def test_multi_input_node(self):
# test multi-input layer
a = DummyTensor()
b = DummyTensor()
dense = DummyLayer()
a_2 = DummyTensor()
node_module.Node(layer=dense, call_args=(a, ), outputs=a_2)
b_2 = DummyTensor()
node_module.Node(layer=dense, call_args=(b, ), outputs=b_2)
concat_layer = DummyLayer()
merged = DummyTensor()
node_module.Node(layer=concat_layer,
call_args=([a_2, b_2], ),
outputs=merged)
merge_layer, merge_node_index, merge_tensor_index = merged._keras_history
self.assertEqual(merge_node_index, 0)
self.assertEqual(merge_tensor_index, 0)
self.assertLen(merge_layer._inbound_nodes, 1)
self.assertLen(merge_layer._outbound_nodes, 0)
self.assertLen(merge_layer._inbound_nodes[0].input_tensors, 2)
self.assertEqual(merge_layer._inbound_nodes[0].input_tensors,
[a_2, b_2])
self.assertLen(merge_layer._inbound_nodes[0].inbound_layers, 2)
def test_arg_and_kwarg_mix(self):
input_layer = DummyLayer()
input_layer_2 = DummyLayer()
a = DummyTensor()
node_a = node_module.Node(layer=input_layer, outputs=a)
b = DummyTensor()
node_b = node_module.Node(layer=input_layer_2, outputs=b)
arg_2 = DummyTensor()
arg_3 = DummyTensor()
node_c = node_module.Node(layer=input_layer, outputs=arg_3)
kwarg_x = DummyTensor()
kwarg_y = DummyTensor()
node_d = node_module.Node(layer=input_layer, outputs=kwarg_y)
merge_layer = DummyLayer()
merged = DummyTensor()
node = node_module.Node(layer=merge_layer,
call_args=([a, b], arg_2, arg_3),
call_kwargs={
'x': kwarg_x,
'y': kwarg_y
},
outputs=merged)
merge_layer, merge_node_index, merge_tensor_index = merged._keras_history
# Check the saved call args/kwargs
self.assertEqual(([a, b], arg_2, arg_3), node.call_args)
self.assertEqual({'x': kwarg_x, 'y': kwarg_y}, node.call_kwargs)
# Only the inputs that were produced by input nodes should appear in
# keras_tensors
self.assertEqual({a, b, arg_3, kwarg_y}, set(node.keras_inputs))
self.assertEqual(set(node.parent_nodes),
{node_a, node_b, node_c, node_d})
# Check the layer wirings
self.assertEqual(merge_node_index, 0)
self.assertEqual(merge_tensor_index, 0)
self.assertLen(merge_layer._inbound_nodes, 1)
self.assertLen(merge_layer._outbound_nodes, 0)
self.assertLen(input_layer._outbound_nodes, 3)
self.assertLen(input_layer_2._outbound_nodes, 1)
# The 'backwards compatibility' attributes should only check the
# first call argument
self.assertLen(merge_layer._inbound_nodes[0].input_tensors, 2)
self.assertEqual(merge_layer._inbound_nodes[0].input_tensors, [a, b])
self.assertLen(merge_layer._inbound_nodes[0].inbound_layers, 2)
def test_chained_node_construction(self):
# test basics
a = DummyTensor(shape=(None, 32))
b = DummyTensor(shape=(None, 32))
a_layer = DummyLayer()
node = node_module.Node(a_layer, outputs=a)
self.assertEqual(node.outbound_layer, a_layer)
self.assertTrue(node.is_input)
self.assertListEqual(node.inbound_layers, [])
self.assertListEqual(node.input_tensors, [a])
self.assertListEqual(node.input_shapes, [(None, 32)])
self.assertListEqual(node.output_tensors, [a])
self.assertListEqual(node.output_shapes, [(None, 32)])
b_layer = DummyLayer()
node_module.Node(b_layer, outputs=b)
dense = DummyLayer()
a_2 = DummyTensor()
node_a = node_module.Node(layer=dense, call_args=(a, ), outputs=a_2)
b_2 = DummyTensor()
node_b = node_module.Node(layer=dense, call_args=(b, ), outputs=b_2)
# test the node attributes
self.assertFalse(node_a.is_input)
self.assertFalse(node_b.is_input)
self.assertEqual(node_a.call_args, (a, ))
self.assertEqual(node_a.call_kwargs, {})
self.assertEqual(node_a.outputs, a_2)
# Test the layer wiring
self.assertLen(dense._inbound_nodes, 2)
self.assertLen(dense._outbound_nodes, 0)
self.assertEqual(dense._inbound_nodes, [node_a, node_b])
self.assertEqual(dense._inbound_nodes[0].inbound_layers, a_layer)
