add to signature_def outputs
map_key: string key to key into signature_def outputs map
signature_def: object of type meta_graph_pb2.SignatureDef()
Sideffect:
adds a TensorInfo with tensor_name to signature_def outputs map keyed with
map_key
"""
tensor_info = meta_graph_pb2.TensorInfo(name=tensor_name)
signature_def.outputs[map_key].CopyFrom(tensor_info)
示例13
def _convert_named_signatures_to_signature_def(signatures):
"""Convert named signatures to object of type SignatureDef.
Args:
signatures: object of type manifest_pb2.Signatures()
Returns:
object of type SignatureDef which contains a converted version of named
signatures from input signatures object
Raises:
RuntimeError: if input and output named signatures are not of type
GenericSignature
"""
signature_def = meta_graph_pb2.SignatureDef()
input_signature = signatures.named_signatures[
signature_constants.PREDICT_INPUTS]
output_signature = signatures.named_signatures[
signature_constants.PREDICT_OUTPUTS]
# TODO(pdudnik): what if there are other signatures? Mimic cr/140900781 once
# it is submitted.
if (input_signature.WhichOneof("type") != "generic_signature" or
output_signature.WhichOneof("type") != "generic_signature"):
raise RuntimeError("Named input and output signatures can only be "
"up-converted if they are generic signature. "
"Input signature type is %s, output signature type is "
"%s" % (input_signature.WhichOneof("type"),
output_signature.WhichOneof("type")))
signature_def.method_name = signature_constants.PREDICT_METHOD_NAME
for key, val in input_signature.generic_signature.map.items():
_add_input_to_signature_def(val.tensor_name, key, signature_def)
for key, val in output_signature.generic_signature.map.items():
_add_output_to_signature_def(val.tensor_name, key, signature_def)
return signature_def
示例14
def _convert_signatures_to_signature_defs(metagraph_def):
"""Produce default and named upconverted SignatureDef objects from Signatures.
Args:
metagraph_def: object of type meta_graph_pb2.MetaGraphDef containing legacy
format Session Bundle signatures
Returns:
default_signature_def: object of type SignatureDef which contains an
upconverted version of default signatures in metagraph_def
named_signature_def: object of type SignatureDef which contains an
upconverted version of named signatures in metagraph_def
"""
collection_def = metagraph_def.collection_def
signatures_proto = manifest_pb2.Signatures()
signatures = collection_def[legacy_constants.SIGNATURES_KEY].any_list.value[0]
signatures.Unpack(signatures_proto)
default_signature_def = None
named_signature_def = None
if signatures_proto.HasField("default_signature"):
default_signature_def = _convert_default_signature_to_signature_def(
signatures_proto)
if len(signatures_proto.named_signatures) > 1:
named_signature_def = _convert_named_signatures_to_signature_def(
signatures_proto)
return default_signature_def, named_signature_def
示例15
def build_tensor_info(name=None, dtype=None, shape=None):
"""Utility function to build TensorInfo proto.
Args:
name: Name of the tensor to be used in the TensorInfo.
dtype: Datatype to be set in the TensorInfo.
shape: TensorShapeProto to specify the shape of the tensor in the
TensorInfo.
Returns:
A TensorInfo protocol buffer constructed based on the supplied arguments.
"""
return meta_graph_pb2.TensorInfo(name=name, dtype=dtype, shape=shape)
# SignatureDef helpers.
示例16
def _mark_outputs_as_train_op(graph: tf.Graph,
signature_def: SignatureDef) -> None:
"""Mark output nodes as training ops, so the optimizer ignores them"""
train_op = GraphKeys.TRAIN_OP
for _, tensor in signature_def.outputs.items():
name = _to_node_name(tensor.name)
graph.add_to_collection(train_op, graph.get_operation_by_name(name))
示例17
def _run_tf_optimizer(config: ConfigProto,
graph: tf.Graph,
signature_def: SignatureDef) -> GraphDef:
"""Run the TF optimizer ("grappler") on a graph"""
graph_def = graph.as_graph_def()
meta_graph = export_meta_graph(graph_def=graph_def, graph=graph)
meta_graph.signature_def['not_used_key'].CopyFrom(signature_def)
return tf_optimizer.OptimizeGraph(config, meta_graph)
示例18
def is_valid_signature(signature_def):
"""Determine whether a SignatureDef can be served by TensorFlow Serving."""
