Python tensorflow.python.ops.gen_array_ops.reverse_sequence() Examples
The following are 7
code examples of tensorflow.python.ops.gen_array_ops.reverse_sequence().
You can vote up the ones you like or vote down the ones you don't like,
and go to the original project or source file by following the links above each example.
You may also want to check out all available functions/classes of the module
tensorflow.python.ops.gen_array_ops
, or try the search function
.
.
Example #1
| Source File: array_ops.py From lambda-packs with MIT License | 6 votes |
|
def reverse_sequence(input,
seq_lengths,
seq_axis=None,
batch_axis=None,
name=None,
seq_dim=None,
batch_dim=None):
seq_axis = deprecation.deprecated_argument_lookup("seq_axis", seq_axis,
"seq_dim", seq_dim)
batch_axis = deprecation.deprecated_argument_lookup("batch_axis", batch_axis,
"batch_dim", batch_dim)
return gen_array_ops.reverse_sequence(
input=input,
seq_lengths=seq_lengths,
seq_dim=seq_axis,
batch_dim=batch_axis,
name=name)
# pylint: enable=redefined-builtin
Example #2
| Source File: array_ops.py From auto-alt-text-lambda-api with MIT License | 6 votes |
|
def reverse_sequence(input,
seq_lengths,
seq_axis=None,
batch_axis=None,
name=None,
seq_dim=None,
batch_dim=None):
seq_axis = deprecation.deprecated_argument_lookup("seq_axis", seq_axis,
"seq_dim", seq_dim)
batch_axis = deprecation.deprecated_argument_lookup("batch_axis", batch_axis,
"batch_dim", batch_dim)
return gen_array_ops.reverse_sequence(
input=input,
seq_lengths=seq_lengths,
seq_dim=seq_axis,
batch_dim=batch_axis,
name=name)
# pylint: enable=redefined-builtin
Example #3
| Source File: array_ops.py From Serverless-Deep-Learning-with-TensorFlow-and-AWS-Lambda with MIT License | 6 votes |
|
def reverse_sequence(input,
seq_lengths,
seq_axis=None,
batch_axis=None,
name=None,
seq_dim=None,
batch_dim=None):
seq_axis = deprecation.deprecated_argument_lookup("seq_axis", seq_axis,
"seq_dim", seq_dim)
batch_axis = deprecation.deprecated_argument_lookup("batch_axis", batch_axis,
"batch_dim", batch_dim)
return gen_array_ops.reverse_sequence(
input=input,
seq_lengths=seq_lengths,
seq_dim=seq_axis,
batch_dim=batch_axis,
name=name)
# pylint: enable=redefined-builtin
Example #4
| Source File: array_ops.py From keras-lambda with MIT License | 6 votes |
|
def reverse_sequence(input,
seq_lengths,
seq_axis=None,
batch_axis=None,
name=None,
seq_dim=None,
batch_dim=None):
seq_axis = deprecation.deprecated_argument_lookup("seq_axis", seq_axis,
"seq_dim", seq_dim)
batch_axis = deprecation.deprecated_argument_lookup("batch_axis", batch_axis,
"batch_dim", batch_dim)
return gen_array_ops.reverse_sequence(
input=input,
seq_lengths=seq_lengths,
seq_dim=seq_axis,
batch_dim=batch_axis,
name=name)
# pylint: enable=redefined-builtin
Example #5
| Source File: crf.py From tensorflow_nlp with Apache License 2.0 | 4 votes |
|
def crf_decode(potentials, transition_params, sequence_length):
"""Decode the highest scoring sequence of tags in TensorFlow.
This is a function for tensor.
Args:
potentials: A [batch_size, max_seq_len, num_tags] tensor, matrix of
unary potentials.
transition_params: A [num_tags, num_tags] tensor, matrix of
binary potentials.
sequence_length: A [batch_size] tensor, containing sequence lengths.
