简单的 TensorFlow CNN 二分类器示例

以下是一个使用TensorFlow实现CNN进行文本二分类的Python代码示例，其中包括了一个简单的数据示例： ```python import tensorflow as tf # 定义超参数 embedding_size = 50 filter_sizes = [3, 4, 5] num_filters = 128 dropout_keep_prob = 0.5 l2_reg_lambda = 0.0 learning_rate = 1e-3 # 定义输入数据 input_x = tf.placeholder(tf.float32, [None, sequence_length, embedding_size], name="input_x") input_y = tf.placeholder(tf.float32, [None, num_classes], name="input_y") dropout_keep_prob = tf.placeholder(tf.float32, name="dropout_keep_prob") # 定义卷积层 pooled_outputs = [] for i, filter_size in enumerate(filter_sizes): with tf.name_scope("conv-maxpool-%s" % filter_size): # 卷积层 filter_shape = [filter_size, embedding_size, 1, num_filters] W = tf.Variable(tf.truncated_normal(filter_shape, stddev=0.1), name="W") b = tf.Variable(tf.constant(0.1, shape=[num_filters]), name="b") conv = tf.nn.conv2d( input_x_expanded, W, strides=[1, 1, 1, 1], padding="VALID", name="conv") # 非线性激活函数 h = tf.nn.relu(tf.nn.bias_add(conv, b), name="relu") # 最大池化层 pooled = tf.nn.max_pool( h, ksize=[1, sequence_length - filter_size + 1, 1, 1], strides=[1, 1, 1, 1], padding='VALID', name="pool") pooled_outputs.append(pooled) # 合并所有池化层的输出 num_filters_total = num_filters * len(filter_sizes) h_pool = tf.concat(pooled_outputs, 3) h_pool_flat = tf.reshape(h_pool, [-1, num_filters_total]) # Dropout层 with tf.name_scope("dropout"): h_drop = tf.nn.dropout(h_pool_flat, dropout_keep_prob) # 全连接层 with tf.name_scope("output"): W = tf.get_variable( "W", shape=[num_filters_total, num_classes], initializer=tf.contrib.layers.xavier_initializer()) b = tf.Variable(tf.constant(0.1, shape=[num_classes]), name="b") scores = tf.nn.xw_plus_b(h_drop, W, b, name="scores") predictions = tf.argmax(scores, 1, name="predictions") # 定义损失函数 with tf.name_scope("loss"): losses = tf.nn.softmax_cross_entropy_with_logits(logits=scores, labels=input_y) l2_loss = tf.contrib.layers.apply_regularization(tf.contrib.layers.l2_regularizer(l2_reg_lambda), tf.trainable_variables()) loss = tf.reduce_mean(losses + l2_loss) # 定义优化器 with tf.name_scope("optimizer"): optimizer = tf.train.AdamOptimizer(learning_rate) grads_and_vars = optimizer.compute_gradients(loss) train_op = optimizer.apply_gradients(grads_and_vars) # 训练模型 with tf.Session() as sess: sess.run(tf.global_variables_initializer()) # 示例数据 x_train = [ [0.2, 0.4, 0.6, 0.8, 0.3, 0.1, 0.9, 0.5, 0.7, 0.2], [0.3, 0.6, 0.9, 0.2, 0.5, 0.8, 0.1, 0.7, 0.4, 0.2] ] y_train = [ [0, 1], [1, 0] ] # 训练模型 for i in range(1000): _, loss_val = sess.run([train_op, loss], feed_dict={input_x: x_train, input_y: y_train, dropout_keep_prob: 0.5}) if i % 100 == 0: print("Step %d, Loss: %f" % (i, loss_val)) ``` 上面代码中的示例数据包括两个输入样本，每个样本由10个特征值组成，标签是一个二分类标签。在实际应用中，应该使用更大的数据集进行训练。