def _get_concat_variable(name, shape, dtype, num_shards):
"""Get a sharded variable concatenated into one tensor."""
sharded_variable = _get_sharded_variable(name, shape, dtype, num_shards)
if len(sharded_variable) == 1:
return sharded_variable[0]
concat_name = name + "/concat"
concat_full_name = vs.get_variable_scope().name + "/" + concat_name + ":0"
for value in ops.get_collection(ops.GraphKeys.CONCATENATED_VARIABLES):
if value.name == concat_full_name:
return value
concat_variable = array_ops.concat(0, sharded_variable, name=concat_name)
ops.add_to_collection(ops.GraphKeys.CONCATENATED_VARIABLES,
concat_variable)
return concat_variable
python类get_variable_scope()的实例源码
def _get_concat_variable(name, shape, dtype, num_shards):
"""Get a sharded variable concatenated into one tensor."""
sharded_variable = _get_sharded_variable(name, shape, dtype, num_shards)
if len(sharded_variable) == 1:
return sharded_variable[0]
concat_name = name + "/concat"
concat_full_name = vs.get_variable_scope().name + "/" + concat_name + ":0"
for value in ops.get_collection(ops.GraphKeys.CONCATENATED_VARIABLES):
if value.name == concat_full_name:
return value
concat_variable = array_ops.concat(0, sharded_variable, name=concat_name)
ops.add_to_collection(ops.GraphKeys.CONCATENATED_VARIABLES,
concat_variable)
return concat_variable
def _get_concat_variable(name, shape, dtype, num_shards):
"""Get a sharded variable concatenated into one tensor."""
sharded_variable = _get_sharded_variable(name, shape, dtype, num_shards)
if len(sharded_variable) == 1:
return sharded_variable[0]
concat_name = name + "/concat"
concat_full_name = vs.get_variable_scope().name + "/" + concat_name + ":0"
for value in ops.get_collection(ops.GraphKeys.CONCATENATED_VARIABLES):
if value.name == concat_full_name:
return value
concat_variable = array_ops.concat(sharded_variable, 0, name=concat_name)
ops.add_to_collection(ops.GraphKeys.CONCATENATED_VARIABLES,
concat_variable)
return concat_variable
rnn_module.py 文件源码
项目：LSTM-CRF-For-Named-Entity-Recognition
作者: zpppy
项目源码
文件源码
阅读 24
收藏 0
点赞 0
评论 0
def _get_concat_variable(name, shape, dtype, num_shards):
"""Get a sharded variable concatenated into one tensor."""
sharded_variable = _get_sharded_variable(name, shape, dtype, num_shards)
if len(sharded_variable) == 1:
return sharded_variable[0]
concat_name = name + "/concat"
concat_full_name = vs.get_variable_scope().name + "/" + concat_name + ":0"
for value in ops.get_collection(ops.GraphKeys.CONCATENATED_VARIABLES):
if value.name == concat_full_name:
return value
concat_variable = array_ops.concat(sharded_variable, 0, name=concat_name)
ops.add_to_collection(ops.GraphKeys.CONCATENATED_VARIABLES,
concat_variable)
return concat_variable
def _get_concat_variable(name, shape, dtype, num_shards):
"""Get a sharded variable concatenated into one tensor."""
sharded_variable = _get_sharded_variable(name, shape, dtype, num_shards)
if len(sharded_variable) == 1:
return sharded_variable[0]
concat_name = name + "/concat"
concat_full_name = vs.get_variable_scope().name + "/" + concat_name + ":0"
for value in ops.get_collection(ops.GraphKeys.CONCATENATED_VARIABLES):
if value.name == concat_full_name:
return value
concat_variable = array_ops.concat(0, sharded_variable, name=concat_name)
ops.add_to_collection(ops.GraphKeys.CONCATENATED_VARIABLES,
concat_variable)
return concat_variable
def __call__(self, inputs, state, scope=None):
"""Run the cell on embedded inputs."""
with vs.variable_scope(scope or type(self).__name__): # "EmbeddingWrapper"
with ops.device("/cpu:0"):
if self._embedding:
embedding = self._embedding
else:
if self._initializer:
initializer = self._initializer
elif vs.get_variable_scope().initializer:
initializer = vs.get_variable_scope().initializer
else:
# Default initializer for embeddings should have variance=1.
sqrt3 = math.sqrt(3) # Uniform(-sqrt(3), sqrt(3)) has variance=1.
initializer = init_ops.random_uniform_initializer(-sqrt3, sqrt3)
embedding = vs.get_variable("embedding", [self._embedding_classes,
self._cell.input_size],
initializer=initializer)
embedded = embedding_ops.embedding_lookup(
embedding, array_ops.reshape(inputs, [-1]))
return self._cell(embedded, state)
def _get_concat_variable(name, shape, dtype, num_shards):
"""Get a sharded variable concatenated into one tensor."""
