本文整理汇总了Python中tensorflow.regex_replace方法的典型用法代码示例。如果您正苦于以下问题：Python tensorflow.regex_replace方法的具体用法？Python tensorflow.regex_replace怎么用？Python tensorflow.regex_replace使用的例子？那么恭喜您, 这里精选的方法代码示例或许可以为您提供帮助。您也可以进一步了解该方法所在类tensorflow的用法示例。
在下文中一共展示了tensorflow.regex_replace方法的3个代码示例，这些例子默认根据受欢迎程度排序。您可以为喜欢或者感觉有用的代码点赞，您的评价将有助于系统推荐出更棒的Python代码示例。
示例1: parse_raw_text
# 需要导入模块: import tensorflow [as 别名]
# 或者: from tensorflow import regex_replace [as 别名]
def parse_raw_text(sentence):
"""Splits text tensor by word to sparse sequence of tokens.
Args:
sentence: `tf.string`, with text record to split.
Returns:
Dictionary mapping feature name to tensors with the following entries
`constants.TOKENS` mapping to a `SparseTensor` and
`constants.SEQUENCE_LENGTH` mapping to a one-dimensional integer `Tensor`.
"""
tokens = tf.regex_replace(sentence, _CHAR_TO_FILTER_OUT, ' ',
replace_global=True)
sparse_sequence = tf.string_split(tokens)
features = {
constants.TOKENS: sparse_sequence,
constants.SEQUENCE_LENGTH: get_sparse_tensor_size(sparse_sequence)
}
return features 示例2: provide_data
# 需要导入模块: import tensorflow [as 别名]
# 或者: from tensorflow import regex_replace [as 别名]
def provide_data(self):
def decode(line):
fields = tf.string_split([line], self.field_delim).values
if self.index: # Skip index
fields = fields[1:]
fields = tf.regex_replace(fields, "|".join(self.na_values), "nan")
fields = tf.string_to_number(fields, tf.float32)
return fields
def fill_na(fields, fill_values):
fields = tf.where(tf.is_nan(fields), fill_values, fields)
return fields
dataset = tf.data.TextLineDataset(self.local_data_file)
if self.header: # Skip header
dataset = dataset.skip(1)
dataset = (
dataset.map(decode)
.map(lambda x: fill_na(x, self.data_schema.field_defaults))
.repeat()
.batch(self.batch_size)
)
iterator = dataset.make_one_shot_iterator()
batch = iterator.get_next()
batch = tf.reshape(batch, [self.batch_size, self.data_schema.field_num])
return batch 示例3: word_error_rate
# 需要导入模块: import tensorflow [as 别名]
# 或者: from tensorflow import regex_replace [as 别名]
def word_error_rate(raw_predictions,
labels,
lookup=None,
weights_fn=common_layers.weights_nonzero):
"""Calculate word error rate.
Args:
raw_predictions: The raw predictions.
labels: The actual labels.
lookup: A tf.constant mapping indices to output tokens.
weights_fn: Weighting function.
Returns:
The word error rate.
"""
def from_tokens(raw, lookup_):
gathered = tf.gather(lookup_, tf.cast(raw, tf.int32))
joined = tf.regex_replace(tf.reduce_join(gathered, axis=1), b"<EOS>.*", b"")
cleaned = tf.regex_replace(joined, b"_", b" ")
tokens = tf.string_split(cleaned, " ")
return tokens
def from_characters(raw, lookup_):
"""Convert ascii+2 encoded codes to string-tokens."""
corrected = tf.bitcast(
tf.clip_by_value(tf.subtract(raw, 2), 0, 255), tf.uint8)
gathered = tf.gather(lookup_, tf.cast(corrected, tf.int32))[:, :, 0]
joined = tf.reduce_join(gathered, axis=1)
cleaned = tf.regex_replace(joined, b"\0", b"")
tokens = tf.string_split(cleaned, " ")
return tokens
if lookup is None:
lookup = tf.constant([chr(i) for i in range(256)])
convert_fn = from_characters
else:
convert_fn = from_tokens
if weights_fn is not common_layers.weights_nonzero:
raise ValueError("Only weights_nonzero can be used for this metric.")
with tf.variable_scope("word_error_rate", values=[raw_predictions, labels]):
raw_predictions = tf.squeeze(
tf.argmax(raw_predictions, axis=-1), axis=(2, 3))
labels = tf.squeeze(labels, axis=(2, 3))
reference = convert_fn(labels, lookup)
predictions = convert_fn(raw_predictions, lookup)
distance = tf.reduce_sum(
tf.edit_distance(predictions, reference, normalize=False))
reference_length = tf.cast(
tf.size(reference.values, out_type=tf.int32), dtype=tf.float32)
return distance / reference_length, reference_length