Returns:
decode_tags: A [batch_size, max_seq_len] tensor, with dtype tf.int32.
Contains the highest scoring tag indicies.
best_score: A [batch_size] tensor, containing the score of decode_tags.
"""
# For simplicity, in shape comments, denote:
# 'batch_size' by 'B', 'max_seq_len' by 'T' , 'num_tags' by 'O' (output).
num_tags = potentials.get_shape()[2].value
# Computes forward decoding. Get last score and backpointers.
crf_fwd_cell = CrfDecodeForwardRnnCell(transition_params)
initial_state = array_ops.slice(potentials, [0, 0, 0], [-1, 1, -1])
initial_state = array_ops.squeeze(initial_state, axis=[1]) # [B, O]
inputs = array_ops.slice(potentials, [0, 1, 0], [-1, -1, -1]) # [B, T-1, O]
backpointers, last_score = rnn.dynamic_rnn(
crf_fwd_cell,
inputs=inputs,
sequence_length=sequence_length - 1,
initial_state=initial_state,
time_major=False,
dtype=dtypes.int32) # [B, T - 1, O], [B, O]
backpointers = gen_array_ops.reverse_sequence(
backpointers, sequence_length - 1, seq_dim=1) # [B, T-1, O]
# Computes backward decoding. Extract tag indices from backpointers.
crf_bwd_cell = CrfDecodeBackwardRnnCell(num_tags)
initial_state = math_ops.cast(math_ops.argmax(last_score, axis=1),
dtype=dtypes.int32) # [B]
initial_state = array_ops.expand_dims(initial_state, axis=-1) # [B, 1]
decode_tags, _ = rnn.dynamic_rnn(
crf_bwd_cell,
inputs=backpointers,
sequence_length=sequence_length - 1,
initial_state=initial_state,
time_major=False,
dtype=dtypes.int32) # [B, T - 1, 1]
decode_tags = array_ops.squeeze(decode_tags, axis=[2]) # [B, T - 1]
decode_tags = array_ops.concat([initial_state, decode_tags], axis=1) # [B, T]
decode_tags = gen_array_ops.reverse_sequence(
decode_tags, sequence_length, seq_dim=1) # [B, T]
best_score = math_ops.reduce_max(last_score, axis=1) # [B]
return decode_tags, best_score
Example #6
| Source File: crf.py From tensorflow-nlp-examples with MIT License | 4 votes |
|
def crf_decode(potentials, transition_params, sequence_length):
"""Decode the highest scoring sequence of tags in TensorFlow.
This is a function for tensor.
Args:
potentials: A [batch_size, max_seq_len, num_tags] tensor, matrix of
unary potentials.
transition_params: A [num_tags, num_tags] tensor, matrix of
binary potentials.
sequence_length: A [batch_size] tensor, containing sequence lengths.
Returns:
decode_tags: A [batch_size, max_seq_len] tensor, with dtype tf.int32.
Contains the highest scoring tag indicies.
best_score: A [batch_size] tensor, containing the score of decode_tags.
"""
# For simplicity, in shape comments, denote:
# 'batch_size' by 'B', 'max_seq_len' by 'T' , 'num_tags' by 'O' (output).
num_tags = potentials.get_shape()[2].value
# Computes forward decoding. Get last score and backpointers.
crf_fwd_cell = CrfDecodeForwardRnnCell(transition_params)
initial_state = array_ops.slice(potentials, [0, 0, 0], [-1, 1, -1])
initial_state = array_ops.squeeze(initial_state, axis=[1]) # [B, O]
inputs = array_ops.slice(potentials, [0, 1, 0], [-1, -1, -1]) # [B, T-1, O]
backpointers, last_score = rnn.dynamic_rnn(
crf_fwd_cell,
inputs=inputs,
sequence_length=sequence_length - 1,
initial_state=initial_state,
time_major=False,
dtype=dtypes.int32) # [B, T - 1, O], [B, O]
backpointers = gen_array_ops.reverse_sequence(backpointers, sequence_length - 1, seq_dim=1) # [B, T-1, O]
