用tensorflow写cnn模型

下面是一个使用 TensorFlow 实现 CNN 模型的示例代码：

import tensorflow as tf

# 定义卷积层
def conv2d(x, W):
    return tf.nn.conv2d(x, W, strides=[1, 1, 1, 1], padding='SAME')

# 定义池化层
def max_pool_2x2(x):
    return tf.nn.max_pool(x, ksize=[1, 2, 2, 1],
                          strides=[1, 2, 2, 1], padding='SAME')

# 定义输入层
x = tf.placeholder(tf.float32, [None, 784])
x_image = tf.reshape(x, [-1,28,28,1])

# 定义第一层卷积层
W_conv1 = tf.Variable(tf.truncated_normal([5, 5, 1, 32], stddev=0.1))
b_conv1 = tf.Variable(tf.constant(0.1, shape=[32]))
h_conv1 = tf.nn.relu(conv2d(x_image, W_conv1) + b_conv1)
h_pool1 = max_pool_2x2(h_conv1)

# 定义第二层卷积层
W_conv2 = tf.Variable(tf.truncated_normal([5, 5, 32, 64], stddev=0.1))
b_conv2 = tf.Variable(tf.constant(0.1, shape=[64]))
h_conv2 = tf.nn.relu(conv2d(h_pool1, W_conv2) + b_conv2)
h_pool2 = max_pool_2x2(h_conv2)

# 定义全连接层
W_fc1 = tf.Variable(tf.truncated_normal([7 * 7 * 64, 1024], stddev=0.1))
b_fc1 = tf.Variable(tf.constant(0.1, shape=[1024]))
h_pool2_flat = tf.reshape(h_pool2, [-1, 7*7*64])
h_fc1 = tf.nn.relu(tf.matmul(h_pool2_flat, W_fc1) + b_fc1)

# 定义 Dropout 层
keep_prob = tf.placeholder(tf.float32)
h_fc1_drop = tf.nn.dropout(h_fc1, keep_prob)

# 定义输出层
W_fc2 = tf.Variable(tf.truncated_normal([1024, 10], stddev=0.1))
b_fc2 = tf.Variable(tf.constant(0.1, shape=[10]))
y_conv = tf.matmul(h_fc1_drop, W_fc2) + b_fc2

# 定义标签
y_ = tf.placeholder(tf.float32, [None, 10])

# 定义损失函数
cross_entropy = tf.reduce_mean(
    tf.nn.softmax_cross_entropy_with_logits(labels=y_, logits=y_conv))

# 定义优化器
train_step = tf.train.AdamOptimizer(1e-4).minimize(cross_entropy)

# 定义评估模型准确率的操作
correct_prediction = tf.equal(tf.argmax(y_conv,1), tf.argmax(y_,1))
accuracy = tf.reduce_mean(tf.cast(correct_prediction, tf.float32))

# 训练模型
with tf.Session() as sess:
    sess.run(tf.global_variables_initializer())
    for i in range(20000):
        batch = mnist.train.next_batch(50)
        if i % 100 == 0:
            train_accuracy = accuracy.eval(feed_dict={
                x: batch[0], y_: batch[1], keep_prob: 1.0})
            print('step %d, training accuracy %g' % (i, train_accuracy))
        train_step.run(feed_dict={x: batch[0], y_: batch[1], keep_prob: 0.5})
    print('test accuracy %g' % accuracy.eval(feed_dict={
        x: mnist.test.images, y_: mnist.test.labels, keep_prob: 1.0}))

在这个例子中，我们使用 TensorFlow 实现了一个简单的 CNN 模型，用于对 MNIST 数据集中的手写数字进行分类。该模型包括两个卷积层、一个全连接层和一个输出层。每个卷积层都包含一个卷积操作和一个最大池化操作，用于提取特征和减小数据规模。全连接层和输出层用于将特征转换为分类结果。训练过程使用 Adam 优化器和 Dropout 技术进行正则化，以提高模型的泛化能力。