使用tensorflow和mnist数据集做一个简单的数据分类

重点是softmax激活函数和cross-entropy的搭配可以进行多分类的预测

其他的和之前的训练都差不多，有一个计算准确度的函数值得注意

import tensorflow as tf
from tensorflow.examples.tutorials.mnist import input_data
#下载数据集
mnist = input_data.read_data_sets('MNIST_data',one_hot=True)

#添加层的函数，层有输入参数，输出参数，偏置，还有激活函数
def add_layer(inputs,in_size,out_size,activation_function=None):
    #随机初始化参数和偏置
    Weights = tf.Variable(tf.random_normal([in_size,out_size]))
    biases = tf.Variable(tf.zeros([1,out_size])+0.1)
    #计算（W*a+b）
    Wx_plus_b = tf.matmul(inputs,Weights)+biases
    #如果有激励函数就A（W*a+b）
    if activation_function is None:
        outputs = Wx_plus_b
    else:
        outputs = activation_function(Wx_plus_b)
    return outputs

#计算准确度
#输入：测试集图片和标注
#输出：当前训练的神经网络对测试机图片的预测结果的准确度
def compute_accuracy(v_xs,v_ys):
	#全局化predict网
    global prediction
    #使用网络对测试集图片进行预测
    y_pre = sess.run(prediction,feed_dict={xs:v_xs})
    #对比计算准确度
    correct_prediction = tf.equal(tf.arg_max(y_pre,1),tf.arg_max(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

#define placeholder for inputs to network
xs = tf.placeholder(tf.float32,[None,784]) #28*28
ys = tf.placeholder(tf.float32,[None,10])

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

#the error between prediction and data --- loss
#交叉熵。在多分类问题中经常使用
cross_entry  = tf.reduce_mean(-tf.reduce_sum(ys*tf.log(prediction),
                                            reduction_indices=[1]))
#定义训练步骤
train_step = tf.train.GradientDescentOptimizer(0.5).minimize(cross_entry)

sess = tf.Session()
#初始化变量
sess.run(tf.initialize_all_variables())

for i in range(1000):
	#分批加载训练数据
    batch_xs,batch_ys = mnist.train.next_batch(100)
    #训练
    sess.run(train_step,feed_dict={xs:batch_xs,ys:batch_ys})
    #打印准确度
    if i%50 == 0:
        print(compute_accuracy(mnist.test.images,mnist.test.labels))

reference

https://www.bilibili.com/video/av16001891/?p=22