TensorFlow（二） Classfication

导入mnist数据集，0-9  10个数字的图片，经过训练后， 预测图片中是哪个数字，运用softmax进行分类，最后计算准确度

from __future__ import print_function
import tensorflow as tf
import numpy as np
import matplotlib.pyplot as plt
import pandas as pd
from tensorflow.examples.tutorials.mnist import input_data

mnist = input_data.read_data_sets('E:/mnist_data', one_hot=True)

def add_layer(inputs, in_size, out_size, activation_function=None):   #添加一个层
    w = tf.Variable(tf.random_normal([in_size, out_size]))   #从正态分布中生成随机值
    b = tf.Variable(tf.zeros([1, out_size]) + 0.1)
    Wx_plus_b = tf.matmul(inputs, w) + b
    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})           #计算出预测值
    correct_prediction = tf.equal(tf.argmax(y_pre, 1), tf.argmax(v_ys, 1))      #看预测值的准确性
    accuracy = tf.reduce_mean(tf.cast(correct_prediction, tf.float32))          #将bool类型转换为dtype类型，并计算均值
    result = sess.run(accuracy, feed_dict={xs:v_xs, ys:v_ys})           #运行，计算准确性并返回
    return result


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

prediction = add_layer(xs, 784, 10, activation_function=tf.nn.softmax)          #经过训练，出一个预测值

loss = tf.reduce_mean(-tf.reduce_sum(ys * tf.log(prediction), reduction_indices=[1]))           #softmax损失函数计算方法
train_step = tf.train.GradientDescentOptimizer(0.5).minimize(loss)                  #训练，梯度下降

sess = tf.Session()

sess.run(tf.initialize_all_variables())                                #初始化
for i in range(1000):
    batch_xs, batch_ys = mnist.train.next_batch(100)                    #按批次训练，每批次100行
    sess.run(train_step, feed_dict={xs:batch_xs, ys: batch_ys})         #执行训练
    if i % 50 == 0:
        print(compute_accuracy(mnist.test.images, mnist.test.labels))       #计算精确度