sharded_variable = _get_sharded_variable(name, shape, dtype, num_shards)
if len(sharded_variable) == 1:
return sharded_variable[0]
concat_name = name + "/concat"
concat_full_name = vs.get_variable_scope().name + "/" + concat_name + ":0"
for value in ops.get_collection(ops.GraphKeys.CONCATENATED_VARIABLES):
if value.name == concat_full_name:
return value
concat_variable = array_ops.concat(0, sharded_variable, name=concat_name)
ops.add_to_collection(ops.GraphKeys.CONCATENATED_VARIABLES,
concat_variable)
return concat_variable
grl_seq2seq.py 文件源码
项目：Deep-Reinforcement-Learning-for-Dialogue-Generation-in-tensorflow
作者: liuyuemaicha
项目源码
文件源码
阅读 28
收藏 0
点赞 0
评论 0
def rnn_decoder(decoder_inputs, initial_state, cell, loop_function=None,
scope=None):
with variable_scope.variable_scope(scope or "rnn_decoder"):
state = initial_state
outputs = []
prev = None
for i, inp in enumerate(decoder_inputs):
if loop_function is not None and prev is not None:
with variable_scope.variable_scope("loop_function", reuse=True):
inp = loop_function(prev, i)
if i > 0:
variable_scope.get_variable_scope().reuse_variables()
output, state = cell(inp, state)
outputs.append(output)
if loop_function is not None:
prev = output
return outputs, state
def _get_concat_variable(name, shape, dtype, num_shards):
"""Get a sharded variable concatenated into one tensor."""
sharded_variable = _get_sharded_variable(name, shape, dtype, num_shards)
if len(sharded_variable) == 1:
return sharded_variable[0]
concat_name = name + "/concat"
concat_full_name = vs.get_variable_scope().name + "/" + concat_name + ":0"
for value in ops.get_collection(ops.GraphKeys.CONCATENATED_VARIABLES):
if value.name == concat_full_name:
return value
concat_variable = array_ops.concat(0, sharded_variable, name=concat_name)
ops.add_to_collection(ops.GraphKeys.CONCATENATED_VARIABLES,
concat_variable)
return concat_variable
def __call__(self, inputs, state, scope=None):
"""Run the cell on embedded inputs."""
with vs.variable_scope(scope or type(self).__name__): # "EmbeddingWrapper"
with ops.device("/cpu:0"):
if self._initializer:
initializer = self._initializer
elif vs.get_variable_scope().initializer:
initializer = vs.get_variable_scope().initializer
else:
# Default initializer for embeddings should have variance=1.
sqrt3 = math.sqrt(3) # Uniform(-sqrt(3), sqrt(3)) has variance=1.
initializer = init_ops.random_uniform_initializer(-sqrt3, sqrt3)
if type(state) is tuple:
data_type = state[0].dtype
else:
data_type = state.dtype
embedding = vs.get_variable(
"embedding", [self._embedding_classes, self._embedding_size],
initializer=initializer,
dtype=data_type)
embedded = embedding_ops.embedding_lookup(
embedding, array_ops.reshape(inputs, [-1]))
return self._cell(embedded, state)
def _get_concat_variable(name, shape, dtype, num_shards):
"""Get a sharded variable concatenated into one tensor."""
sharded_variable = _get_sharded_variable(name, shape, dtype, num_shards)
if len(sharded_variable) == 1:
return sharded_variable[0]
concat_name = name + "/concat"
concat_full_name = vs.get_variable_scope().name + "/" + concat_name + ":0"
for value in ops.get_collection(ops.GraphKeys.CONCATENATED_VARIABLES):
if value.name == concat_full_name:
return value
concat_variable = array_ops.concat(0, sharded_variable, name=concat_name)
ops.add_to_collection(ops.GraphKeys.CONCATENATED_VARIABLES,
concat_variable)
return concat_variable
def __call__(self, inputs, state, scope=None):
"""Run the cell on embedded inputs."""
with vs.variable_scope(scope or type(self).__name__): # "EmbeddingWrapper"
with ops.device("/cpu:0"):
if self._initializer:
initializer = self._initializer
elif vs.get_variable_scope().initializer:
initializer = vs.get_variable_scope().initializer
else:
# Default initializer for embeddings should have variance=1.
sqrt3 = math.sqrt(3) # Uniform(-sqrt(3), sqrt(3)) has variance=1.
initializer = init_ops.random_uniform_initializer(-sqrt3, sqrt3)
if type(state) is tuple:
data_type = state[0].dtype
else:
data_type = state.dtype
embedding = vs.get_variable(
"embedding", [self._embedding_classes, self._embedding_size],
initializer=initializer,
dtype=data_type)
embedded = embedding_ops.embedding_lookup(
embedding, array_ops.reshape(inputs, [-1]))
return self._cell(embedded, state)
seq2seq.py 文件源码
项目：Variational-Recurrent-Autoencoder-Tensorflow
作者: Chung-I
项目源码
文件源码
阅读 24
收藏 0
点赞 0
评论 0
def variational_encoder_with_buckets(encoder_inputs, buckets, encoder,
enc_latent, softmax_loss_function=None,
per_example_loss=False, name=None):
"""Create a sequence-to-sequence model with support for bucketing.
