本文整理汇总了Python中syntaxnet.ops.gen_parser_ops.char_token_generator方法的典型用法代码示例。如果您正苦于以下问题：Python gen_parser_ops.char_token_generator方法的具体用法？Python gen_parser_ops.char_token_generator怎么用？Python gen_parser_ops.char_token_generator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: annotate_text
# 需要导入模块: from syntaxnet.ops import gen_parser_ops [as 别名]
# 或者: from syntaxnet.ops.gen_parser_ops import char_token_generator [as 别名]
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
# 需要导入模块: from syntaxnet.ops import gen_parser_ops [as 别名]
# 或者: from syntaxnet.ops.gen_parser_ops import char_token_generator [as 别名]
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
# 需要导入模块: from syntaxnet.ops import gen_parser_ops [as 别名]
# 或者: from syntaxnet.ops.gen_parser_ops import char_token_generator [as 别名]
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