def _clone_sequential_model(model, input_tensors=None):
"""Clone a `Sequential` model instance.
Model cloning is similar to calling a model on new inputs,
except that it creates new layers (and thus new weights) instead
of sharing the weights of the existing layers.
Arguments:
model: Instance of `Sequential`.
input_tensors: optional list of input tensors
to build the model upon. If not provided,
placeholders will be created.
Returns:
An instance of `Sequential` reproducing the behavior
of the original model, on top of new inputs tensors,
using newly instantiated weights.
Raises:
ValueError: in case of invalid `model` argument value.
"""
if not isinstance(model, Sequential):
raise ValueError(
'Expected `model` argument '
'to be a `Sequential` model instance, '
'but got:', model)
def clone(layer):
return layer.__class__.from_config(layer.get_config())
layers = [clone(layer) for layer in model.layers]
if input_tensors is None:
return Sequential(layers=layers, name=model.name)
else:
if len(generic_utils.to_list(input_tensors)) != 1:
raise ValueError('To clone a `Sequential` model, we expect '
' at most one tensor '
'as part of `input_tensors`.')
x = generic_utils.to_list(input_tensors)[0]
if K.is_keras_tensor(x):
origin_layer = x._keras_history[0]
if isinstance(origin_layer, InputLayer):
return Sequential(layers=[origin_layer] + layers,
name=model.name)
else:
raise ValueError('Cannot clone a `Sequential` model on top '
'of a tensor that comes from a Keras layer '
'other than an `InputLayer`. '
'Use the functional API instead.')
input_tensor = Input(tensor=x, name='input_wrapper_for_' + str(x.name))
input_layer = input_tensor._keras_history[0]
return Sequential(layers=[input_layer] + layers, name=model.name)
def build(self, input_shape=None):
if input_shape and not self.inputs:
batch_shape = tuple(input_shape)
dtype = K.floatx()
x = Input(
batch_shape=batch_shape, dtype=dtype, name=self.name + '_input')
self.inputs = [x]
for layer in self._layers:
x = layer(x)
self.outputs = [x]
if self.inputs:
self._init_graph_network(self.inputs, self.outputs, name=self.name)
self.built = True
def _clone_functional_model(model, input_tensors=None):
"""Clone a functional `Model` instance.
Model cloning is similar to calling a model on new inputs,
except that it creates new layers (and thus new weights) instead
of sharing the weights of the existing layers.
Arguments:
model: Instance of `Model`.
input_tensors: optional list of input tensors
to build the model upon. If not provided,
placeholders will be created.
Returns:
An instance of `Model` reproducing the behavior
of the original model, on top of new inputs tensors,
using newly instantiated weights.
Raises:
ValueError: in case of invalid `model` argument value.
"""
if not isinstance(model, Model):
raise ValueError(
'Expected `model` argument '
'to be a `Model` instance, got ', model)
if isinstance(model, Sequential):
raise ValueError(
'Expected `model` argument '
'to be a functional `Model` instance, '
'got a `Sequential` instance instead:', model)
layer_map = {} # Cache for created layers.
tensor_map = {} # Map {reference_tensor: (corresponding_tensor, mask)}
if input_tensors is None:
# Create placeholders to build the model on top of.
input_layers = []
input_tensors = []
for layer in model._input_layers:
input_tensor = Input(batch_shape=layer._batch_input_shape,
dtype=layer.dtype,
sparse=layer.sparse,
name=layer.name)
input_tensors.append(input_tensor)
# Cache newly created input layer.
newly_created_input_layer = input_tensor._keras_history[0]
layer_map[layer] = newly_created_input_layer
for original_input_layer, cloned_input_layer in zip(
model._input_layers, input_layers):
layer_map[original_input_layer] = cloned_input_layer
else:
# Make sure that all input tensors come from a Keras layer.
# If tensor comes from an input layer: cache the input layer.
input_tensors = generic_utils.to_list(input_tensors)
input_tensors_ = []
for i, x in enumerate(input_tensors):
if not K.is_keras_tensor(x):
name = model._input_layers[i].name
input_tensor = Input(tensor=x,
name='input_wrapper_for_' + name)
input_tensors_.append(input_tensor)
# Cache newly created input layer.
original_input_layer = x._keras_history[0]
newly_created_input_layer = input_tensor._keras_history[0]
layer_map[original_input_layer] = newly_created_input_layer
else:
input_tensors_.append(x)
input_tensors = input_tensors_
for x, y in zip(model.inputs, input_tensors):
tensor_map[x] = (y, None) # tensor, mask
# Iterated over every node in the reference model, in depth order.
depth_keys = list(model._nodes_by_depth.keys())
depth_keys.sort(reverse=True)
for depth in depth_keys:
nodes = model._nodes_by_depth[depth]
for node in nodes:
# Recover the corresponding layer.
layer = node.outbound_layer
# Get or create layer.
if layer not in layer_map:
# Clone layer.
new_layer = layer.__class__.from_config(layer.get_config())
layer_map[layer] = new_layer
layer = new_layer
else:
# Reuse previously cloned layer.
layer = layer_map[layer]
# Don't call InputLayer multiple times.
if isinstance(layer, InputLayer):
continue
# Gather inputs to call the new layer.
referenceinput_tensors_ = node.input_tensors
reference_output_tensors = node.output_tensors
# If all previous input tensors are available in tensor_map,
# then call node.inbound_layer on them.
computed_data = [] # List of tuples (input, mask).
for x in referenceinput_tensors_:
if x in tensor_map:
computed_data.append(tensor_map[x])
if len(computed_data) == len(referenceinput_tensors_):
# Call layer.
if node.arguments:
kwargs = node.arguments
else:
kwargs = {}
if len(computed_data) == 1:
computed_tensor, computed_mask = computed_data[0]
if has_arg(layer.call, 'mask'):
if 'mask' not in kwargs:
kwargs['mask'] = computed_mask
output_tensors = generic_utils.to_list(
layer(computed_tensor, **kwargs))
output_masks = generic_utils.to_list(
layer.compute_mask(computed_tensor, computed_mask))
computed_tensors = [computed_tensor]
computed_masks = [computed_mask]
else:
computed_tensors = [x[0] for x in computed_data]
computed_masks = [x[1] for x in computed_data]
if has_arg(layer.call, 'mask'):
if 'mask' not in kwargs:
kwargs['mask'] = computed_masks
output_tensors = generic_utils.to_list(
layer(computed_tensors, **kwargs))
output_masks = generic_utils.to_list(
layer.compute_mask(computed_tensors, computed_masks))
# Update tensor_map.
for x, y, mask in zip(reference_output_tensors, output_tensors,
output_masks):
tensor_map[x] = (y, mask)
# Check that we did compute the model outputs,
# then instantiate a new model from inputs and outputs.
output_tensors = []
for x in model.outputs:
assert x in tensor_map, 'Could not compute output ' + str(x)
tensor, _ = tensor_map[x]
output_tensors.append(tensor)
return Model(input_tensors, output_tensors, name=model.name)
def add(self, layer):
"""Adds a layer instance on top of the layer stack.
Arguments:
layer: layer instance.
Raises:
TypeError: If `layer` is not a layer instance.
ValueError: In case the `layer` argument does not
know its input shape.
ValueError: In case the `layer` argument has
multiple output tensors, or is already connected
somewhere else (forbidden in `Sequential` models).
"""
if not isinstance(layer, (base_layer.Layer, base_layer.TFBaseLayer)):
raise TypeError('The added layer must be '
'an instance of class Layer. '
'Found: ' + str(layer))
if not self.outputs:
# First layer in model: check that it is an input layer.
if not isinstance(layer, InputLayer):
# Create an input layer.
# First, we need to infer its expected input shape and dtype.
if isinstance(layer, (Model, Sequential)):
# We were passed a model as first layer.
# This requires a specific way to figure out the
# input shape and dtype.
if not layer.layers:
raise ValueError('Cannot add an empty model '
'to a `Sequential` model.')