if signature_def is None:
return False
return (_is_valid_classification_signature(signature_def) or
_is_valid_regression_signature(signature_def) or
_is_valid_predict_signature(signature_def))
示例19
def _is_valid_predict_signature(signature_def):
"""Determine whether the argument is a servable 'predict' SignatureDef."""
if signature_def.method_name != signature_constants.PREDICT_METHOD_NAME:
return False
if not signature_def.inputs.keys():
return False
if not signature_def.outputs.keys():
return False
return True
示例20
def _is_valid_classification_signature(signature_def):
"""Determine whether the argument is a servable 'classify' SignatureDef."""
if signature_def.method_name != signature_constants.CLASSIFY_METHOD_NAME:
return False
if (set(signature_def.inputs.keys())
!= set([signature_constants.CLASSIFY_INPUTS])):
return False
if (signature_def.inputs[signature_constants.CLASSIFY_INPUTS].dtype !=
types_pb2.DT_STRING):
return False
allowed_outputs = set([signature_constants.CLASSIFY_OUTPUT_CLASSES,
signature_constants.CLASSIFY_OUTPUT_SCORES])
if not signature_def.outputs.keys():
return False
if set(signature_def.outputs.keys()) - allowed_outputs:
return False
if (signature_constants.CLASSIFY_OUTPUT_CLASSES in signature_def.outputs
and
signature_def.outputs[signature_constants.CLASSIFY_OUTPUT_CLASSES].dtype
!= types_pb2.DT_STRING):
return False
if (signature_constants.CLASSIFY_OUTPUT_SCORES in signature_def.outputs
and
signature_def.outputs[signature_constants.CLASSIFY_OUTPUT_SCORES].dtype !=
types_pb2.DT_FLOAT):
return False
return True
示例21
def get_signature_def_input_types(signature):
"""Returns map of output names to their types.
Args:
signature: SignatureDef proto.
Returns:
Map from string to DType objects.
"""
return _get_types_from_tensor_info_dict(signature.inputs)
示例22
def get_signature_def_output_shapes(signature):
"""Returns map of output names to their shapes.
Args:
signature: SignatureDef proto.
Returns:
Map from string to TensorShape objects.
"""
return _get_shapes_from_tensor_info_dict(signature.outputs)
示例23
def get_signature_def_output_types(signature):
"""Returns map of output names to their types.
Args:
signature: SignatureDef proto.
Returns:
Map from string to DType objects.
"""
return _get_types_from_tensor_info_dict(signature.outputs)
示例24
def _add_input_to_signature_def(tensor_name, map_key, signature_def):
"""Add input tensor to signature_def.
Args:
tensor_name: string name of tensor to add to signature_def inputs
map_key: string key to key into signature_def inputs map
signature_def: object of type meta_graph_pb2.SignatureDef()
Sideffect:
adds a TensorInfo with tensor_name to signature_def inputs map keyed with
map_key
"""
tensor_info = meta_graph_pb2.TensorInfo(name=tensor_name)
signature_def.inputs[map_key].CopyFrom(tensor_info)
示例25
def _add_output_to_signature_def(tensor_name, map_key, signature_def):
"""Add output tensor to signature_def.
Args:
tensor_name: string name of tensor to add to signature_def outputs
map_key: string key to key into signature_def outputs map
signature_def: object of type meta_graph_pb2.SignatureDef()
Sideffect:
adds a TensorInfo with tensor_name to signature_def outputs map keyed with
map_key
"""
tensor_info = meta_graph_pb2.TensorInfo(name=tensor_name)
signature_def.outputs[map_key].CopyFrom(tensor_info)
示例26
def _convert_named_signatures_to_signature_def(signatures):
"""Convert named signatures to object of type SignatureDef.
