用tensorflow写alexnet代码

以下是用TensorFlow实现AlexNet的示例代码：

import tensorflow as tf

# 定义输入
x = tf.placeholder(tf.float32, [None, 227, 227, 3])
y = tf.placeholder(tf.float32, [None, 1000])

# 第一层卷积
conv1 = tf.layers.conv2d(
    inputs=x,
    filters=96,
    kernel_size=[11, 11],
    strides=(4, 4),
    padding='valid',
    activation=tf.nn.relu)

# 最大池化层
pool1 = tf.layers.max_pooling2d(
    inputs=conv1,
    pool_size=[3, 3],
    strides=(2, 2),
    padding='valid')

# 第二层卷积
conv2 = tf.layers.conv2d(
    inputs=pool1,
    filters=256,
    kernel_size=[5, 5],
    strides=(1, 1),
    padding='same',
    activation=tf.nn.relu)

# 最大池化层
pool2 = tf.layers.max_pooling2d(
    inputs=conv2,
    pool_size=[3, 3],
    strides=(2, 2),
    padding='valid')

# 第三层卷积
conv3 = tf.layers.conv2d(
    inputs=pool2,
    filters=384,
    kernel_size=[3, 3],
    strides=(1, 1),
    padding='same',
    activation=tf.nn.relu)

# 第四层卷积
conv4 = tf.layers.conv2d(
    inputs=conv3,
    filters=384,
    kernel_size=[3, 3],
    strides=(1, 1),
    padding='same',
    activation=tf.nn.relu)

# 第五层卷积
conv5 = tf.layers.conv2d(
    inputs=conv4,
    filters=256,
    kernel_size=[3, 3],
    strides=(1, 1),
    padding='same',
    activation=tf.nn.relu)

# 最大池化层
pool5 = tf.layers.max_pooling2d(
    inputs=conv5,
    pool_size=[3, 3],
    strides=(2, 2),
    padding='valid')

# 全连接层1
flatten = tf.layers.flatten(
    inputs=pool5)

fc1 = tf.layers.dense(
    inputs=flatten,
    units=4096,
    activation=tf.nn.relu)

# 全连接层2
fc2 = tf.layers.dense(
    inputs=fc1,
    units=4096,
    activation=tf.nn.relu)

# 输出层
logits = tf.layers.dense(
    inputs=fc2,
    units=1000)

# 定义损失函数和优化器
loss = tf.reduce_mean(tf.nn.softmax_cross_entropy_with_logits(labels=y, logits=logits))
optimizer = tf.train.AdamOptimizer().minimize(loss)

# 训练模型
with tf.Session() as sess:
    sess.run(tf.global_variables_initializer())
    for i in range(num_epochs):
        sess.run(optimizer, feed_dict={x: train_data, y: train_labels})
        if i % 10 == 0:
            print('Epoch:', i, 'Accuracy:', sess.run(accuracy, feed_dict={x: test_data, y: test_labels}))

注意，这里的代码只是AlexNet的简单实现，可能与原始的AlexNet模型实现有一些不同。