def _encode(self):
with tf.variable_scope('answer_encoding', reuse=tf.AUTO_REUSE):
a_rnn = cudnn_gru(num_layers=2 * self.layer_num,
num_units=self.hidden_size,
batch_size=self.N,
input_size=self.a_emb.get_shape().as_list()[-1],
keep_prob=self.dropout_keep_prob,
is_train=self.is_train)
self.a_encodes = a_rnn(self.a_emb, seq_len=self.a_len)
with tf.variable_scope('question_encoding', reuse=tf.AUTO_REUSE):
q_rnn = cudnn_gru(num_layers=2 * self.layer_num,
num_units=self.hidden_size,
batch_size=self.N,
input_size=self.q_emb.get_shape().as_list()[-1],
keep_prob=self.dropout_keep_prob,
is_train=self.is_train)
self.q_encodes = q_rnn(self.q_emb, seq_len=self.q_len)
def _self_attention(self):
with tf.variable_scope('self_attention', reuse=tf.AUTO_REUSE):
self.pp_att = dot_attention(self.gated_att,
self.gated_att,
mask=self.p_mask,
hidden=self.hidden_size,
keep_prob=self.dropout_keep_prob,
is_train=self.is_train)
self_rnn = cudnn_gru(
num_layers=self.layer_num,
num_units=self.hidden_size,
batch_size=self.N,
input_size=self.pp_att.get_shape().as_list()[-1],
keep_prob=self.dropout_keep_prob,
is_train=self.is_train)
self.self_att = self_rnn(self.pp_att, self.p_len)