# In case of nested models: recover the first layer
# of the deepest model to infer input shape and dtype.
first_layer = layer.layers[0]
while isinstance(first_layer, (Model, Sequential)):
first_layer = first_layer.layers[0]
batch_shape = first_layer._batch_input_shape
dtype = first_layer.dtype
else:
# We were passed a regular layer, and it should
# know about its input shape. Otherwise, that's an error.
if not hasattr(layer, '_batch_input_shape'):
raise ValueError('The first layer in a '
'Sequential model must '
'get an `input_shape` argument.')
batch_shape = layer._batch_input_shape
dtype = layer.dtype
# Instantiate the input layer.
x = Input(batch_shape=batch_shape,
dtype=dtype,
name=layer.name + '_input')
# This will build the current layer
# and create the node connecting the current layer
# to the input layer we just created.
layer(x)
if len(layer._inbound_nodes[-1].output_tensors) != 1:
raise ValueError('All layers in a Sequential model '
'should have a single output tensor. '
'For multi-output layers, '
'use the functional API.')
self.outputs = [layer._inbound_nodes[-1].output_tensors[0]]
self.inputs = network.get_source_inputs(self.outputs[0])
# We create an input node, which we will keep updated
# as we add more layers
base_layer.Node(outbound_layer=self,
inbound_layers=[],
node_indices=[],
tensor_indices=[],
input_tensors=self.inputs,
output_tensors=self.outputs)
else:
output_tensor = layer(self.outputs[0])
if isinstance(output_tensor, list):
raise TypeError('All layers in a Sequential model '
'should have a single output tensor. '
'For multi-output layers, '
'use the functional API.')
self.outputs = [output_tensor]
# update self._inbound_nodes
self._inbound_nodes[0].output_tensors = self.outputs
self._inbound_nodes[0].output_shapes = [
K.int_shape(self.outputs[0])
]
self._layers.append(layer)
self.built = False
def add(self, layer):
"""Adds a layer instance on top of the layer stack.
Arguments:
layer: layer instance.
Raises:
TypeError: If `layer` is not a layer instance.
ValueError: In case the `layer` argument does not
know its input shape.
ValueError: In case the `layer` argument has
multiple output tensors, or is already connected
somewhere else (forbidden in `Sequential` models).
"""
if not isinstance(layer, base_layer.Layer):
raise TypeError('The added layer must be '
'an instance of class Layer. '
'Found: ' + str(layer))
self.built = False
if not self._layers:
set_inputs = False
# First layer in model: check that it is an input layer.
if not isinstance(layer, InputLayer):
# Create an input tensor and call `layer` on the input tensor.
# First, we need to infer the expected input shape and dtype.
first_layer = layer
if isinstance(layer, (Model, Sequential)):
# We were passed a model as first layer.
# This requires a specific way to figure out the
# input shape and dtype.
if not layer.layers:
raise ValueError('Cannot add an empty model '
'to a `Sequential` model.')
# In case of nested models: recover the first layer
# of the deepest model to infer input shape and dtype.
first_layer = layer.layers[0]
while isinstance(first_layer, (Model, Sequential)):
first_layer = first_layer.layers[0]
batch_shape = first_layer._batch_input_shape
dtype = first_layer.dtype
if hasattr(first_layer, '_batch_input_shape'):
batch_shape = first_layer._batch_input_shape
dtype = first_layer.dtype
# Instantiate the input layer.
x = Input(batch_shape=batch_shape,
dtype=dtype,
name=layer.name + '_input')
# This will build the current layer
# and create the node connecting the current layer
# to the input layer we just created.
layer(x)
set_inputs = True
else:
# The layer doesn't know about its expected shape. We will have to
# build the model lazily on `fit`/etc.
batch_shape = None
else:
# Corner case where the user passes an InputLayer layer via `add`.
assert len(layer._inbound_nodes[-1].output_tensors) == 1
set_inputs = True
if set_inputs:
if len(layer._inbound_nodes[-1].output_tensors) != 1:
raise ValueError('All layers in a Sequential model '
'should have a single output tensor. '
'For multi-output layers, '
'use the functional API.')
self.outputs = [layer._inbound_nodes[-1].output_tensors[0]]
self.inputs = network.get_source_inputs(self.outputs[0])
elif self.outputs:
output_tensor = layer(self.outputs[0])
if isinstance(output_tensor, list):
raise TypeError('All layers in a Sequential model '
'should have a single output tensor. '
'For multi-output layers, '
'use the functional API.')
self.outputs = [output_tensor]
if self.inputs:
self.build()
else:
self._layers.append(layer)