"""
if len(encoder_inputs) < buckets[-1][0]:
raise ValueError("Length of encoder_inputs (%d) must be at least that of la"
"st bucket (%d)." % (len(encoder_inputs), buckets[-1][0]))
all_inputs = encoder_inputs
means = []
logvars = []
with ops.name_scope(name, "variational_encoder_with_buckets", all_inputs):
for j, bucket in enumerate(buckets):
with variable_scope.variable_scope(variable_scope.get_variable_scope(),
reuse=True if j > 0 else None):
encoder_last_state = encoder(encoder_inputs[:bucket[0]])
mean, logvar = enc_latent(encoder_last_state)
means.append(mean)
logvars.append(logvar)
return means, logvars
def __call__(self, inputs, state, scope=None):
"""Run this RNN cell on inputs, starting from the given state.
Args:
inputs: `2-D` tensor with shape `[batch_size x input_size]`.
state: if `self.state_size` is an integer, this should be a `2-D Tensor`
with shape `[batch_size x self.state_size]`. Otherwise, if
`self.state_size` is a tuple of integers, this should be a tuple
with shapes `[batch_size x s] for s in self.state_size`.
scope: VariableScope for the created subgraph; defaults to class name.
Returns:
A pair containing:
- Output: A `2-D` tensor with shape `[batch_size x self.output_size]`.
- New state: Either a single `2-D` tensor, or a tuple of tensors matching
the arity and shapes of `state`.
"""
if scope is not None:
with vs.variable_scope(scope,
custom_getter=self._rnn_get_variable) as scope:
return super(RNNCell, self).__call__(inputs, state, scope=scope)
else:
with vs.variable_scope(vs.get_variable_scope(),
custom_getter=self._rnn_get_variable):
return super(RNNCell, self).__call__(inputs, state)
def tied_rnn_seq2seq(encoder_inputs,
decoder_inputs,
cell,
loop_function=None,
dtype=dtypes.float32,
scope=None):
"""RNN sequence-to-sequence model with tied encoder and decoder parameters.
This model first runs an RNN to encode encoder_inputs into a state vector, and
then runs decoder, initialized with the last encoder state, on decoder_inputs.
Encoder and decoder use the same RNN cell and share parameters.
Args:
encoder_inputs: A list of 2D Tensors [batch_size x input_size].
decoder_inputs: A list of 2D Tensors [batch_size x input_size].
cell: core_rnn_cell.RNNCell defining the cell function and size.
loop_function: If not None, this function will be applied to i-th output
in order to generate i+1-th input, and decoder_inputs will be ignored,
except for the first element ("GO" symbol), see rnn_decoder for details.
dtype: The dtype of the initial state of the rnn cell (default: tf.float32).
scope: VariableScope for the created subgraph; default: "tied_rnn_seq2seq".
Returns:
A tuple of the form (outputs, state), where:
outputs: A list of the same length as decoder_inputs of 2D Tensors with
shape [batch_size x output_size] containing the generated outputs.
state: The state of each decoder cell in each time-step. This is a list
with length len(decoder_inputs) -- one item for each time-step.
It is a 2D Tensor of shape [batch_size x cell.state_size].
"""
with variable_scope.variable_scope("combined_tied_rnn_seq2seq"):
scope = scope or "tied_rnn_seq2seq"
_, enc_state = core_rnn.static_rnn(
cell, encoder_inputs, dtype=dtype, scope=scope)
variable_scope.get_variable_scope().reuse_variables()
return rnn_decoder(
decoder_inputs,
enc_state,
cell,
loop_function=loop_function,
scope=scope)
def tied_rnn_seq2seq(encoder_inputs,
decoder_inputs,
cell,
loop_function=None,
dtype=dtypes.float32,
scope=None):
"""RNN sequence-to-sequence model with tied encoder and decoder parameters.
This model first runs an RNN to encode encoder_inputs into a state vector, and
then runs decoder, initialized with the last encoder state, on decoder_inputs.
Encoder and decoder use the same RNN cell and share parameters.
Args:
encoder_inputs: A list of 2D Tensors [batch_size x input_size].
decoder_inputs: A list of 2D Tensors [batch_size x input_size].
cell: core_rnn_cell.RNNCell defining the cell function and size.
loop_function: If not None, this function will be applied to i-th output
in order to generate i+1-th input, and decoder_inputs will be ignored,
except for the first element ("GO" symbol), see rnn_decoder for details.
dtype: The dtype of the initial state of the rnn cell (default: tf.float32).
scope: VariableScope for the created subgraph; default: "tied_rnn_seq2seq".
