apn.py 文件源码

def buildAttention(self):
        q_relu = self.tensors['q_relu']
        a_relu = self.tensors['a_relu']
        with tf.name_scope("attention"):
            W = identity([self.params['nb_filter'], self.params['nb_filter']], name='W')
            batch = tf.shape(q_relu)[0]
            q_matmul = tf.batch_matmul(q_relu, tf.tile(tf.expand_dims(W,[0]), tf.pack([batch, tf.constant(1), tf.constant(1)])))
            qa_attention = tf.batch_matmul(q_matmul, a_relu, adj_x=False, adj_y=True, name="attention")
            # shape = (batch, q_length, 1)
            qa_attention = tf.tanh(qa_attention)
            q_max = tf.reduce_max(qa_attention, reduction_indices=[2], keep_dims=True, name='q_max')
            # shape = (batch, 1, a_length)
            a_max = tf.reduce_max(qa_attention, reduction_indices=[1], keep_dims=True, name='a_max')
            # shape = (batch, q_length, 1)
            q_softmax = tf.expand_dims(tf.nn.softmax(tf.squeeze(q_max, [2])), -1)
            # shape = (batch, a_length, 1)
            a_softmax = tf.expand_dims(tf.nn.softmax(tf.squeeze(a_max, [1])), -1)
            # https://www.tensorflow.org/versions/r0.9/api_docs/python/math_ops.html#batch_matmul 
            # shape = (batch, NUM_FILTERS, 1)
            q_feature = tf.batch_matmul(q_relu, q_softmax, adj_x=True, adj_y=False)
            a_feature = tf.batch_matmul(a_relu, a_softmax, adj_x=True, adj_y=False)
        self.tensors['q_feature'] = q_feature
        self.tensors['a_feature'] = a_feature
        self.tensors.setdefault('weights', []).append(W)