参考教程：http://www.tensorfly.cn/tfdoc/tutorials/mnist_beginners.html

数据下载地址：http://wiki.jikexueyuan.com/project/tensorflow-zh/tutorials/mnist_download.html

环境：windows+Python3.5+tensorflow

python代码

from tensorflow.examples.tutorials.mnist import input_data#加载训练数据MNIST_data_folder=r"D:\WorkSpace\tensorFlow\data"mnist=input_data.read_data_sets(MNIST_data_folder,one_hot=True)# print(mnist.train.next_batch(1))import tensorflow as tf# 建立抽象模型x = tf.placeholder("float", [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("float", [None,10])# 定义损失函数和训练方法cross_entropy = -tf.reduce_sum(y_*tf.log(y))  # 损失函数为交叉熵train_step = tf.train.GradientDescentOptimizer(0.01).minimize(cross_entropy)    # 梯度下降法，学习速率为0.01 # 训练目标：最小化损失函数init = tf.initialize_all_variables()sess = tf.Session()sess.run(init)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})correct_prediction = tf.equal(tf.argmax(y,1), tf.argmax(y_,1))accuracy = tf.reduce_mean(tf.cast(correct_prediction, "float"))print(sess.run(accuracy, feed_dict={x: mnist.test.images, y_: mnist.test.labels}))