Returns:
A tuple of the form (outputs, state), where:
outputs: A list of the same length as decoder_inputs of 2D Tensors with
shape [batch_size x output_size] containing the generated outputs.
state: The state of each decoder cell in each time-step. This is a list
with length len(decoder_inputs) -- one item for each time-step.
It is a 2D Tensor of shape [batch_size x cell.state_size].
"""
with variable_scope.variable_scope("combined_tied_rnn_seq2seq"):
scope = scope or "tied_rnn_seq2seq"
_, enc_state = core_rnn.static_rnn(
cell, encoder_inputs, dtype=dtype, scope=scope)
variable_scope.get_variable_scope().reuse_variables()
return rnn_decoder(
decoder_inputs,
enc_state,
cell,
loop_function=loop_function,
scope=scope)
def tied_rnn_seq2seq(encoder_inputs, decoder_inputs, cell,
loop_function=None, dtype=dtypes.float32, scope=None):
"""RNN sequence-to-sequence model with tied encoder and decoder parameters.
This model first runs an RNN to encode encoder_inputs into a state vector, and
then runs decoder, initialized with the last encoder state, on decoder_inputs.
Encoder and decoder use the same RNN cell and share parameters.
Args:
encoder_inputs: A list of 2D Tensors [batch_size x input_size].
decoder_inputs: A list of 2D Tensors [batch_size x input_size].
cell: rnn_cell.RNNCell defining the cell function and size.
loop_function: If not None, this function will be applied to i-th output
in order to generate i+1-th input, and decoder_inputs will be ignored,
except for the first element ("GO" symbol), see rnn_decoder for details.
dtype: The dtype of the initial state of the rnn cell (default: tf.float32).
scope: VariableScope for the created subgraph; default: "tied_rnn_seq2seq".
Returns:
A tuple of the form (outputs, state), where:
outputs: A list of the same length as decoder_inputs of 2D Tensors with
shape [batch_size x output_size] containing the generated outputs.
state: The state of each decoder cell in each time-step. This is a list
with length len(decoder_inputs) -- one item for each time-step.
It is a 2D Tensor of shape [batch_size x cell.state_size].
"""
with variable_scope.variable_scope("combined_tied_rnn_seq2seq"):
scope = scope or "tied_rnn_seq2seq"
_, enc_state = rnn.rnn(
cell, encoder_inputs, dtype=dtype, scope=scope)
variable_scope.get_variable_scope().reuse_variables()
return rnn_decoder(decoder_inputs, enc_state, cell,
loop_function=loop_function, scope=scope)
def rnn_decoder(decoder_inputs, initial_state, cell, scope=None):
"""RNN Decoder that creates training and sampling sub-graphs.
Args:
decoder_inputs: Inputs for decoder, list of tensors.
This is used only in training sub-graph.
initial_state: Initial state for the decoder.
cell: RNN cell to use for decoder.
scope: Scope to use, if None new will be produced.
Returns:
List of tensors for outputs and states for training and sampling sub-graphs.
"""
with vs.variable_scope(scope or "dnn_decoder"):
states, sampling_states = [initial_state], [initial_state]
outputs, sampling_outputs = [], []
with ops.name_scope("training", values=[decoder_inputs, initial_state]):
for i, inp in enumerate(decoder_inputs):
if i > 0:
vs.get_variable_scope().reuse_variables()
output, new_state = cell(inp, states[-1])
outputs.append(output)
states.append(new_state)
with ops.name_scope("sampling", values=[initial_state]):
for i, _ in enumerate(decoder_inputs):
if i == 0:
sampling_outputs.append(outputs[i])
sampling_states.append(states[i])
else:
sampling_output, sampling_state = cell(sampling_outputs[-1],
sampling_states[-1])
sampling_outputs.append(sampling_output)
sampling_states.append(sampling_state)
return outputs, states, sampling_outputs, sampling_states
def rnn_decoder(decoder_inputs, initial_state, cell, scope=None):
"""RNN Decoder that creates training and sampling sub-graphs.
Args:
decoder_inputs: Inputs for decoder, list of tensors.
This is used only in training sub-graph.
initial_state: Initial state for the decoder.
cell: RNN cell to use for decoder.
scope: Scope to use, if None new will be produced.
Returns:
List of tensors for outputs and states for training and sampling sub-graphs.
"""
with vs.variable_scope(scope or "dnn_decoder"):
states, sampling_states = [initial_state], [initial_state]
outputs, sampling_outputs = [], []
with ops.name_scope("training", values=[decoder_inputs, initial_state]):
for i, inp in enumerate(decoder_inputs):
if i > 0:
vs.get_variable_scope().reuse_variables()
output, new_state = cell(inp, states[-1])
outputs.append(output)
states.append(new_state)
with ops.name_scope("sampling", values=[initial_state]):
for i, _ in enumerate(decoder_inputs):
if i == 0:
sampling_outputs.append(outputs[i])
sampling_states.append(states[i])
else:
sampling_output, sampling_state = cell(sampling_outputs[-1],
sampling_states[-1])
sampling_outputs.append(sampling_output)
sampling_states.append(sampling_state)
return outputs, states, sampling_outputs, sampling_states
def tied_rnn_seq2seq(encoder_inputs, decoder_inputs, cell,
loop_function=None, dtype=dtypes.float32, scope=None):
"""RNN sequence-to-sequence model with tied encoder and decoder parameters.
