Python nn_utils.LSTMCell方法代碼示例

本文整理匯總了Python中nn_utils.LSTMCell方法的典型用法代碼示例。如果您正苦於以下問題：Python nn_utils.LSTMCell方法的具體用法？Python nn_utils.LSTMCell怎麽用？Python nn_utils.LSTMCell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nn_utils的用法示例。

在下文中一共展示了nn_utils.LSTMCell方法的2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: LSTM_question_embedding

# 需要導入模塊: import nn_utils [as 別名]
# 或者: from nn_utils import LSTMCell [as 別名]
def LSTM_question_embedding(self, sentence, sentence_length):
    #LSTM processes the input question
    lstm_params = "question_lstm"
    hidden_vectors = []
    sentence = self.batch_question
    question_hidden = tf.zeros(
        [self.batch_size, self.utility.FLAGS.embedding_dims], self.data_type)
    question_c_hidden = tf.zeros(
        [self.batch_size, self.utility.FLAGS.embedding_dims], self.data_type)
    if (self.utility.FLAGS.rnn_dropout > 0.0):
      if (self.mode == "train"):
        rnn_dropout_mask = tf.cast(
            tf.random_uniform(
                tf.shape(question_hidden), minval=0.0, maxval=1.0) <
            self.utility.FLAGS.rnn_dropout,
            self.data_type) / self.utility.FLAGS.rnn_dropout
      else:
        rnn_dropout_mask = tf.ones_like(question_hidden)
    for question_iterator in range(self.question_length):
      curr_word = sentence[:, question_iterator]
      question_vector = nn_utils.apply_dropout(
          nn_utils.get_embedding(curr_word, self.utility, self.params),
          self.utility.FLAGS.dropout, self.mode)
      question_hidden, question_c_hidden = nn_utils.LSTMCell(
          question_vector, question_hidden, question_c_hidden, lstm_params,
          self.params)
      if (self.utility.FLAGS.rnn_dropout > 0.0):
        question_hidden = question_hidden * rnn_dropout_mask
      hidden_vectors.append(tf.expand_dims(question_hidden, 0))
    hidden_vectors = tf.concat(axis=0, values=hidden_vectors)
    return question_hidden, hidden_vectors

開發者ID:ringringyi，項目名稱:DOTA_models，代碼行數:33，代碼來源:model.py

示例2: LSTM_question_embedding

# 需要導入模塊: import nn_utils [as 別名]
# 或者: from nn_utils import LSTMCell [as 別名]
def LSTM_question_embedding(self, sentence, sentence_length):
    #LSTM processes the input question
    lstm_params = "question_lstm"
    hidden_vectors = []
    sentence = self.batch_question
    question_hidden = tf.zeros(
        [self.batch_size, self.utility.FLAGS.embedding_dims], self.data_type)
    question_c_hidden = tf.zeros(
        [self.batch_size, self.utility.FLAGS.embedding_dims], self.data_type)
    if (self.utility.FLAGS.rnn_dropout > 0.0):
      if (self.mode == "train"):
        rnn_dropout_mask = tf.cast(
            tf.random_uniform(
                tf.shape(question_hidden), minval=0.0, maxval=1.0) <
            self.utility.FLAGS.rnn_dropout,
            self.data_type) / self.utility.FLAGS.rnn_dropout
      else:
        rnn_dropout_mask = tf.ones_like(question_hidden)
    for question_iterator in range(self.question_length):
      curr_word = sentence[:, question_iterator]
      question_vector = nn_utils.apply_dropout(
          nn_utils.get_embedding(curr_word, self.utility, self.params),
          self.utility.FLAGS.dropout, self.mode)
      question_hidden, question_c_hidden = nn_utils.LSTMCell(
          question_vector, question_hidden, question_c_hidden, lstm_params,
          self.params)
      if (self.utility.FLAGS.rnn_dropout > 0.0):
        question_hidden = question_hidden * rnn_dropout_mask
      hidden_vectors.append(tf.expand_dims(question_hidden, 0))
    hidden_vectors = tf.concat(0, hidden_vectors)
    return question_hidden, hidden_vectors

開發者ID:coderSkyChen，項目名稱:Action_Recognition_Zoo，代碼行數:33，代碼來源:model.py

注：本文中的nn_utils.LSTMCell方法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。