本文整理匯總了Python中syntaxnet.ops.gen_parser_ops.char_token_generator方法的典型用法代碼示例。如果您正苦於以下問題：Python gen_parser_ops.char_token_generator方法的具體用法？Python gen_parser_ops.char_token_generator怎麽用？Python gen_parser_ops.char_token_generator使用的例子？那麽, 這裏精選的方法代碼示例或許可以為您提供幫助。您也可以進一步了解該方法所在類syntaxnet.ops.gen_parser_ops的用法示例。
在下文中一共展示了gen_parser_ops.char_token_generator方法的3個代碼示例，這些例子默認根據受歡迎程度排序。您可以為喜歡或者感覺有用的代碼點讚，您的評價將有助於係統推薦出更棒的Python代碼示例。
示例1: annotate_text
# 需要導入模塊: from syntaxnet.ops import gen_parser_ops [as 別名]
# 或者: from syntaxnet.ops.gen_parser_ops import char_token_generator [as 別名]
def annotate_text(text):
"""
Segment and parse input text using syntaxnet models.
"""
sentence = sentence_pb2.Sentence(
text=text,
token=[sentence_pb2.Token(word=text, start=-1, end=-1)]
)
# preprocess
with tf.Session(graph=tf.Graph()) as tmp_session:
char_input = gen_parser_ops.char_token_generator([sentence.SerializeToString()])
preprocessed = tmp_session.run(char_input)[0]
segmented, _ = SEGMENTER_MODEL(preprocessed)
annotations, traces = PARSER_MODEL(segmented[0])
assert len(annotations) == 1
assert len(traces) == 1
return sentence_pb2.Sentence.FromString(annotations[0]), traces[0] 示例2: annotate_text
# 需要導入模塊: from syntaxnet.ops import gen_parser_ops [as 別名]
# 或者: from syntaxnet.ops.gen_parser_ops import char_token_generator [as 別名]
def annotate_text(self,text):
sentence = sentence_pb2.Sentence(
text=text,
token=[sentence_pb2.Token(word=text, start=-1, end=-1)]
)
# preprocess
with tf.Session(graph=tf.Graph()) as tmp_session:
char_input = gen_parser_ops.char_token_generator([sentence.SerializeToString()])
preprocessed = tmp_session.run(char_input)[0]
segmented, _ = self.segmenter_model(preprocessed)
annotations, traces = self.parser_model(segmented[0])
assert len(annotations) == 1
assert len(traces) == 1
return sentence_pb2.Sentence.FromString(annotations[0]) 示例3: get_segmenter_corpus
# 需要導入模塊: from syntaxnet.ops import gen_parser_ops [as 別名]
# 或者: from syntaxnet.ops.gen_parser_ops import char_token_generator [as 別名]
def get_segmenter_corpus(input_data_path, use_text_format):
"""Reads in a character corpus for segmenting."""
# Read in the documents.
tf.logging.info('Reading documents...')
if use_text_format:
char_corpus = sentence_io.FormatSentenceReader(input_data_path,
'untokenized-text').corpus()
else:
input_corpus = sentence_io.ConllSentenceReader(input_data_path).corpus()
with tf.Session(graph=tf.Graph()) as tmp_session:
char_input = gen_parser_ops.char_token_generator(input_corpus)
char_corpus = tmp_session.run(char_input)
check.Eq(len(input_corpus), len(char_corpus))
return char_corpus