Args:
signatures: object of type manifest_pb2.Signatures()
Returns:
object of type SignatureDef which contains a converted version of named
signatures from input signatures object
Raises:
RuntimeError: if input and output named signatures are not of type
GenericSignature
"""
signature_def = meta_graph_pb2.SignatureDef()
input_signature = signatures.named_signatures[
signature_constants.PREDICT_INPUTS]
output_signature = signatures.named_signatures[
signature_constants.PREDICT_OUTPUTS]
# TODO(pdudnik): what if there are other signatures? Mimic cr/140900781 once
# it is submitted.
if (input_signature.WhichOneof("type") != "generic_signature" or
output_signature.WhichOneof("type") != "generic_signature"):
raise RuntimeError("Named input and output signatures can only be "
"up-converted if they are generic signature. "
"Input signature type is %s, output signature type is "
"%s" % (input_signature.WhichOneof("type"),
output_signature.WhichOneof("type")))
signature_def.method_name = signature_constants.PREDICT_METHOD_NAME
for key, val in input_signature.generic_signature.map.items():
_add_input_to_signature_def(val.tensor_name, key, signature_def)
for key, val in output_signature.generic_signature.map.items():
_add_output_to_signature_def(val.tensor_name, key, signature_def)
return signature_def
示例27
def _convert_signatures_to_signature_defs(metagraph_def):
"""Produce default and named upconverted SignatureDef objects from Signatures.
Args:
metagraph_def: object of type meta_graph_pb2.MetaGraphDef containing legacy
format Session Bundle signatures
Returns:
default_signature_def: object of type SignatureDef which contains an
upconverted version of default signatures in metagraph_def
named_signature_def: object of type SignatureDef which contains an
upconverted version of named signatures in metagraph_def
"""
collection_def = metagraph_def.collection_def
signatures_proto = manifest_pb2.Signatures()
signatures = collection_def[legacy_constants.SIGNATURES_KEY].any_list.value[0]
signatures.Unpack(signatures_proto)
default_signature_def = None
named_signature_def = None
if signatures_proto.HasField("default_signature"):
default_signature_def = _convert_default_signature_to_signature_def(
signatures_proto)
if len(signatures_proto.named_signatures) > 1:
named_signature_def = _convert_named_signatures_to_signature_def(
signatures_proto)
return default_signature_def, named_signature_def
示例28
def _convert_default_signature_to_signature_def(signatures):
"""Convert default signature to object of type SignatureDef.
Args:
signatures: object of type manifest_pb2.Signatures()
Returns:
object of type SignatureDef which contains a converted version of default
signature from input signatures object
Returns None if signature is of generic type because it cannot be converted
to SignatureDef.
"""
default_signature = signatures.default_signature
signature_def = meta_graph_pb2.SignatureDef()
if default_signature.WhichOneof("type") == "regression_signature":
regression_signature = default_signature.regression_signature
signature_def.method_name = signature_constants.REGRESS_METHOD_NAME
_add_input_to_signature_def(regression_signature.input.tensor_name,
signature_constants.REGRESS_INPUTS,
signature_def)
_add_output_to_signature_def(regression_signature.output.tensor_name,
signature_constants.REGRESS_OUTPUTS,
signature_def)
elif default_signature.WhichOneof("type") == "classification_signature":
classification_signature = default_signature.classification_signature
signature_def.method_name = signature_constants.CLASSIFY_METHOD_NAME
_add_input_to_signature_def(classification_signature.input.tensor_name,
signature_constants.CLASSIFY_INPUTS,
signature_def)
_add_output_to_signature_def(classification_signature.classes.tensor_name,
signature_constants.CLASSIFY_OUTPUT_CLASSES,
signature_def)
_add_output_to_signature_def(classification_signature.scores.tensor_name,
signature_constants.CLASSIFY_OUTPUT_SCORES,
signature_def)
else:
logging.error("Only classification and regression default signatures "
"are supported for up-conversion. %s is not "
"supported" % default_signature.WhichOneof("type"))
return None
return signature_def
示例29
def _load_saved_model_from_session_bundle_path(export_dir, target, config):
"""Load legacy TF Exporter/SessionBundle checkpoint.