self.assertEqual(dense._inbound_nodes[0].outbound_layer, dense)
self.assertEqual(dense._inbound_nodes[1].inbound_layers, b_layer)
self.assertEqual(dense._inbound_nodes[1].outbound_layer, dense)
self.assertIs(dense._inbound_nodes[0].input_tensors, a)
self.assertIs(dense._inbound_nodes[1].input_tensors, b)
def __init__(self, label=None, min_value=None, max_value=None, **kwargs):
if not label:
prefix = 'C'
name = prefix + '_' + str(backend.get_uid(prefix))
else:
name = label
dtype = backend.floatx()
super(ConstantLayer, self).__init__(dtype=dtype, name=name)
# backend.random_uniform_variable(shape=(20,), low=[0.]*20, high=[1.]*20)
self._c = self.add_weight(name=label,
shape=(1, len(min_value)),
initializer=K.initializers.RandomUniform(
minval=min_value, maxval=max_value),
trainable=True)
self.is_placeholder = False
self.built = True
self._batch_input_shape = (len(min_value), )
#self.batch_size = len(min_value)
#graph = backend.get_graph()
#with graph.as_default():
# fake_input_tensor = backend.constant(backend.get_value(self._c))
# Create an input node to add to self.outbound_node
# and set output_tensors' _keras_history.
fake_input_tensor = self._c
fake_input_tensor._keras_history = base_layer.KerasHistory(self, 0, 0)
fake_input_tensor._keras_mask = None
fake_input_tensor._ltn_doms = []
node_module.Node(self,
inbound_layers=[],
node_indices=[],
tensor_indices=[],
input_tensors=[fake_input_tensor],
output_tensors=[fake_input_tensor])
def __init__(self,
input_shape=None,
batch_size=None,
dtype=None,
input_tensor=None,
sparse=False,
name=None,
ragged=False,
**kwargs):
strategy = distribution_strategy_context.get_strategy()
if strategy and batch_size is not None and \
distributed_training_utils.global_batch_size_supported(strategy):
if batch_size % strategy.num_replicas_in_sync != 0:
raise ValueError(
'The `batch_size` argument value {} cannot be '
'divisible by number of replicas {}'.format(
batch_size, strategy.num_replicas_in_sync))
batch_size = batch_size // strategy.num_replicas_in_sync
if 'batch_input_shape' in kwargs:
batch_input_shape = kwargs.pop('batch_input_shape')
if input_shape and batch_input_shape:
raise ValueError('Only provide the input_shape OR '
'batch_input_shape argument to '
'InputLayer, not both at the same time.')
batch_size = batch_input_shape[0]
input_shape = batch_input_shape[1:]
if kwargs:
raise ValueError('Unrecognized keyword arguments:', kwargs.keys())
if not name:
prefix = 'input'
name = prefix + '_' + str(backend.get_uid(prefix))
if not dtype:
if input_tensor is None:
dtype = backend.floatx()
else:
dtype = backend.dtype(input_tensor)
elif input_tensor is not None and input_tensor.dtype != dtype:
raise ValueError(
'`input_tensor.dtype` differs from `dtype`: %s vs. %s' %
(input_tensor.dtype, dtype))
super(InputLayer, self).__init__(dtype=dtype, name=name)
self.built = True
self.sparse = sparse
self.batch_size = batch_size
self.supports_masking = True
if isinstance(input_shape, tensor_shape.TensorShape):
input_shape = tuple(input_shape.as_list())
elif isinstance(input_shape, int):
input_shape = (input_shape, )
if input_tensor is None:
if input_shape is not None:
batch_input_shape = (batch_size, ) + tuple(input_shape)
else:
batch_input_shape = None
graph = backend.get_graph()
with graph.as_default():
input_tensor = backend.placeholder(shape=batch_input_shape,
dtype=dtype,
name=self.name,
sparse=sparse,
ragged=ragged)
self.is_placeholder = True
self._batch_input_shape = batch_input_shape
else:
if not tf_utils.is_symbolic_tensor(input_tensor):
raise ValueError(
'You should not pass an EagerTensor to `Input`. '
'For example, instead of creating an '
'InputLayer, you should instantiate your model and '
'directly call it on your input.')