This model first runs an RNN to encode encoder_inputs into a state vector, and
then runs decoder, initialized with the last encoder state, on decoder_inputs.
Encoder and decoder use the same RNN cell and share parameters.
Args:
encoder_inputs: A list of 2D Tensors [batch_size x input_size].
decoder_inputs: A list of 2D Tensors [batch_size x input_size].
cell: rnn_cell.RNNCell defining the cell function and size.
loop_function: If not None, this function will be applied to i-th output
in order to generate i+1-th input, and decoder_inputs will be ignored,
except for the first element ("GO" symbol), see rnn_decoder for details.
dtype: The dtype of the initial state of the rnn cell (default: tf.float32).
scope: VariableScope for the created subgraph; default: "tied_rnn_seq2seq".
Returns:
A tuple of the form (outputs, state), where:
outputs: A list of the same length as decoder_inputs of 2D Tensors with
shape [batch_size x output_size] containing the generated outputs.
state: The state of each decoder cell in each time-step. This is a list
with length len(decoder_inputs) -- one item for each time-step.
It is a 2D Tensor of shape [batch_size x cell.state_size].
"""
with variable_scope.variable_scope("combined_tied_rnn_seq2seq"):
scope = scope or "tied_rnn_seq2seq"
_, enc_state = rnn.rnn(
cell, encoder_inputs, dtype=dtype, scope=scope)
variable_scope.get_variable_scope().reuse_variables()
return rnn_decoder(decoder_inputs, enc_state, cell,
loop_function=loop_function, scope=scope)
def model_with_buckets(encoder_inputs, decoder_inputs, targets, weights, buckets, vocab_size, batch_size, seq2seq,
output_projection=None, softmax_loss_function=None, per_example_loss=False, name=None):
if len(encoder_inputs) < buckets[-1][0]:
raise ValueError("Length of encoder_inputs (%d) must be at least that of la"
"st bucket (%d)." % (len(encoder_inputs), buckets[-1][0]))
if len(targets) < buckets[-1][1]:
raise ValueError("Length of targets (%d) must be at least that of last"
"bucket (%d)." % (len(targets), buckets[-1][1]))
if len(weights) < buckets[-1][1]:
raise ValueError("Length of weights (%d) must be at least that of last"
"bucket (%d)." % (len(weights), buckets[-1][1]))
all_inputs = encoder_inputs + decoder_inputs + targets + weights
losses = []
outputs = []
encoder_states = []
with ops.name_scope(name, "model_with_buckets", all_inputs):
for j, bucket in enumerate(buckets):
with variable_scope.variable_scope(variable_scope.get_variable_scope(),
reuse=True if j > 0 else None):
bucket_outputs, decoder_states, encoder_state = seq2seq(encoder_inputs[:bucket[0]],
decoder_inputs[:bucket[1]])
outputs.append(bucket_outputs)
#print("bucket outputs: %s" %bucket_outputs)
encoder_states.append(encoder_state)
if per_example_loss:
losses.append(sequence_loss_by_example(
outputs[-1], targets[:bucket[1]], weights[:bucket[1]],
softmax_loss_function=softmax_loss_function))
else:
# losses.append(sequence_loss_by_mle(outputs[-1], targets[:bucket[1]], vocab_size, bucket[1], batch_size, output_projection))
losses.append(sequence_loss(outputs[-1], targets[:bucket[1]], weights[:bucket[1]], softmax_loss_function=softmax_loss_function))
return outputs, losses, encoder_states
def tied_rnn_seq2seq(encoder_inputs, decoder_inputs, cell,
loop_function=None, dtype=dtypes.float32, scope=None):
"""RNN sequence-to-sequence model with tied encoder and decoder parameters.
This model first runs an RNN to encode encoder_inputs into a state vector, and
then runs decoder, initialized with the last encoder state, on decoder_inputs.
Encoder and decoder use the same RNN cell and share parameters.
Args:
encoder_inputs: A list of 2D Tensors [batch_size x input_size].
decoder_inputs: A list of 2D Tensors [batch_size x input_size].
cell: rnn_cell.RNNCell defining the cell function and size.
loop_function: If not None, this function will be applied to i-th output
in order to generate i+1-th input, and decoder_inputs will be ignored,
except for the first element ("GO" symbol), see rnn_decoder for details.
dtype: The dtype of the initial state of the rnn cell (default: tf.float32).
scope: VariableScope for the created subgraph; default: "tied_rnn_seq2seq".
