TensorFlow 分类栗子

# -*- coding: utf-8 -*-
"""
Created on Wed Sep  5 19:53:23 2018

@author: lc
"""

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

#如果没有这个数据集就下载，如果有就运行
mnist=input_data.read_data_sets('MNIST_data/',one_hot=True)

def add_layer(inputs,in_size,out_size,activation_function=None):
    Weights=tf.Variable(tf.random_normal([in_size,out_size]))
    biases=tf.Variable(tf.zeros([1,out_size])+0.1)
    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

xs=tf.placeholder(tf.float32,[None,784])
#不规定有多少个sample，但每个sample有784个像素
ys=tf.placeholder(tf.float32,[None,10])

def compute_accuracy(v_xs,v_ys):
    global prediction
    y_pre=sess.run(prediction,feed_dict={xs:v_xs})
    #把预测得十个数里最大的索引和真实值最大的索引进行比较，一样就代表对的
    correct_prediction=tf.equal(tf.aargmax(y_pre,1),tf.argmax(v_ys,1))
    #计算这一组数据中，有多少是对的，有多少是错的
    accuracy=tf.reduce_mean(tf.cast(correct_prediction,tf.float32))
    result =sess.run(accuracy,feed_dict={xs:v_xs,ys:v_ys})
    return result




#softmax配合交叉熵做分类
prediction=add_layer(xs,784,10,activation_function=tf.nn.softmax)

#交叉熵 loss
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)


sess=tf.Session()
sess.run(tf.initialize_all_variables())

for i in range(1000):
    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))
        #mnist数据集分train和test部分