def _log_variable(variable):
if isinstance(variable, list):
for var in variable:
if fc._is_variable(variable): # pylint: disable=protected-access
logging.info('Created variable %s, with device=%s', var.name,
var.device)
elif fc._is_variable(variable): # pylint: disable=protected-access
logging.info('Created variable %s, with device=%s', variable.name,
variable.device)
def _log_variable(variable):
if isinstance(variable, list):
for var in variable:
if fc._is_variable(variable): # pylint: disable=protected-access
logging.info('Created variable %s, with device=%s', var.name,
var.device)
elif fc._is_variable(variable): # pylint: disable=protected-access
logging.info('Created variable %s, with device=%s', variable.name,
variable.device)
def _create_joint_embedding_lookup(columns_to_tensors,
embedding_lookup_arguments,
num_outputs,
trainable,
weight_collections):
"""Creates an embedding lookup for all columns sharing a single weight."""
for arg in embedding_lookup_arguments:
assert arg.weight_tensor is None, (
'Joint sums for weighted sparse columns are not supported. '
'Please use weighted_sum_from_feature_columns instead.')
assert arg.combiner == 'sum', (
'Combiners other than sum are not supported for joint sums. '
'Please use weighted_sum_from_feature_columns instead.')
assert len(embedding_lookup_arguments) >= 1, (
'At least one column must be in the model.')
prev_size = 0
sparse_tensors = []
for a in embedding_lookup_arguments:
t = a.input_tensor
values = t.values + prev_size
prev_size += a.vocab_size
sparse_tensors.append(
sparse_tensor_py.SparseTensor(t.indices,
values,
t.dense_shape))
sparse_tensor = sparse_ops.sparse_concat(1, sparse_tensors)
with variable_scope.variable_scope(
None, default_name='linear_weights', values=columns_to_tensors.values()):
variable = contrib_variables.model_variable(
name='weights',
shape=[prev_size, num_outputs],
dtype=dtypes.float32,
initializer=init_ops.zeros_initializer(),
trainable=trainable,
collections=weight_collections)
if fc._is_variable(variable): # pylint: disable=protected-access
variable = [variable]
else:
variable = variable._get_variable_list() # pylint: disable=protected-access
predictions = embedding_ops.safe_embedding_lookup_sparse(
variable,
sparse_tensor,
sparse_weights=None,
combiner='sum',
name='_weights')
return variable, predictions
def _create_joint_embedding_lookup(columns_to_tensors,
embedding_lookup_arguments,
num_outputs,
trainable,
weight_collections):
"""Creates an embedding lookup for all columns sharing a single weight."""
for arg in embedding_lookup_arguments:
assert arg.weight_tensor is None, (
'Joint sums for weighted sparse columns are not supported. '
'Please use weighted_sum_from_feature_columns instead.')
assert arg.combiner == 'sum', (
'Combiners other than sum are not supported for joint sums. '
'Please use weighted_sum_from_feature_columns instead.')
assert len(embedding_lookup_arguments) >= 1, (
'At least one column must be in the model.')
prev_size = 0
sparse_tensors = []
for a in embedding_lookup_arguments:
t = a.input_tensor
values = t.values + prev_size
prev_size += a.vocab_size
sparse_tensors.append(
sparse_tensor_py.SparseTensor(t.indices,
values,
t.dense_shape))
sparse_tensor = sparse_ops.sparse_concat(1, sparse_tensors)
with variable_scope.variable_scope(
None, default_name='linear_weights', values=columns_to_tensors.values()):
variable = contrib_variables.model_variable(
name='weights',
shape=[prev_size, num_outputs],
dtype=dtypes.float32,
initializer=init_ops.zeros_initializer(),
trainable=trainable,
collections=weight_collections)
if fc._is_variable(variable): # pylint: disable=protected-access
variable = [variable]
else:
variable = variable._get_variable_list() # pylint: disable=protected-access
predictions = embedding_ops.safe_embedding_lookup_sparse(
variable,
sparse_tensor,
sparse_weights=None,
combiner='sum',
name='_weights')
return variable, predictions
def _create_embedding_lookup(column,
columns_to_tensors,
embedding_lookup_arguments,
num_outputs,
trainable,
weight_collections):
"""Creates variables and returns predictions for linear weights in a model.
Args:
column: the column we're working on.
columns_to_tensors: a map from column name to tensors.
embedding_lookup_arguments: arguments for embedding lookup.
num_outputs: how many outputs.
trainable: whether the variable we create is trainable.
weight_collections: weights will be placed here.
Returns:
variables: the created embeddings.
predictions: the computed predictions.
"""
with variable_scope.variable_scope(
None, default_name=column.name, values=columns_to_tensors.values()):
variable = contrib_variables.model_variable(
name='weights',
shape=[embedding_lookup_arguments.vocab_size, num_outputs],
dtype=dtypes.float32,
initializer=embedding_lookup_arguments.initializer,
trainable=trainable,
collections=weight_collections)
if fc._is_variable(variable): # pylint: disable=protected-access
variable = [variable]
else:
variable = variable._get_variable_list() # pylint: disable=protected-access
predictions = embedding_ops.safe_embedding_lookup_sparse(
variable,
embedding_lookup_arguments.input_tensor,
sparse_weights=embedding_lookup_arguments.weight_tensor,
combiner=embedding_lookup_arguments.combiner,
name=column.name + '_weights')
return variable, predictions
def _create_embedding_lookup(column,
columns_to_tensors,
embedding_lookup_arguments,
num_outputs,
trainable,
weight_collections):
"""Creates variables and returns predictions for linear weights in a model.