Returns:
A tuple of the form (outputs, state), where:
outputs: A list of the same length as decoder_inputs of 2D Tensors with
shape [batch_size x output_size] containing the generated outputs.
state: The state of each decoder cell in each time-step. This is a list
with length len(decoder_inputs) -- one item for each time-step.
It is a 2D Tensor of shape [batch_size x cell.state_size].
"""
with variable_scope.variable_scope("combined_tied_rnn_seq2seq"):
scope = scope or "tied_rnn_seq2seq"
_, enc_state = rnn.rnn(
cell, encoder_inputs, dtype=dtype, scope=scope)
variable_scope.get_variable_scope().reuse_variables()
return rnn_decoder(decoder_inputs, enc_state, cell,
loop_function=loop_function, scope=scope)
def embedding_rnn_seq2seq(encoder_inputs, decoder_inputs, cell,
num_encoder_symbols, num_decoder_symbols,
embedding_size, output_projection=None,
feed_previous=False, dtype=dtypes.float32,
scope=None):
with variable_scope.variable_scope(scope or "embedding_rnn_seq2seq"):
# Encoder.
encoder_cell = rnn_cell.EmbeddingWrapper(
cell, embedding_classes=num_encoder_symbols,
embedding_size=embedding_size)
_, encoder_state = rnn.rnn(encoder_cell, encoder_inputs, dtype=dtype)
# Decoder.
if output_projection is None:
cell = rnn_cell.OutputProjectionWrapper(cell, num_decoder_symbols)
if isinstance(feed_previous, bool):
return embedding_rnn_decoder(
decoder_inputs, encoder_state, cell, num_decoder_symbols,
embedding_size, output_projection=output_projection,
feed_previous=feed_previous)
# If feed_previous is a Tensor, we construct 2 graphs and use cond.
def decoder(feed_previous_bool):
reuse = None if feed_previous_bool else True
with variable_scope.variable_scope(variable_scope.get_variable_scope(),
reuse=reuse):
outputs, state = embedding_rnn_decoder(
decoder_inputs, encoder_state, cell, num_decoder_symbols,
embedding_size, output_projection=output_projection,
feed_previous=feed_previous_bool,
update_embedding_for_previous=False)
return outputs + [state]
outputs_and_state = control_flow_ops.cond(feed_previous,
lambda: decoder(True),
lambda: decoder(False))
return outputs_and_state[:-1], outputs_and_state[-1]
def model_with_buckets(encoder_inputs, decoder_inputs, targets, weights, seq_len,
buckets, seq2seq, softmax_loss_function=None,
per_example_loss=False, name=None):
if len(encoder_inputs) < buckets[-1][0]:
raise ValueError("Length of encoder_inputs (%d) must be at least that of la"
"st bucket (%d)." % (len(encoder_inputs), buckets[-1][0]))
if len(targets) < buckets[-1][1]:
raise ValueError("Length of targets (%d) must be at least that of last"
"bucket (%d)." % (len(targets), buckets[-1][1]))
if len(weights) < buckets[-1][1]:
raise ValueError("Length of weights (%d) must be at least that of last"
"bucket (%d)." % (len(weights), buckets[-1][1]))
all_inputs = encoder_inputs + decoder_inputs + targets + weights
losses = []
outputs = []
with tf.name_scope(name, "model_with_buckets", all_inputs):
for j, bucket in enumerate(buckets):
with variable_scope.variable_scope(variable_scope.get_variable_scope(),
reuse=True if j > 0 else None):
bucket_outputs, _ = seq2seq(encoder_inputs[:bucket[0]],
decoder_inputs[:bucket[1]],
seq_len)
outputs.append(bucket_outputs)
if per_example_loss:
losses.append(sequence_loss_by_example(
outputs[-1], targets[:bucket[1]], weights[:bucket[1]],
softmax_loss_function=softmax_loss_function))
else:
losses.append(sequence_loss(
outputs[-1], targets[:bucket[1]], weights[:bucket[1]],
softmax_loss_function=softmax_loss_function))
return outputs, losses
def many2one_model_with_buckets(encoder_inputs_list, decoder_inputs, targets, weights,
buckets, seq2seq, softmax_loss_function=None,
per_example_loss=False, name=None, spscale=20):
# Modified model with buckets to accept 2 encoders
if len(encoder_inputs_list[0]) < buckets[-1][0]:
raise ValueError("Length of encoder_inputs (%d) must be at least that of la"
"st bucket (%d)." % (len(encoder_inputs), buckets[-1][0]))
if len(targets) < buckets[-1][1]:
raise ValueError("Length of targets (%d) must be at least that of last"
"bucket (%d)." % (len(targets), buckets[-1][1]))
if len(weights) < buckets[-1][1]:
raise ValueError("Length of weights (%d) must be at least that of last"
"bucket (%d)." % (len(weights), buckets[-1][1]))
all_inputs = encoder_inputs_list + decoder_inputs + targets + weights
losses = []
outputs = []
speech_buckets = [(x*spscale, y) for (x,y) in buckets]
with ops.op_scope(all_inputs, name, "many2one_model_with_buckets"):
for j, bucket in enumerate(buckets):
with variable_scope.variable_scope(variable_scope.get_variable_scope(),
reuse=True if j > 0 else None):
#bucket_outputs, _ = seq2seq(encoder_inputs[:bucket[0]], decoder_inputs[:bucket[1]])
x = encoder_inputs_list[0][:bucket[0]]
#print( x )
y = encoder_inputs_list[1][:speech_buckets[j][0]]
bucket_outputs, _ = seq2seq([x, y], decoder_inputs[:bucket[1]])
outputs.append(bucket_outputs)
if per_example_loss:
losses.append(sequence_loss_by_example(
outputs[-1], targets[:bucket[1]], weights[:bucket[1]],
softmax_loss_function=softmax_loss_function))
else:
losses.append(sequence_loss(
outputs[-1], targets[:bucket[1]], weights[:bucket[1]],
softmax_loss_function=softmax_loss_function))
return outputs, losses
def embedding_rnn_seq2seq(encoder_inputs, decoder_inputs, cell,
num_encoder_symbols, num_decoder_symbols,
embedding_size, output_projection=None,
feed_previous=False, dtype=dtypes.float32,
scope=None):
"""Embedding RNN sequence-to-sequence model.
