def evaluate_frozen_graph(filename, input_arrays, output_arrays):
"""Returns a function that evaluates the frozen graph on input data.
Args:
filename: Full filepath of file containing frozen GraphDef.
input_arrays: List of input tensors to freeze graph with.
output_arrays: List of output tensors to freeze graph with.
Returns:
Lambda function ([np.ndarray data] : [np.ndarray result]).
"""
with _session.Session().as_default() as sess:
with _file_io.FileIO(filename, "rb") as f:
file_content = f.read()
graph_def = _graph_pb2.GraphDef()
graph_def.ParseFromString(file_content)
_import_graph_def(graph_def, name="")
inputs = _convert_saved_model.get_tensors_from_tensor_names(
sess.graph, input_arrays)
outputs = _convert_saved_model.get_tensors_from_tensor_names(
sess.graph, output_arrays)
return lambda input_data: sess.run(outputs, dict(zip(inputs, input_data)))
def evaluate_frozen_graph(filename, input_arrays, output_arrays):
"""Returns a function that evaluates the frozen graph on input data.
Args:
filename: Full filepath of file containing frozen GraphDef.
input_arrays: List of input tensors to freeze graph with.
output_arrays: List of output tensors to freeze graph with.
Returns:
Lambda function ([np.ndarray data] : [np.ndarray result]).
"""
with _session.Session().as_default() as sess:
with _file_io.FileIO(filename, "rb") as f:
file_content = f.read()
graph_def = _graph_pb2.GraphDef()
graph_def.ParseFromString(file_content)
_import_graph_def(graph_def, name="")
inputs = _convert_saved_model.get_tensors_from_tensor_names(
sess.graph, input_arrays)
outputs = _convert_saved_model.get_tensors_from_tensor_names(
sess.graph, output_arrays)
return lambda input_data: sess.run(outputs,
dict(zip(inputs, input_data)))
def testGetTensorsInvalid(self):
in_tensor = array_ops.placeholder(
shape=[1, 16, 16, 3], dtype=dtypes.float32)
_ = in_tensor + in_tensor
sess = session.Session()
with self.assertRaises(ValueError) as error:
convert_saved_model.get_tensors_from_tensor_names(sess.graph,
["invalid-input"])
self.assertEqual("Invalid tensors 'invalid-input' were found.",
str(error.exception))
def testGetTensorsInvalid(self):
in_tensor = array_ops.placeholder(shape=[1, 16, 16, 3],
dtype=dtypes.float32)
_ = in_tensor + in_tensor
sess = session.Session()
with self.assertRaises(ValueError) as error:
convert_saved_model.get_tensors_from_tensor_names(
sess.graph, ["invalid-input"])
self.assertEqual("Invalid tensors 'invalid-input' were found.",
str(error.exception))
def testGetTensorsValid(self):
in_tensor = array_ops.placeholder(
shape=[1, 16, 16, 3], dtype=dtypes.float32)
_ = in_tensor + in_tensor
sess = session.Session()
tensors = convert_saved_model.get_tensors_from_tensor_names(
sess.graph, ["Placeholder"])
self.assertEqual("Placeholder:0", tensors[0].name)
def testGetTensorsValid(self):
in_tensor = array_ops.placeholder(shape=[1, 16, 16, 3],
dtype=dtypes.float32)
_ = in_tensor + in_tensor
sess = session.Session()
tensors = convert_saved_model.get_tensors_from_tensor_names(
sess.graph, ["Placeholder"])
self.assertEqual("Placeholder:0", tensors[0].name)
def from_keras_model_file(cls,
model_file,
input_arrays=None,
input_shapes=None,
output_arrays=None):
"""Creates a TocoConverter class from a tf.keras model file.
Args:
model_file: Full filepath of HDF5 file containing the tf.keras model.
input_arrays: List of input tensors to freeze graph with. Uses input
arrays from SignatureDef when none are provided. (default None)
input_shapes: Dict of strings representing input tensor names to list of
integers representing input shapes (e.g., {"foo" : [1, 16, 16, 3]}).
Automatically determined when input shapes is None (e.g., {"foo" :
None}). (default None)
output_arrays: List of output tensors to freeze graph with. Uses output
arrays from SignatureDef when none are provided. (default None)
Returns:
TocoConverter class.
"""
_keras.backend.clear_session()
_keras.backend.set_learning_phase(False)
keras_model = _keras.models.load_model(model_file)
sess = _keras.backend.get_session()
# Get input and output tensors.
if input_arrays:
input_tensors = get_tensors_from_tensor_names(
sess.graph, input_arrays)
else:
input_tensors = keras_model.inputs
if output_arrays:
output_tensors = get_tensors_from_tensor_names(
sess.graph, output_arrays)
else:
output_tensors = keras_model.outputs
set_tensor_shapes(input_tensors, input_shapes)
graph_def = _freeze_graph(sess, output_tensors)
return cls(graph_def, input_tensors, output_tensors)
def from_keras_model_file(cls,
model_file,
input_arrays=None,
input_shapes=None,
output_arrays=None):
"""Creates a TocoConverter class from a tf.keras model file.