Args:
export_dir: the directory that contains files exported by exporter.
target: The execution engine to connect to. See target in tf.Session()
config: A ConfigProto proto with configuration options. See config in
tf.Session()
Returns:
session: a tensorflow session created from the variable files.
metagraph_def: The `MetaGraphDef` protocol buffer loaded in the provided
session. This can be used to further extract signature-defs,
collection-defs, etc.
This model is up-converted to SavedModel format. Specifically, metagraph_def
SignatureDef field is populated with Signatures converted from legacy
signatures contained within CollectionDef
Raises:
RuntimeError: If metagraph already contains signature_def and cannot be
up-converted.
"""
meta_graph_filename = os.path.join(export_dir,
legacy_constants.META_GRAPH_DEF_FILENAME)
metagraph_def = meta_graph.read_meta_graph_file(meta_graph_filename)
if metagraph_def.signature_def:
raise RuntimeError("Legacy graph contains signature def, unable to "
"up-convert.")
# Add SignatureDef to metagraph.
default_signature_def, named_signature_def = (
_convert_signatures_to_signature_defs(metagraph_def))
if default_signature_def:
metagraph_def.signature_def[
signature_constants.DEFAULT_SERVING_SIGNATURE_DEF_KEY].CopyFrom(
default_signature_def)
if named_signature_def:
signature_def_key = signature_constants.DEFAULT_SERVING_SIGNATURE_DEF_KEY
if default_signature_def:
signature_def_key += "_from_named"
metagraph_def.signature_def[signature_def_key].CopyFrom(named_signature_def)
# We cannot just output session we loaded with older metagraph_def and
# up-converted metagraph definition because Session has an internal object of
# type Graph which is populated from meta_graph_def. If we do not create
# session with our new meta_graph_def, then Graph will be out of sync with
# meta_graph_def.
sess, metagraph_def = session_bundle.load_session_bundle_from_path(
export_dir, target, config, meta_graph_def=metagraph_def)
return sess, metagraph_def
示例30
def testAddInputToSignatureDef(self):
signature_def = meta_graph_pb2.SignatureDef()
signature_def_compare = meta_graph_pb2.SignatureDef()
# Add input to signature-def corresponding to `foo_key`.
bundle_shim._add_input_to_signature_def("foo-name", "foo-key",
signature_def)
self.assertEqual(len(signature_def.inputs), 1)
self.assertEqual(len(signature_def.outputs), 0)
self.assertProtoEquals(
signature_def.inputs["foo-key"],
meta_graph_pb2.TensorInfo(name="foo-name"))
# Attempt to add another input to the signature-def with the same tensor
# name and key.
bundle_shim._add_input_to_signature_def("foo-name", "foo-key",
signature_def)
self.assertEqual(len(signature_def.inputs), 1)
self.assertEqual(len(signature_def.outputs), 0)
self.assertProtoEquals(
signature_def.inputs["foo-key"],
meta_graph_pb2.TensorInfo(name="foo-name"))
# Add another input to the signature-def corresponding to `bar-key`.
bundle_shim._add_input_to_signature_def("bar-name", "bar-key",
signature_def)
self.assertEqual(len(signature_def.inputs), 2)
self.assertEqual(len(signature_def.outputs), 0)
self.assertProtoEquals(
signature_def.inputs["bar-key"],
meta_graph_pb2.TensorInfo(name="bar-name"))
# Add an input to the signature-def corresponding to `foo-key` with an
# updated tensor name.
bundle_shim._add_input_to_signature_def("bar-name", "foo-key",
signature_def)
self.assertEqual(len(signature_def.inputs), 2)
self.assertEqual(len(signature_def.outputs), 0)
self.assertProtoEquals(
signature_def.inputs["foo-key"],
meta_graph_pb2.TensorInfo(name="bar-name"))
# Test that there are no other side-effects.
del signature_def.inputs["foo-key"]
del signature_def.inputs["bar-key"]
self.assertProtoEquals(signature_def, signature_def_compare)