"""
with variable_scope.variable_scope(scope or "embedding_rnn_seq2seq"):
# Encoder.
encoder_cell = rnn_cell.EmbeddingWrapper(
cell, embedding_classes=num_encoder_symbols,
embedding_size=embedding_size)
_, encoder_state = rnn.rnn(encoder_cell, encoder_inputs, dtype=dtype)
# Decoder.
if output_projection is None:
cell = rnn_cell.OutputProjectionWrapper(cell, num_decoder_symbols)
if isinstance(feed_previous, bool):
return embedding_rnn_decoder(
decoder_inputs, encoder_state, cell, num_decoder_symbols,
embedding_size, output_projection=output_projection,
feed_previous=feed_previous)
# If feed_previous is a Tensor, we construct 2 graphs and use cond.
def decoder(feed_previous_bool):
reuse = None if feed_previous_bool else True
with variable_scope.variable_scope(variable_scope.get_variable_scope(),
reuse=reuse):
outputs, state = embedding_rnn_decoder(
decoder_inputs, encoder_state, cell, num_decoder_symbols,
embedding_size, output_projection=output_projection,
feed_previous=feed_previous_bool,
update_embedding_for_previous=False)
return outputs + [state]
outputs_and_state = control_flow_ops.cond(feed_previous,
lambda: decoder(True),
lambda: decoder(False))
return outputs_and_state[:-1], outputs_and_state[-1]
def many2one_model_with_buckets(encoder_inputs_list, decoder_inputs, targets, weights,
buckets, seq2seq, softmax_loss_function=None,
per_example_loss=False, name=None, spscale=20):
# Modified model with buckets to accept 2 encoders
if len(encoder_inputs_list[0]) < buckets[-1][0]:
raise ValueError("Length of encoder_inputs (%d) must be at least that of la"
"st bucket (%d)." % (len(encoder_inputs), buckets[-1][0]))
if len(targets) < buckets[-1][1]:
raise ValueError("Length of targets (%d) must be at least that of last"
"bucket (%d)." % (len(targets), buckets[-1][1]))
if len(weights) < buckets[-1][1]:
raise ValueError("Length of weights (%d) must be at least that of last"
"bucket (%d)." % (len(weights), buckets[-1][1]))
all_inputs = encoder_inputs_list + decoder_inputs + targets + weights
losses = []
outputs = []
speech_buckets = [(x*spscale, y) for (x,y) in buckets]
with ops.op_scope(all_inputs, name, "many2one_model_with_buckets"):
for j, bucket in enumerate(buckets):
with variable_scope.variable_scope(variable_scope.get_variable_scope(),
reuse=True if j > 0 else None):
#bucket_outputs, _ = seq2seq(encoder_inputs[:bucket[0]], decoder_inputs[:bucket[1]])
x = encoder_inputs_list[0][:bucket[0]]
#print( x )
y = encoder_inputs_list[1][:speech_buckets[j][0]]
bucket_outputs, _ = seq2seq([x, y], decoder_inputs[:bucket[1]])
outputs.append(bucket_outputs)
if per_example_loss:
losses.append(sequence_loss_by_example(
outputs[-1], targets[:bucket[1]], weights[:bucket[1]],
softmax_loss_function=softmax_loss_function))
else:
losses.append(sequence_loss(
outputs[-1], targets[:bucket[1]], weights[:bucket[1]],
softmax_loss_function=softmax_loss_function))
return outputs, losses
def embedding_rnn_seq2seq(encoder_inputs, decoder_inputs, cell,
num_encoder_symbols, num_decoder_symbols,
embedding_size, output_projection=None,
feed_previous=False, dtype=dtypes.float32,
scope=None):
"""Embedding RNN sequence-to-sequence model.
