NLP分类常用模型（一）：一维卷积tf.layers.conv1d() + 全连接tf.layers.dense()

本是古典何须时尚 2023-07-23 08:59 9阅读 0赞

class TextCNN(object):
        """文本分类，CNN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='input_x')
            self.y = tf.placeholder(tf.float32, [None, config.lables], name='input_y')
            self.keep_prob = tf.placeholder(tf.float32, name='keep_prob')
            self.cnn()
    
        def cnn(self):
            """CNN模型"""
            # 词向量映射
            with tf.device('/cpu:0'):
            # with tf.name_scope("emd"):
                embedding = tf.get_variable('embedding', [config.vocab_size, config.embedding_dim])
                embedding_inputs = tf.nn.embedding_lookup(embedding, self.y)
    
            with tf.name_scope("cnn"):
                # CNN layer
                conv = tf.layers.conv1d(embedding_inputs, config.num_filters, config.kernel_size, name='conv')
                # global max pooling layer
                gmp = tf.reduce_max(conv, reduction_indices=[1], name='gmp')
    
            with tf.name_scope("score"):
                # 全连接层，后面接dropout以及relu激活
                fc = tf.layers.dense(gmp, config.conn_hidden_dim_1, name='fc1')
                fc = tf.contrib.layers.dropout(fc, self.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))