写一段python深度学习的代码

以下是一段基于TensorFlow的深度学习Python代码：

import tensorflow as tf

# 定义输入和输出
x = tf.placeholder(tf.float32, [None, 784])
y_ = tf.placeholder(tf.float32, [None, 10])

# 定义权重和偏置
W = tf.Variable(tf.zeros([784, 10]))
b = tf.Variable(tf.zeros([10]))

# 定义模型
y = tf.nn.softmax(tf.matmul(x, W) + b)

# 定义损失函数
cross_entropy = tf.reduce_mean(-tf.reduce_sum(y_ * tf.log(y), reduction_indices=[1]))

# 定义优化器
train_step = tf.train.GradientDescentOptimizer(0.5).minimize(cross_entropy)

# 初始化变量
init = tf.initialize_all_variables()

# 运行模型
sess = tf.Session()
sess.run(init)

# 训练模型
for i in range(1000):
batch_xs, batch_ys = mnist.train.next_batch(100)
sess.run(train_step, feed_dict={x: batch_xs, y_: batch_ys})