Args:
column: the column we're working on.
columns_to_tensors: a map from column name to tensors.
embedding_lookup_arguments: arguments for embedding lookup.
num_outputs: how many outputs.
trainable: whether the variable we create is trainable.
weight_collections: weights will be placed here.
Returns:
variables: the created embeddings.
predictions: the computed predictions.
"""
with variable_scope.variable_scope(
None, default_name=column.name, values=columns_to_tensors.values()):
variable = contrib_variables.model_variable(
name='weights',
shape=[embedding_lookup_arguments.vocab_size, num_outputs],
dtype=dtypes.float32,
initializer=embedding_lookup_arguments.initializer,
trainable=trainable,
collections=weight_collections)
if fc._is_variable(variable): # pylint: disable=protected-access
variable = [variable]
else:
variable = variable._get_variable_list() # pylint: disable=protected-access
predictions = embedding_ops.safe_embedding_lookup_sparse(
variable,
embedding_lookup_arguments.input_tensor,
sparse_weights=embedding_lookup_arguments.weight_tensor,
combiner=embedding_lookup_arguments.combiner,
name=column.name + '_weights')
return variable, predictions
def _to_dnn_input_layer(self,
transformed_input_tensor,
weight_collections=None,
trainable=True,
output_rank=2):
"""Returns a Tensor as an input to the first layer of neural network.
Args:
transformed_input_tensor: A tensor that has undergone the transformations
in `insert_transformed_feature`. Rank should be >= `output_rank`.
unused_weight_collections: Unused. One hot encodings are not variable.
unused_trainable: Unused. One hot encodings are not trainable.
output_rank: the desired rank of the output `Tensor`.
Returns:
A outputs Tensor of RNN to be fed into the first layer of neural network.
Raises:
"""
sparse_id_column = self.sparse_id_column.id_tensor(transformed_input_tensor)
# pylint: disable=protected-access
sparse_id_column = layers._inner_flatten(sparse_id_column, output_rank)
batch_size = sparse_id_column.dense_shape[0]
dense_id_tensor = sparse_ops.sparse_to_dense(sparse_id_column.indices,
[batch_size,
self.max_sequence_length],
sparse_id_column.values,
default_value=0)
# dense_id_tensor = gen_array_ops.reshape(dense_id_tensor, [-1, self.max_sequence_length])
if self.shared_embedding_name is not None:
shared_embedding_collection_name = (
"SHARED_EMBEDDING_COLLECTION_" + self.shared_embedding_name.upper())
graph = ops.get_default_graph()
shared_embedding_collection = (
graph.get_collection_ref(shared_embedding_collection_name))
shape = [self.length, self.embedding_dimension]
if shared_embedding_collection:
if len(shared_embedding_collection) > 1:
raise ValueError(
"Collection %s can only contain one "
"(partitioned) variable." % shared_embedding_collection_name)
else:
embeddings = shared_embedding_collection[0]
if embeddings.get_shape() != shape:
raise ValueError(
"The embedding variable with name {} already "
"exists, but its shape does not match required "
"embedding shape here. Please make sure to use "
"different shared_embedding_name for different "
"shared embeddings.".format(args.shared_embedding_name))
else:
embeddings = contrib_variables.model_variable(
name=self.shared_embedding_name,
shape=shape,
dtype=dtypes.float32,
initializer=self.initializer,
trainable=(trainable and self.trainable),
collections=weight_collections)
graph.add_to_collection(shared_embedding_collection_name, embeddings)
else:
embeddings = contrib_variables.model_variable(
name="weights",
shape=[self.length, self.embedding_dimension],
dtype=dtypes.float32,
initializer=self.initializer,
trainable=(trainable and self.trainable),
collections=weight_collections)
if _is_variable(embeddings):
embeddings = [embeddings]
else:
embeddings = embeddings._get_variable_list() # pylint: disable=protected-access
embedding_inputs = embedding_lookup(
embeddings,
dense_id_tensor,
max_norm=self.max_norm)
dropout = (self.dropout_keep_probabilities
if self.mode == model_fn.ModeKeys.TRAIN
else None)
sequence_length = self._sequence_length(dense_id_tensor)
if bidirectional_rnn:
cell_fw = rnn_common.construct_rnn_cell(self.num_units, self.cell_type, dropout)
cell_bw = rnn_common.construct_rnn_cell(self.num_units, self.cell_type, dropout)
_rnn_outputs, _ = rnn.bidirectional_dynamic_rnn(cell_fw,
cell_bw,
embedding_inputs,
sequence_length=sequence_length,
dtype=dtypes.float32)
rnn_outputs = array_ops.concat(_rnn_outputs, axis=2)
else:
cell = rnn_common.construct_rnn_cell(self.num_units, self.cell_type, dropout)
rnn_outputs, _ = rnn.dynamic_rnn(cell,
embedding_inputs,
sequence_length=sequence_length,
dtype=dtypes.float32)
return self._extract_last_relevent(rnn_outputs, sequence_length)
