rnn_cell.py 文件源码

def _attention(self, query, attn_states):
    conv2d = nn_ops.conv2d
    reduce_sum = math_ops.reduce_sum
    softmax = nn_ops.softmax
    tanh = math_ops.tanh

    with tf.variable_scope("attention"):
      k = tf.get_variable(
          "attn_w", [1, 1, self._attn_size, self._attn_vec_size])
      v = tf.get_variable("attn_v", [self._attn_vec_size])
      hidden = array_ops.reshape(attn_states,
                                 [-1, self._attn_length, 1, self._attn_size])
      hidden_features = conv2d(hidden, k, [1, 1, 1, 1], "SAME")
      y = _linear(query, self._attn_vec_size, True)
      y = array_ops.reshape(y, [-1, 1, 1, self._attn_vec_size])
      s = reduce_sum(v * tanh(hidden_features + y), [2, 3])
      a = softmax(s)
      d = reduce_sum(
          array_ops.reshape(a, [-1, self._attn_length, 1, 1]) * hidden, [1, 2])
      new_attns = array_ops.reshape(d, [-1, self._attn_size])
      new_attn_states = array_ops.slice(attn_states, [0, 1, 0], [-1, -1, -1])
      return new_attns, new_attn_states