Python special_words.UNK屬性代碼示例

本文整理匯總了Python中skip_thoughts.data.special_words.UNK屬性的典型用法代碼示例。如果您正苦於以下問題：Python special_words.UNK屬性的具體用法？Python special_words.UNK怎麽用？Python special_words.UNK使用的例子？那麽, 這裏精選的屬性代碼示例或許可以為您提供幫助。您也可以進一步了解該屬性所在類skip_thoughts.data.special_words的用法示例。

在下文中一共展示了special_words.UNK屬性的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: _word_to_embedding

# 需要導入模塊: from skip_thoughts.data import special_words [as 別名]
# 或者: from skip_thoughts.data.special_words import UNK [as 別名]
def _word_to_embedding(self, w):
    """Returns the embedding of a word."""
    return self._embeddings.get(w, self._embeddings[special_words.UNK])

開發者ID:ringringyi，項目名稱:DOTA_models，代碼行數:5，代碼來源:skip_thoughts_encoder.py

示例2: _build_vocabulary

# 需要導入模塊: from skip_thoughts.data import special_words [as 別名]
# 或者: from skip_thoughts.data.special_words import UNK [as 別名]
def _build_vocabulary(input_files):
  """Loads or builds the model vocabulary.

  Args:
    input_files: List of pre-tokenized input .txt files.

  Returns:
    vocab: A dictionary of word to id.
  """
  if FLAGS.vocab_file:
    tf.logging.info("Loading existing vocab file.")
    vocab = collections.OrderedDict()
    with tf.gfile.GFile(FLAGS.vocab_file, mode="r") as f:
      for i, line in enumerate(f):
        word = line.decode("utf-8").strip()
        assert word not in vocab, "Attempting to add word twice: %s" % word
        vocab[word] = i
    tf.logging.info("Read vocab of size %d from %s",
                    len(vocab), FLAGS.vocab_file)
    return vocab

  tf.logging.info("Creating vocabulary.")
  num = 0
  wordcount = collections.Counter()
  for input_file in input_files:
    tf.logging.info("Processing file: %s", input_file)
    for sentence in tf.gfile.FastGFile(input_file):
      wordcount.update(sentence.split())

      num += 1
      if num % 1000000 == 0:
        tf.logging.info("Processed %d sentences", num)

  tf.logging.info("Processed %d sentences total", num)

  words = wordcount.keys()
  freqs = wordcount.values()
  sorted_indices = np.argsort(freqs)[::-1]

  vocab = collections.OrderedDict()
  vocab[special_words.EOS] = special_words.EOS_ID
  vocab[special_words.UNK] = special_words.UNK_ID
  for w_id, w_index in enumerate(sorted_indices[0:FLAGS.num_words - 2]):
    vocab[words[w_index]] = w_id + 2  # 0: EOS, 1: UNK.

  tf.logging.info("Created vocab with %d words", len(vocab))

  vocab_file = os.path.join(FLAGS.output_dir, "vocab.txt")
  with tf.gfile.FastGFile(vocab_file, "w") as f:
    f.write("\n".join(vocab.keys()))
  tf.logging.info("Wrote vocab file to %s", vocab_file)

  word_counts_file = os.path.join(FLAGS.output_dir, "word_counts.txt")
  with tf.gfile.FastGFile(word_counts_file, "w") as f:
    for i in sorted_indices:
      f.write("%s %d\n" % (words[i], freqs[i]))
  tf.logging.info("Wrote word counts file to %s", word_counts_file)

  return vocab

開發者ID:ringringyi，項目名稱:DOTA_models，代碼行數:61，代碼來源:preprocess_dataset.py

示例3: _build_vocabulary

# 需要導入模塊: from skip_thoughts.data import special_words [as 別名]
# 或者: from skip_thoughts.data.special_words import UNK [as 別名]
def _build_vocabulary(input_files):
  """Loads or builds the model vocabulary.

  Args:
    input_files: List of pre-tokenized input .txt files.

  Returns:
    vocab: A dictionary of word to id.
  """
  if FLAGS.vocab_file:
    tf.logging.info("Loading existing vocab file.")
    vocab = collections.OrderedDict()
    with tf.gfile.GFile(FLAGS.vocab_file, mode="r") as f:
      for i, line in enumerate(f):
        word = line.decode("utf-8").strip()
        assert word not in vocab, "Attempting to add word twice: %s" % word
        vocab[word] = i
    tf.logging.info("Read vocab of size %d from %s",
                    len(vocab), FLAGS.vocab_file)
    return vocab

  tf.logging.info("Creating vocabulary.")
  num = 0
  wordcount = collections.Counter()
  for input_file in input_files:
    tf.logging.info("Processing file: %s", input_file)
    for sentence in tf.gfile.FastGFile(input_file):
      wordcount.update(sentence.split())

      num += 1
      if num % 1000000 == 0:
        tf.logging.info("Processed %d sentences", num)

  tf.logging.info("Processed %d sentences total", num)

  words = list(wordcount)
  freqs = list(wordcount.values())
  sorted_indices = np.argsort(freqs)[::-1]

  vocab = collections.OrderedDict()
  vocab[special_words.EOS] = special_words.EOS_ID
  vocab[special_words.UNK] = special_words.UNK_ID
  for w_id, w_index in enumerate(sorted_indices[0:FLAGS.num_words - 2]):
    vocab[words[w_index]] = w_id + 2  # 0: EOS, 1: UNK.

  tf.logging.info("Created vocab with %d words", len(vocab))

  vocab_file = os.path.join(FLAGS.output_dir, "vocab.txt")
  with tf.gfile.FastGFile(vocab_file, "w") as f:
    f.write("\n".join(vocab.keys()))
  tf.logging.info("Wrote vocab file to %s", vocab_file)

  word_counts_file = os.path.join(FLAGS.output_dir, "word_counts.txt")
  with tf.gfile.FastGFile(word_counts_file, "w") as f:
    for i in sorted_indices:
      f.write("%s %d\n" % (words[i], freqs[i]))
  tf.logging.info("Wrote word counts file to %s", word_counts_file)

  return vocab

開發者ID:generalized-iou，項目名稱:g-tensorflow-models，代碼行數:61，代碼來源:preprocess_dataset.py

注：本文中的skip_thoughts.data.special_words.UNK屬性示例由純淨天空整理自Github/MSDocs等開源代碼及文檔管理平台，相關代碼片段篩選自各路編程大神貢獻的開源項目，源碼版權歸原作者所有，傳播和使用請參考對應項目的License；未經允許，請勿轉載。