NLP分类常用模型（二）：rnn多层 tf.nn.dynamic_rnn()+ 全连接tf.layers.dense()

末蓝、 2023-07-23 08:59 10阅读 0赞

"""文本分类，RNN模型"""
        def __init__(self):
            # 三个待输入的数据
            self.x = tf.placeholder(tf.int32, [None, config.max_seq_length], name='x')
            self.y = tf.placeholder(tf.float32, [None, config.lables], name='y')
            self.keep_prob = tf.placeholder(tf.float32, name='keep_prob')
            self.rnn()
    
        def rnn(self):
            """rnn模型"""
            def lstm_cell():  # lstm核
                return tf.contrib.rnn.BasicLSTMCell(config.lstm_hidden_size, state_is_tuple=True)
    
            def dropout():  # 为每一个rnn核后面加一个dropout层
                cell = lstm_cell()
                return tf.contrib.rnn.DropoutWrapper(cell, config.keep_prob)
    
            # 词向量映射
            with tf.name_scope("embedding"):
                embedding = tf.get_variable('embedding', [config.vocab_size, config.embedding_dim])
                embedding_inputs = tf.nn.embedding_lookup(embedding, self.x)
    
            with tf.name_scope("rnn"):
                # 多层rnn网络
                cells = [dropout() for _ in range(3)]
                rnn_cell = tf.contrib.rnn.MultiRNNCell(cells, state_is_tuple=True)
    
                _outputs, _ = tf.nn.dynamic_rnn(cell=rnn_cell, inputs=embedding_inputs, dtype=tf.float32)
                # _outputs [batch_size, n_step, lstm_hidden_size]
                last = _outputs[:, -1, :]  # 取最后一个时序输出作为结果
    
            with tf.name_scope("score"):
                # 全连接层，后面接dropout以及relu激活
                fc = tf.layers.dense(last, config.lstm_hidden_size, name='fc1')
                fc = tf.contrib.layers.dropout(fc, config.keep_prob)
                fc = tf.nn.relu(fc)
                # 分类器
                self.logits = tf.layers.dense(fc, config.lables, name='fc2')
                self.y_pred_cls = tf.argmax(tf.nn.softmax(self.logits), 1)  # 预测类别
    
            with tf.name_scope("optimize"):
                # 损失函数，交叉熵
                cross_entropy = tf.nn.softmax_cross_entropy_with_logits(logits=self.logits, labels=self.y)
                self.loss = tf.reduce_mean(cross_entropy)
                # 优化器
                self.train_op = tf.train.AdamOptimizer(learning_rate=config.learning_rate).minimize(self.loss)
    
            with tf.name_scope("accuracy"):
                # 准确率
                correct_pred = tf.equal(tf.argmax(self.y, 1), self.y_pred_cls)
                self.accuracy = tf.reduce_mean(tf.cast(correct_pred, tf.float32))