tensorflow每个变量封装了一个程序，需要通过sess.run 进行调用

接下来我们使用一下使用mnist数据，这是一个手写图像的数据，训练集是55000*28*28, 测试集10000* 28*28 

第一步：导入数据

import numpy as npimport tensorflow as tfimport matplotlib.pyplot as pltfrom tensorflow.examples.tutorials.mnist import input_data # 导入数据mnist = input_data.read_data_sets('data/', one_hot=True)print (" tpye of 'mnist' is %s" % (type(mnist)))print (" number of trian data is %d" % (mnist.train.num_examples))print (" number of test data is %d" % (mnist.test.num_examples))training = mnist.train.imagestraininglable = mnist.train.labelstesting = mnist.test.imagestestinglabel = mnist.test.labels

第二步：初识化变量

#初始化x和yx = tf.placeholder('float', [None, 784])y = tf.placeholder('float', [None, 10])# 初始化W和b W = tf.Variable(tf.zeros([784, 10]))b = tf.Variable(tf.zeros([10]))sess = tf.Session()

第三步： 构造初始化函数 

# 构造多分类方程actv = tf.nn.softmax(tf.matmul(x, W) + b)# 构造代价函数y*log(y1), y1表示的是预测值cost = tf.reduce_mean(-tf.reduce_sum(y*tf.log(actv), reduction_indices=1))#训练模型learning_rate = 0.01#优化模型，使得cost最小化optm = tf.train.GradientDescentOptimizer(learning_rate).minimize(cost)# 预测结果的最大值索引与真实值的索引进行比对, tf.argmax( , 1) #找出一行中的最大值的索引pred = tf.equal(tf.argmax(actv, 1), tf.argmax(y, 1))# 计算正确率, tf.cast 把布尔值转换为数字形式accr = tf.reduce_mean(tf.cast(pred, 'float'))

第四步：迭代优化参数

init = tf.global_variables_initializer()# 训练次数train_epoches = 50# 每次抽取样本数batch_size = 100# 每5次循环打印一次结果display_step = 5sess = tf.Session()sess.run(init)for train_epoch in range(train_epoches):    avg_cost = 0    # 每次选取100个数据，循环的次数    num_batch = int(mnist.train.num_examples/batch_size)    for i in range(num_batch):        # 抽取数据        bacth_x, bacth_y = mnist.train.next_batch(batch_size)        # 进行cost优化        sess.run(optm, feed_dict={x:bacth_x, y:bacth_y})        # 加上cost的值        feeds = {x:bacth_x, y:bacth_y}        avg_cost += sess.run(cost, feed_dict=feeds)/num_batch    # 每5次打印一次结果    if train_epoch % display_step == 0:        feeds_train = {x:bacth_x, y:bacth_y}        feed_test = {x:mnist.test.images, y:mnist.test.labels}        # 计算训练集的准确率, feed_dict的参数        train_acc = sess.run(accr, feed_dict=feeds_train)        # 计算测试集的准确率        test_acc = sess.run(accr, feed_dict=feed_test)        print("Epoch: %03d/%03d cost: %.9f train_acc: %.3f test_acc: %.3f"              % (train_epoch, train_epoches, avg_cost, train_acc, test_acc))