self.is_placeholder = False
self._batch_input_shape = tuple(input_tensor.shape.as_list())
# Create an input node to add to self.outbound_node
# and set output_tensors' _keras_history.
input_tensor._keras_history = base_layer.KerasHistory(self, 0, 0)
input_tensor._keras_mask = None
node_module.Node(self,
inbound_layers=[],
node_indices=[],
tensor_indices=[],
input_tensors=[input_tensor],
output_tensors=[input_tensor])
def __init__(self,
input_shape=None,
batch_size=None,
dtype=None,
input_tensor=None,
sparse=None,
name=None,
ragged=None,
type_spec=None,
**kwargs):
self._init_input_shape = input_shape
self._init_batch_size = batch_size
self._init_dtype = dtype
self._init_sparse = sparse
self._init_ragged = ragged
self._init_type_spec = type_spec
strategy = distribution_strategy_context.get_strategy()
if strategy and batch_size is not None and \
distributed_training_utils.global_batch_size_supported(strategy):
if batch_size % strategy.num_replicas_in_sync != 0:
raise ValueError(
'The `batch_size` argument ({}) must be divisible by '
'the number of replicas ({})'.format(
batch_size, strategy.num_replicas_in_sync))
batch_size = batch_size // strategy.num_replicas_in_sync
if 'batch_input_shape' in kwargs:
batch_input_shape = kwargs.pop('batch_input_shape')
if input_shape and batch_input_shape:
raise ValueError('Only provide the input_shape OR '
'batch_input_shape argument to '
'InputLayer, not both at the same time.')
batch_size = batch_input_shape[0]
input_shape = batch_input_shape[1:]
if kwargs:
raise ValueError('Unrecognized keyword arguments:', kwargs.keys())
if sparse and ragged:
raise ValueError(
'Cannot set both sparse and ragged to True in a Keras input.')
if not name:
prefix = 'input'
name = prefix + '_' + str(backend.get_uid(prefix))
if not dtype:
if input_tensor is None:
dtype = backend.floatx()
else:
dtype = backend.dtype(input_tensor)
elif input_tensor is not None and input_tensor.dtype != dtype:
raise ValueError(
'`input_tensor.dtype` differs from `dtype`: %s vs. %s' %
(input_tensor.dtype, dtype))
super(InputLayer, self).__init__(dtype=dtype, name=name)
self.built = True
self.sparse = True if sparse else False
self.ragged = True if ragged else False
self.batch_size = batch_size
self.supports_masking = True
if isinstance(input_shape, tensor_shape.TensorShape):
input_shape = tuple(input_shape.as_list())
elif isinstance(input_shape, int):
input_shape = (input_shape, )
if type_spec is not None:
args_that_must_be_none = [
('(input_)shape', self._init_input_shape),
('batch_size', self._init_batch_size),
('dtype', self._init_dtype),
('input_tensor', input_tensor),
('sparse', self._init_sparse),
('ragged', self._init_ragged),
]
for arg_name, arg in args_that_must_be_none:
_assert_other_arg_none(arg_name, arg)
if not keras_tensor.keras_tensors_enabled():
raise ValueError(
'Creating Keras inputs from a type_spec is only '
'supported when eager execution is enabled.')
input_tensor = keras_tensor.keras_tensor_from_type_spec(type_spec)
if isinstance(input_tensor, keras_tensor.SparseKerasTensor):
self.sparse = True
if isinstance(input_tensor, keras_tensor.RaggedKerasTensor):
self.ragged = True
self.is_placeholder = True
try:
self._batch_input_shape = tuple(input_tensor.shape.as_list())
except ValueError:
# If the shape cannot be represented as a tuple (e.g. unknown rank)
self._batch_input_shape = None
elif input_tensor is None:
if input_shape is not None:
batch_input_shape = (batch_size, ) + tuple(input_shape)
else:
batch_input_shape = None
graph = backend.get_graph()
with graph.as_default():
input_tensor = backend.placeholder(shape=batch_input_shape,
dtype=dtype,
name=self.name,
sparse=sparse,
ragged=ragged)
self.is_placeholder = True
self._batch_input_shape = batch_input_shape
else:
if keras_tensor.keras_tensors_enabled():
if not isinstance(input_tensor, keras_tensor.KerasTensor):
input_tensor = keras_tensor.keras_tensor_from_tensor(
input_tensor)
else:
if not tf_utils.is_symbolic_tensor(input_tensor):
raise ValueError(
'You should not pass an EagerTensor to `Input`. '
'For example, instead of creating an '
'InputLayer, you should instantiate your model and '
'directly call it on your input.')
