classification 分类学习

import tensorflow as tf
from tensorflow.examples.tutorials.mnist import input_data

#softmax和交叉熵结合生成分类算法

#从input_data中读取数据集，使用one_hot编码
mnist = input_data.read_data_sets('MNIST_data',one_hot=True)

#定义添加层
#in_size,out_size输入单位输出单位大小
def add_layer(inputs, in_size,out_size,activation_function=None):
    with tf.name_scope('layer'):
        with tf.name_scope('weights'):
          Weights = tf.Variable(tf.random_normal([in_size,out_size]))#矩阵  #tf.random.normal生成随机数
        with tf.name_scope('biases'):
          biases = tf.Variable(tf.zeros([1,out_size]) + 0.1)#列表
        with tf.name_scope('Wx_plus_b'):
          Wx_plus_b = tf.matmul(inputs,Weights) + biases
        if activation_function is None:
            outputs = Wx_plus_b
        else:
            outputs = activation_function(Wx_plus_b)
        return outputs

def compute_accuracy(v_xs,v_ys):
    global prediction
    y_pre = sess.run(prediction,feed_dict={xs:v_xs,ys:v_ys})
    correct_prediction = tf.equal(tf.argmax(y_pre,1),tf.argmax(v_ys,1))
    accuracy = tf.reduce_mean(tf.cast(correct_prediction,tf.float32))
    result = sess.run(accuracy,feed_dict={xs:v_xs,ys:v_ys})
    return result
xs = tf.placeholder(tf.float32,[None,784])#不规定有多少sample，但是每个sample的大小是28x28
ys = tf.placeholder(tf.float32,[None,10])#不规定有多少输入，但每个sample有十个输出

#add output layer
prediction = add_layer(xs,784,10,activation_function=tf.nn.softmax)

#计算差值 loss
#cross_entropy交叉熵 是损失函数
cross_entropy = tf.reduce_mean(-tf.reduce_sum(ys*tf.log(prediction),reduction_indices=[1]))
train_step = tf.train.GradientDescentOptimizer(0.5).minimize(cross_entropy)
# reducition_indices=[1]按列求和，reducition_indices=[0]按行求和

#会话控制
sess=tf.Session()
sess.run(tf.initialize_all_variables())

for i in range(1000):
    #每100个进行一次梯度下降
    batch_xs,batch_ys = mnist.train.next_batch(100)
    sess.run(train_step,feed_dict={xs:batch_xs,ys:batch_ys})
    if i % 50 == 0:
        print(compute_accuracy(mnist.test.images,mnist.test.labels))

注意：若是无法连接网络

在控制台找到mnist.py,点击进入mnist.py
将

# CVDF mirror of http://yann.lecun.com/exdb/mnist/
#DEFAULT_SOURCE_URL = 'https://storage.googleapis.com/cvdf-datasets/mnist/'

修改为：
#CVDF mirror of http://yann.lecun.com/exdb/mnist/
#DEFAULT_SOURCE_URL = ‘https://storage.googleapis.com/cvdf-datasets/mnist/’
DEFAULT_SOURCE_URL = ‘http://yann.lecun.com/exdb/mnist/’

保存mnist.py