"""
with variable_scope.variable_scope(scope or "embedding_rnn_seq2seq"):
# Encoder.
encoder_cell = rnn_cell.EmbeddingWrapper(
cell, embedding_classes=num_encoder_symbols,
embedding_size=embedding_size)
_, encoder_state = rnn.rnn(encoder_cell, encoder_inputs, dtype=dtype)
# Decoder.
if output_projection is None:
cell = rnn_cell.OutputProjectionWrapper(cell, num_decoder_symbols)
if isinstance(feed_previous, bool):
return embedding_rnn_decoder(
decoder_inputs, encoder_state, cell, num_decoder_symbols,
embedding_size, output_projection=output_projection,
feed_previous=feed_previous)
# If feed_previous is a Tensor, we construct 2 graphs and use cond.
def decoder(feed_previous_bool):
reuse = None if feed_previous_bool else True
with variable_scope.variable_scope(variable_scope.get_variable_scope(),
reuse=reuse):
outputs, state = embedding_rnn_decoder(
decoder_inputs, encoder_state, cell, num_decoder_symbols,
embedding_size, output_projection=output_projection,
feed_previous=feed_previous_bool,
update_embedding_for_previous=False)
return outputs + [state]
outputs_and_state = control_flow_ops.cond(feed_previous,
lambda: decoder(True),
lambda: decoder(False))
return outputs_and_state[:-1], outputs_and_state[-1]
def embedding_rnn_seq2seq(encoder_inputs, decoder_inputs, cell,
num_encoder_symbols, num_decoder_symbols,
embedding_size, output_projection=None,
feed_previous=False, dtype=dtypes.float32,
scope=None):
"""Embedding RNN sequence-to-sequence model.
"""
with variable_scope.variable_scope(scope or "embedding_rnn_seq2seq"):
# Encoder.
encoder_cell = rnn_cell.EmbeddingWrapper(
cell, embedding_classes=num_encoder_symbols,
embedding_size=embedding_size)
_, encoder_state = rnn.rnn(encoder_cell, encoder_inputs, dtype=dtype)
# Decoder.
if output_projection is None:
cell = rnn_cell.OutputProjectionWrapper(cell, num_decoder_symbols)
if isinstance(feed_previous, bool):
return embedding_rnn_decoder(
decoder_inputs, encoder_state, cell, num_decoder_symbols,
embedding_size, output_projection=output_projection,
feed_previous=feed_previous)
# If feed_previous is a Tensor, we construct 2 graphs and use cond.
def decoder(feed_previous_bool):
reuse = None if feed_previous_bool else True
with variable_scope.variable_scope(variable_scope.get_variable_scope(),
reuse=reuse):
outputs, state = embedding_rnn_decoder(
decoder_inputs, encoder_state, cell, num_decoder_symbols,
embedding_size, output_projection=output_projection,
feed_previous=feed_previous_bool,
update_embedding_for_previous=False)
return outputs + [state]
outputs_and_state = control_flow_ops.cond(feed_previous,
lambda: decoder(True),
lambda: decoder(False))
return outputs_and_state[:-1], outputs_and_state[-1]
def embedding_rnn_seq2seq(encoder_inputs, decoder_inputs, cell,
num_encoder_symbols, num_decoder_symbols,
embedding_size, output_projection=None,
feed_previous=False, dtype=dtypes.float32,
scope=None):
with variable_scope.variable_scope(scope or "embedding_rnn_seq2seq"):
# Encoder.
encoder_cell = rnn_cell.EmbeddingWrapper(
cell, embedding_classes=num_encoder_symbols,
embedding_size=embedding_size)
_, encoder_state = rnn.rnn(encoder_cell, encoder_inputs, dtype=dtype)
# Decoder.
if output_projection is None:
cell = rnn_cell.OutputProjectionWrapper(cell, num_decoder_symbols)
if isinstance(feed_previous, bool):
return embedding_rnn_decoder(
decoder_inputs, encoder_state, cell, num_decoder_symbols,
embedding_size, output_projection=output_projection,
feed_previous=feed_previous)
# If feed_previous is a Tensor, we construct 2 graphs and use cond.
def decoder(feed_previous_bool):
reuse = None if feed_previous_bool else True
with variable_scope.variable_scope(variable_scope.get_variable_scope(),
reuse=reuse):
outputs, state = embedding_rnn_decoder(
decoder_inputs, encoder_state, cell, num_decoder_symbols,
embedding_size, output_projection=output_projection,
feed_previous=feed_previous_bool,
update_embedding_for_previous=False)
return outputs + [state]
outputs_and_state = control_flow_ops.cond(feed_previous,
lambda: decoder(True),
lambda: decoder(False))
return outputs_and_state[:-1], outputs_and_state[-1]
