search

THTBSE / rnn_text_classification

bidirectional rnn for text classification
109 stars 61 forks source link

Problem in model.py #4

Open THUHJ opened 6 years ago

THUHJ commented 6 years ago

https://github.com/THTBSE/rnn_text_classification/blob/master/model.py

# 定义反向RNN Cell with tf.name_scope('bw_rnn'), tf.variable_scope('bw_rnn'): print tf.get_variable_scope().name lstm_bw_cell_list = [tf.contrib.rnn.LSTMCell(rnn_size) for _ in xrange(layer_size)] lstm_bw_cell_m = tf.contrib.rnn.DropoutWrapper(tf.contrib.rnn.MultiRNNCell(lstm_fw_cell_list), output_keep_prob=self.output_keep_prob)

In the definition of lstm_bw_cell_m, It should be lstm_bw_cell_list rather than lstm_fw_cell_list. Right?

D0ngs3c commented 5 years ago

https://github.com/THTBSE/rnn_text_classification/blob/master/model.py

# 定义反向RNN Cell with tf.name_scope('bw_rnn'), tf.variable_scope('bw_rnn'): print tf.get_variable_scope().name lstm_bw_cell_list = [tf.contrib.rnn.LSTMCell(rnn_size) for _ in xrange(layer_size)] lstm_bw_cell_m = tf.contrib.rnn.DropoutWrapper(tf.contrib.rnn.MultiRNNCell(lstm_fw_cell_list), output_keep_prob=self.output_keep_prob)

In the definition of lstm_bw_cell_m, It should be lstm_bw_cell_list rather than lstm_fw_cell_list. Right?

i think so