Tensorflow 1.x学习记录（四）：Classification 分类学习

import tensorflow as tf
import numpy as np
import matplotlib.pyplot as plt
from tensorflow.examples.tutorials.mnist import input_data

mnist = input_data.read_data_sets('MNIST_data',one_hot = True)  # 自动引入数据包

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

def compute_accuracy(v_xs,v_ys):      #定义功能
    global predition
    y_pre = sess.run(predition,feed_dict={xs:v_xs})
    correct_prediction = tf.equal(tf.argmax(y_pre,1),tf.argmax(v_ys,1)) #预测值与真实值对比,argnax返回最大值的下标，
    #0表示按列比较返回，1表示按行比较返回
    accuracy = tf.reduce_mean(tf.cast(correct_prediction,tf.float32))  #分析对比结果，输出百分比
    result = sess.run(accuracy,feed_dict={xs:v_xs,ys:v_ys})
    return result


xs = tf.placeholder(tf.float32,[None,784])
ys = tf.placeholder(tf.float32,[None,10])  #传值

prediction = add_layer(xs,784,10,activation_function=tf.nn.softmax)  #softmax用来进行classification


cross_entropy = tf.reduce_mean(-tf.reduce_sum(ys * tf.log(prediction),reduction_indices=[1])) #计算loss
train_step = tf.train.GradientDescentOptimizer(0.1).minimize(cross_entropy)

init = tf.global_variables_initializer()
sess = tf.Session()
sess.run(init)

for i in range(1000):
    batch_xs,batch_ys = mnist.train.next_batch(100)  #将数据分流，每次训练100个
    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))