标签:代码 str out class 版本 seq drop tmc tar
tf 经常更新版本,网上教程又是各版本都有,且不标明版本,致使各种用法难以分清哪个新,哪个旧,这里做个记录,以前的博客我就不更新了,请大家见谅。
tf.nn.rnn_cell 改为 tf.contrib.rnn
# 原代码 lstm_cell = tf.nn.rnn_cell.BasicLSTMCell(HIDDEN_SIZE) if is_training: lstm_cell = tf.nn.rnn_cell.DropoutWrapper(lstm_cell, output_keep_prob=KEEP_PROB) cell = tf.nn.rnn_cell.MultiRNNCell([lstm_cell] * NUM_LAYERS) # 修改为 lstm_cell = tf.contrib.rnn.BasicLSTMCell(HIDDEN_SIZE) if is_training: lstm_cell = tf.contrib.rnn.DropoutWrapper(lstm_cell, output_keep_prob=KEEP_PROB) cell = tf.contrib.rnn.MultiRNNCell([lstm_cell] * NUM_LAYERS)
tf.nn.seq2seq.sequence_loss_by_example 改为 tf.contrib.legacy_seq2seq.sequence_loss_by_example
# 原代码 loss = tf.nn.seq2seq.sequence_loss_by_example( [logits], [tf.reshape(self.targets, [-1])], [tf.ones([batch_size * num_steps], dtype=tf.float32)]) # 修改为 loss = tf.contrib.legacy_seq2seq.sequence_loss_by_example( [logits], [tf.reshape(self.targets, [-1])], [tf.ones([batch_size * num_steps], dtype=tf.float32)])
tf.concat
# 原代码 concated = tf.concat(1, [indices, labels]) # 修改为 concated = tf.concat([indices, labels], 1)
标签:代码 str out class 版本 seq drop tmc tar
原文地址:https://www.cnblogs.com/yanshw/p/10550597.html