1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436
| from __future__ import absolute_import from __future__ import division from __future__ import print_function
import collections import re import unicodedata import six import tensorflow as tf import sys import traceback import logging
reload(sys) sys.setdefaultencoding('utf8')
logger=logging
def validate_case_matches_checkpoint(do_lower_case, init_checkpoint): """Checks whether the casing config is consistent with the checkpoint name."""
if not init_checkpoint: return
m = re.match("^.*?([A-Za-z0-9_-]+)/bert_model.ckpt", init_checkpoint) if m is None: return
model_name = m.group(1)
lower_models = [ "uncased_L-24_H-1024_A-16", "uncased_L-12_H-768_A-12", "multilingual_L-12_H-768_A-12", "chinese_L-12_H-768_A-12" ]
cased_models = [ "cased_L-12_H-768_A-12", "cased_L-24_H-1024_A-16", "multi_cased_L-12_H-768_A-12" ]
is_bad_config = False if model_name in lower_models and not do_lower_case: is_bad_config = True actual_flag = "False" case_name = "lowercased" opposite_flag = "True"
if model_name in cased_models and do_lower_case: is_bad_config = True actual_flag = "True" case_name = "cased" opposite_flag = "False"
if is_bad_config: raise ValueError( "You passed in `--do_lower_case=%s` with `--init_checkpoint=%s`. " "However, `%s` seems to be a %s model, so you " "should pass in `--do_lower_case=%s` so that the fine-tuning matches " "how the model was pre-training. If this error is wrong, please " "just comment out this check." % (actual_flag, init_checkpoint, model_name, case_name, opposite_flag))
def convert_to_unicode(text): """Converts `text` to Unicode (if it's not already), assuming utf-8 input.""" if six.PY3: if isinstance(text, str): return text elif isinstance(text, bytes): return text.decode("utf-8", "ignore") else: raise ValueError("Unsupported string type: %s" % (type(text))) elif six.PY2: if isinstance(text, str): return text.decode("utf-8", "ignore") elif isinstance(text, unicode): return text else: raise ValueError("Unsupported string type: %s" % (type(text))) else: raise ValueError("Not running on Python2 or Python 3?")
def printable_text(text): """Returns text encoded in a way suitable for print or `tf.logging`."""
if six.PY3: if isinstance(text, str): return text elif isinstance(text, bytes): return text.decode("utf-8", "ignore") else: raise ValueError("Unsupported string type: %s" % (type(text))) elif six.PY2: if isinstance(text, str): return text elif isinstance(text, unicode): return text.encode("utf-8") else: raise ValueError("Unsupported string type: %s" % (type(text))) else: raise ValueError("Not running on Python2 or Python 3?")
def load_vocab(vocab_file): """Loads a vocabulary file into a dictionary.""" vocab = collections.OrderedDict() index = 0 with tf.gfile.GFile(vocab_file, "r") as reader: while True: token = convert_to_unicode(reader.readline()) if not token: break token = token.strip() vocab[token] = index index += 1 return vocab
def convert_by_vocab(vocab, items): """Converts a sequence of [tokens|ids] using the vocab.""" output = [] for item in items: output.append(vocab[item]) return output
def convert_tokens_to_ids(vocab, tokens): return convert_by_vocab(vocab, tokens)
def convert_ids_to_tokens(inv_vocab, ids): return convert_by_vocab(inv_vocab, ids)
def whitespace_tokenize(text): """Runs basic whitespace cleaning and splitting on a piece of text.""" text = text.strip() if not text: return [] tokens = text.split() return tokens
class FullTokenizer(object): """Runs end-to-end tokenziation."""
def __init__(self, vocab_file, do_lower_case=True): self.vocab = load_vocab(vocab_file) self.inv_vocab = {v: k for k, v in self.vocab.items()} self.basic_tokenizer = BasicTokenizer(do_lower_case=do_lower_case) self.wordpiece_tokenizer = WordpieceTokenizer(vocab=self.vocab)
def tokenize(self, text): split_tokens = [] logger.debug("text is: {:s}".format(text)) basic_tokenizers = self.basic_tokenizer.tokenize(text) logger.debug("basic_tokenizers is {}".format(basic_tokenizers)) for token in basic_tokenizers: logger.debug("BasicTokenizer output: {:s}".format(token)) for sub_token in self.wordpiece_tokenizer.tokenize(token): split_tokens.append(sub_token) logger.debug("Splits token is {}".format(split_tokens)) return split_tokens def tokenize_unicoder(self, text): """ [summary] just token the textual part, do not change the rest Arguments: text {[string]} -- ["id\tdet1\tdet2\ttext"]
Returns: details [list] -- [id,det1,det2,token1,token2,token3,token4...] """ try: if isinstance(text,str): split_text = text.strip().split("\t") else: split_text = text logger.info("split text {}".format(split_text)) image_id, image_url, title_text = split_text if not AbaseClient.exists(Params.abase_image_text_relevance_data.format(image_id)): logger.error("{} do not exist in abase".format(image_id)) return [] split_tokens = [image_id,image_url] for token in self.basic_tokenizer.tokenize(title_text): logger.debug("tokenize_unicoder: BasicTokenizer output is --> {}".format(token)) for sub_token in self.wordpiece_tokenizer.tokenize(token): split_tokens.append(sub_token) return split_tokens except: logger.error(traceback.format_exc()) return []
def convert_tokens_to_ids(self, tokens): return convert_by_vocab(self.vocab, tokens)
def convert_ids_to_tokens(self, ids): return convert_by_vocab(self.inv_vocab, ids)
class BasicTokenizer(object): """Runs basic tokenization (punctuation splitting, lower casing, etc.)."""
def __init__(self, do_lower_case=True): """Constructs a BasicTokenizer.
