只要有点基础的都能看明白，我就不做过多的解释了！

from tensorflow.examples.tutorials.mnist import input_data
mnist=input_data.read_data_sets("MNIST_data/",one_hot=True)
print(mnist.train.images.shape,mnist.train.labels.shape)
print(mnist.test.images.shape,mnist.test.labels.shape)
print(mnist.validation.images.shape,mnist.validation.labels.shape)

可以得到：

(55000, 784) (55000, 10)
(10000, 784) (10000, 10)
(5000, 784) (5000, 10)

构造模型

import tensorflow as tf

sess = tf.InteractiveSession()
# [None,784] 不限定输入的条数，只是限定输入的维度数
x = tf.placeholder(tf.float32,[None,784])
W = tf.Variable(tf.zeros([784,10]))
b = tf.Variable(tf.zeros([10]))
y = tf.nn.softmax(tf.matmul(x,W)+b)
y_ = tf.placeholder(tf.float32,[None,10])
# 求和、取平均
cross_entropy = tf.reduce_mean(-tf.reduce_sum(y_*tf.log(y),reduction_indices=[1]))
train_step = tf.train.GradientDescentOptimizer(0.5).minimize(cross_entropy)
tf.global_variables_initializer().run()

for i in range(10000):
    batch_xs,batch_ys = mnist.train.next_batch(100)
    train_step.run({x: batch_xs,y_: batch_ys})

correct_prediction = tf.equal(tf.arg_max(y,1),tf.arg_max(y_,1))
accuracy = tf.reduce_mean(tf.cast(correct_prediction,tf.float32))
print(accuracy.eval({x:mnist.test.images,y_:mnist.test.labels}))

执行完的结果：

0.9239