self.is_placeholder = False
try:
self._batch_input_shape = tuple(input_tensor.shape.as_list())
except ValueError:
# If the shape cannot be represented as a tuple (e.g. unknown rank)
self._batch_input_shape = None
# Create an input node.
input_tensor._keras_mask = None
node_module.Node(layer=self, outputs=input_tensor)
# Store type spec
if isinstance(input_tensor, keras_tensor.KerasTensor) or (
tf_utils.is_extension_type(input_tensor)):
self._type_spec = input_tensor._type_spec # pylint: disable=protected-access
else:
self._type_spec = tensor_spec.TensorSpec(shape=input_tensor.shape,
dtype=input_tensor.dtype,
name=self.name)
def _init_graph_network(self, inputs, outputs, name=None, **kwargs):
generic_utils.validate_kwargs(
kwargs, {'trainable'},
'Functional models may only specify `name` and `trainable` keyword '
'arguments during initialization. Got an unexpected argument:')
# Normalize and set self.inputs, self.outputs.
if isinstance(inputs, list) and len(nest.flatten(inputs)) == 1:
inputs = inputs[0]
if isinstance(outputs, list) and len(nest.flatten(outputs)) == 1:
outputs = outputs[0]
self._nested_outputs = outputs
self._nested_inputs = inputs
self.inputs = nest.flatten(inputs)
self.outputs = nest.flatten(outputs)
if any(not hasattr(tensor, '_keras_history') for tensor in self.outputs):
base_layer_utils.create_keras_history(self._nested_outputs)
self._base_init(name=name, **kwargs)
self._validate_graph_inputs_and_outputs()
# A Network does not create weights of its own, thus it is already
# built.
self.built = True
self._compute_output_and_mask_jointly = True
self._is_graph_network = True
# `_expects_training_arg` is True since the `training` argument is always
# present in the signature of the `call` method of a graph network.
self._expects_training_arg = True
self._expects_mask_arg = True
# A graph network does not autocast inputs, as its layers will cast them
# instead.
self._autocast = False
self._input_layers = []
self._output_layers = []
self._input_coordinates = []
self._output_coordinates = []
self._supports_ragged_inputs = None
# This is for performance optimization when calling the Network on new
# inputs. Every time the Network is called on a set on input tensors,
# we compute the output tensors, output masks and output shapes in one pass,
# then cache them here. When any of these outputs is queried later, we
# retrieve it from there instead of recomputing it.
self._output_mask_cache = {}
self._output_tensor_cache = {}
self._output_shape_cache = {}
# Build self._output_layers:
for x in self.outputs:
layer, node_index, tensor_index = x._keras_history # pylint: disable=protected-access
self._output_layers.append(layer)
self._output_coordinates.append((layer, node_index, tensor_index))
# Build self._input_layers:
for x in self.inputs:
layer, node_index, tensor_index = x._keras_history # pylint: disable=protected-access
# It's supposed to be an input layer, so only one node
# and one tensor output.
assert node_index == 0
assert tensor_index == 0
self._input_layers.append(layer)
self._input_coordinates.append((layer, node_index, tensor_index))
# Keep track of the network's nodes and layers.
nodes, nodes_by_depth, layers, _ = _map_graph_network(
self.inputs, self.outputs)
self._network_nodes = nodes
self._nodes_by_depth = nodes_by_depth
self._layers = layers
self._layer_call_argspecs = {}
for layer in self._layers:
self._layer_call_argspecs[layer] = tf_inspect.getfullargspec(layer.call)
layer._attribute_sentinel.add_parent(self._attribute_sentinel)
self._track_layers(layers)
# Create the node linking internal inputs to internal outputs.
node_module.Node(
outbound_layer=self,
inbound_layers=[],
node_indices=[],
tensor_indices=[],
input_tensors=self._nested_inputs,
output_tensors=self._nested_outputs)
# Build self.input_names and self.output_names.
self._set_output_names()
self.input_names = []
self._feed_input_names = []
self._feed_inputs = []
self._feed_input_shapes = []
for layer in self._input_layers:
self.input_names.append(layer.name)
if layer.is_placeholder:
self._feed_input_names.append(layer.name)
# Use batch_input_shape here because non-eager composite tensors may not
# have a shape attribute that's meaningful (sparse, for instance, has
# a tensor that's non-constant and needs to be fed). This means that
# input layers that create placeholders will need to have the
# batch_input_shape attr to allow for input shape validation.
self._feed_input_shapes.append(layer._batch_input_shape)
self._feed_inputs.append(layer.input)