Args: do_lower_case: Whether to lower case the input. """ self.do_lower_case = do_lower_case
def tokenize(self, text): """Tokenizes a piece of text.""" text = convert_to_unicode(text) text = self._clean_text(text)
text = self._tokenize_chinese_chars(text)
orig_tokens = whitespace_tokenize(text) split_tokens = [] for token in orig_tokens: if self.do_lower_case: token = token.lower() token = self._run_strip_accents(token) split_tokens.extend(self._run_split_on_punc(token))
output_tokens = whitespace_tokenize(" ".join(split_tokens)) return output_tokens
def _run_strip_accents(self, text): """Strips accents from a piece of text.""" text = unicodedata.normalize("NFD", text) output = [] for char in text: cat = unicodedata.category(char) if cat == "Mn": continue output.append(char) return "".join(output)
def _run_split_on_punc(self, text): """Splits punctuation on a piece of text.""" chars = list(text) i = 0 start_new_word = True output = [] while i < len(chars): char = chars[i] if _is_punctuation(char): output.append([char]) start_new_word = True else: if start_new_word: output.append([]) start_new_word = False output[-1].append(char) i += 1
return ["".join(x) for x in output]
def _tokenize_chinese_chars(self, text): """Adds whitespace around any CJK character.""" output = [] for char in text: cp = ord(char) if self._is_chinese_char(cp): output.append(" ") output.append(char) output.append(" ") else: output.append(char) return "".join(output)
def _is_chinese_char(self, cp): """Checks whether CP is the codepoint of a CJK character.""" if ((cp >= 0x4E00 and cp <= 0x9FFF) or (cp >= 0x3400 and cp <= 0x4DBF) or (cp >= 0x20000 and cp <= 0x2A6DF) or (cp >= 0x2A700 and cp <= 0x2B73F) or (cp >= 0x2B740 and cp <= 0x2B81F) or (cp >= 0x2B820 and cp <= 0x2CEAF) or (cp >= 0xF900 and cp <= 0xFAFF) or (cp >= 0x2F800 and cp <= 0x2FA1F)): return True
return False
def _clean_text(self, text): """Performs invalid character removal and whitespace cleanup on text.""" output = [] for char in text: cp = ord(char) if cp == 0 or cp == 0xfffd or _is_control(char): continue if _is_whitespace(char): output.append(" ") else: output.append(char) return "".join(output)
class WordpieceTokenizer(object): """Runs WordPiece tokenziation."""
def __init__(self, vocab, unk_token="[UNK]", max_input_chars_per_word=200): self.vocab = vocab self.unk_token = unk_token self.max_input_chars_per_word = max_input_chars_per_word
def tokenize(self, text): """Tokenizes a piece of text into its word pieces.
This uses a greedy longest-match-first algorithm to perform tokenization using the given vocabulary.
For example: input = "unaffable" output = ["un", "##aff", "##able"]
Args: text: A single token or whitespace separated tokens. This should have already been passed through `BasicTokenizer.
Returns: A list of wordpiece tokens. """
text = convert_to_unicode(text)
output_tokens = [] for token in whitespace_tokenize(text): chars = list(token) if len(chars) > self.max_input_chars_per_word: output_tokens.append(self.unk_token) continue
is_bad = False start = 0 sub_tokens = [] while start < len(chars): end = len(chars) cur_substr = None while start < end: substr = "".join(chars[start:end]) if start > 0: substr = "##" + substr if substr in self.vocab: cur_substr = substr break end -= 1 if cur_substr is None: is_bad = True break sub_tokens.append(cur_substr) start = end
if is_bad: output_tokens.append(self.unk_token) else: output_tokens.extend(sub_tokens) return output_tokens
def _is_whitespace(char): """Checks whether `chars` is a whitespace character.""" if char == " " or char == "\t" or char == "\n" or char == "\r": return True cat = unicodedata.category(char) if cat == "Zs": return True return False
def _is_control(char): """Checks whether `chars` is a control character.""" if char == "\t" or char == "\n" or char == "\r": return False cat = unicodedata.category(char) if cat in ("Cc", "Cf"): return True return False
def _is_punctuation(char): """Checks whether `chars` is a punctuation character.""" cp = ord(char) if ((cp >= 33 and cp <= 47) or (cp >= 58 and cp <= 64) or (cp >= 91 and cp <= 96) or (cp >= 123 and cp <= 126)): return True cat = unicodedata.category(char) if cat.startswith("P"): return True return False if __name__ == "__main__": tk = FullTokenizer( "config/vocab.txt") text = "10009090090 熊猫烧香" tokens = tk.tokenize(text) logger.info("tokens: {}".format(tokens)) ids = tk.convert_tokens_to_ids(tokens) logger.info("ids: {}".format(ids))
|