# Computes backward decoding. Extract tag indices from backpointers.
crf_bwd_cell = CrfDecodeBackwardRnnCell(num_tags)
initial_state = math_ops.cast(math_ops.argmax(last_score, axis=1), dtype=dtypes.int32) # [B]
initial_state = array_ops.expand_dims(initial_state, axis=-1) # [B, 1]
decode_tags, _ = rnn.dynamic_rnn(
crf_bwd_cell,
inputs=backpointers,
sequence_length=sequence_length - 1,
initial_state=initial_state,
time_major=False,
dtype=dtypes.int32) # [B, T - 1, 1]
decode_tags = array_ops.squeeze(decode_tags, axis=[2]) # [B, T - 1]
decode_tags = array_ops.concat([initial_state, decode_tags], axis=1) # [B, T]
decode_tags = gen_array_ops.reverse_sequence(decode_tags, sequence_length, seq_dim=1) # [B, T]
best_score = math_ops.reduce_max(last_score, axis=1) # [B]
return decode_tags, best_score
Example #7
| Source File: crf.py From keras-crf-layer with MIT License | 4 votes |
|
def crf_decode(potentials, transition_params, sequence_length):
"""Decode the highest scoring sequence of tags in TensorFlow.
This is a function for tensor.
Args:
potentials: A [batch_size, max_seq_len, num_tags] tensor, matrix of
unary potentials.
transition_params: A [num_tags, num_tags] tensor, matrix of
binary potentials.
sequence_length: A [batch_size] tensor, containing sequence lengths.
Returns:
decode_tags: A [batch_size, max_seq_len] tensor, with dtype tf.int32.
Contains the highest scoring tag indicies.
best_score: A [batch_size] tensor, containing the score of decode_tags.
"""
# For simplicity, in shape comments, denote:
# 'batch_size' by 'B', 'max_seq_len' by 'T' , 'num_tags' by 'O' (output).
num_tags = potentials.get_shape()[2].value
# Computes forward decoding. Get last score and backpointers.
crf_fwd_cell = CrfDecodeForwardRnnCell(transition_params)
initial_state = array_ops.slice(potentials, [0, 0, 0], [-1, 1, -1])
initial_state = array_ops.squeeze(initial_state, axis=[1]) # [B, O]
inputs = array_ops.slice(potentials, [0, 1, 0], [-1, -1, -1]) # [B, T-1, O]
backpointers, last_score = rnn.dynamic_rnn(
crf_fwd_cell,
inputs=inputs,
sequence_length=sequence_length - 1,
initial_state=initial_state,
time_major=False,
dtype=dtypes.int32) # [B, T - 1, O], [B, O]
backpointers = gen_array_ops.reverse_sequence(backpointers, sequence_length - 1, seq_dim=1) # [B, T-1, O]
# Computes backward decoding. Extract tag indices from backpointers.
crf_bwd_cell = CrfDecodeBackwardRnnCell(num_tags)
initial_state = math_ops.cast(math_ops.argmax(last_score, axis=1), dtype=dtypes.int32) # [B]
initial_state = array_ops.expand_dims(initial_state, axis=-1) # [B, 1]
decode_tags, _ = rnn.dynamic_rnn(
crf_bwd_cell,
inputs=backpointers,
sequence_length=sequence_length - 1,
initial_state=initial_state,
time_major=False,
dtype=dtypes.int32) # [B, T - 1, 1]
decode_tags = array_ops.squeeze(decode_tags, axis=[2]) # [B, T - 1]
decode_tags = array_ops.concat([initial_state, decode_tags], axis=1) # [B, T]
decode_tags = gen_array_ops.reverse_sequence(decode_tags, sequence_length, seq_dim=1) # [B, T]
best_score = math_ops.reduce_max(last_score, axis=1) # [B]
return decode_tags, best_score