Args:
model_file: Full filepath of HDF5 file containing the tf.keras model.
input_arrays: List of input tensors to freeze graph with. Uses input
arrays from SignatureDef when none are provided. (default None)
input_shapes: Dict of strings representing input tensor names to list of
integers representing input shapes (e.g., {"foo" : [1, 16, 16, 3]}).
Automatically determined when input shapes is None (e.g., {"foo" :
None}). (default None)
output_arrays: List of output tensors to freeze graph with. Uses output
arrays from SignatureDef when none are provided. (default None)
Returns:
TocoConverter class.
"""
_keras.backend.clear_session()
_keras.backend.set_learning_phase(False)
keras_model = _keras.models.load_model(model_file)
sess = _keras.backend.get_session()
# Get input and output tensors.
if input_arrays:
input_tensors = get_tensors_from_tensor_names(sess.graph, input_arrays)
else:
input_tensors = keras_model.inputs
if output_arrays:
output_tensors = get_tensors_from_tensor_names(sess.graph, output_arrays)
else:
output_tensors = keras_model.outputs
set_tensor_shapes(input_tensors, input_shapes)
graph_def = _freeze_graph(sess, output_tensors)
return cls(graph_def, input_tensors, output_tensors)
def from_frozen_graph(cls,
graph_def_file,
input_arrays,
output_arrays,
input_shapes=None):
"""Creates a TocoConverter class from a file containing a frozen GraphDef.
Args:
graph_def_file: Full filepath of file containing TensorFlow GraphDef.
input_arrays: List of input tensors to freeze graph with.
output_arrays: List of output tensors to freeze graph with.
input_shapes: Dict of strings representing input tensor names to list of
integers representing input shapes (e.g., {"foo" : [1, 16, 16, 3]}).
Automatically determined when input shapes is None (e.g., {"foo" :
None}). (default None)
Returns:
TocoConverter class.
Raises:
ValueError:
Unable to parse input file.
The graph is not frozen.
input_arrays or output_arrays contains an invalid tensor name.
"""
with _session.Session() as sess:
sess.run(global_variables_initializer())
# Read GraphDef from file.
graph_def = _graph_pb2.GraphDef()
with open(graph_def_file, "rb") as f:
file_content = f.read()
try:
graph_def.ParseFromString(file_content)
except (_text_format.ParseError, DecodeError):
try:
print("Ignore 'tcmalloc: large alloc' warnings.")
if not isinstance(file_content, str):
if PY3:
file_content = file_content.decode('utf-8')
else:
file_content = file_content.encode('utf-8')
_text_format.Merge(file_content, graph_def)
except (_text_format.ParseError, DecodeError):
raise ValueError("Unable to parse input file '{}'.".format(
graph_def_file))
sess.graph.as_default()
import_graph_def(graph_def, name="")
# Get input and output tensors.
input_tensors = get_tensors_from_tensor_names(
sess.graph, input_arrays)
output_tensors = get_tensors_from_tensor_names(
sess.graph, output_arrays)
set_tensor_shapes(input_tensors, input_shapes)
# Check if graph is frozen.
if not _is_frozen_graph(sess):
raise ValueError(
"Please freeze the graph using freeze_graph.py")
# Create TocoConverter class.
return cls(sess.graph_def, input_tensors, output_tensors)
def from_frozen_graph(cls,
graph_def_file,
input_arrays,
output_arrays,
input_shapes=None):
"""Creates a TocoConverter class from a file containing a frozen GraphDef.
Args:
graph_def_file: Full filepath of file containing TensorFlow GraphDef.
input_arrays: List of input tensors to freeze graph with.
output_arrays: List of output tensors to freeze graph with.
input_shapes: Dict of strings representing input tensor names to list of
integers representing input shapes (e.g., {"foo" : [1, 16, 16, 3]}).
Automatically determined when input shapes is None (e.g., {"foo" :
None}). (default None)
Returns:
TocoConverter class.
Raises:
ValueError:
Unable to parse input file.
The graph is not frozen.
input_arrays or output_arrays contains an invalid tensor name.
"""
with _session.Session() as sess:
sess.run(global_variables_initializer())
# Read GraphDef from file.
graph_def = _graph_pb2.GraphDef()
with open(graph_def_file, "rb") as f:
file_content = f.read()
try:
graph_def.ParseFromString(file_content)
except (_text_format.ParseError, DecodeError):
try:
print("Ignore 'tcmalloc: large alloc' warnings.")
if not isinstance(file_content, str):
if PY3:
file_content = file_content.decode('utf-8')
else:
file_content = file_content.encode('utf-8')
_text_format.Merge(file_content, graph_def)
except (_text_format.ParseError, DecodeError):
raise ValueError(
"Unable to parse input file '{}'.".format(graph_def_file))
sess.graph.as_default()
import_graph_def(graph_def, name="")
# Get input and output tensors.
input_tensors = get_tensors_from_tensor_names(sess.graph, input_arrays)
output_tensors = get_tensors_from_tensor_names(sess.graph, output_arrays)
set_tensor_shapes(input_tensors, input_shapes)
# Check if graph is frozen.
if not _is_frozen_graph(sess):
raise ValueError("Please freeze the graph using freeze_graph.py.")
# Create TocoConverter class.
return cls(sess.graph_def, input_tensors, output_tensors)
