from __future__ import print_function
import tensorflow as tf
from tensorflow.examples.tutorials.mnist import input_data
# number 1 to 10 data
mnist = input_data.read_data_sets('C:/Users/hubinghua/Desktop/MNIST_data/', one_hot=True)#数据加载
def add_layer(inputs, in_size, out_size, activation_function=None,):
# add one more layer and return the output of this layer
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):#用来计算准确度
global prediction#把prediction设为全局变量
y_pre = sess.run(prediction, feed_dict={xs: v_xs})#y的预测值
correct_prediction = tf.equal(tf.argmax(y_pre,1), tf.argmax(v_ys,1))
#tf.argmax是输出该向量中最大数对应的下标
accuracy = tf.reduce_mean(tf.cast(correct_prediction, tf.float32))
#将correct_prediction转化为浮点数,求平均数就是其正确率
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]) # 28x28
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 real data
cross_entropy = tf.reduce_mean(-tf.reduce_sum(ys * tf.log(prediction),
reduction_indices=[1]))
# loss这个是损失函数,也就是逻辑回归里面的损失函数表达形式,一般用来做分类问题
train_step = tf.train.GradientDescentOptimizer(0.5).minimize(cross_entropy)
sess = tf.Session()
# important step
# tf.initialize_all_variables() no long valid from
# 2017-03-02 if using tensorflow >= 0.12
if int((tf.__version__).split('.')[1]) < 12 and int((tf.__version__).split('.')[0]) < 1:
init = tf.initialize_all_variables()
else:
init = tf.global_variables_initializer()
sess.run(init)
for i in range(1000):
batch_xs, batch_ys = mnist.train.next_batch(100)
#批量梯度下降,每迭代一步随机抽取100个数据去训练,一共迭代一千次,每一次都用100个数据去训练,
#这里用来训练的数据是包里的训练集
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))
#没迭代50次输出训练的精确度,这里测试精确度所用到的数据是包了的测试集
相关解释:
一、
for i in range(1000):
batch_xs, batch_ys = mnist.train.next_batch(100) 这里每迭代一步都从训练集里抽取100个样本数据去训练
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)) 每迭代50次输出训练的精确度,这里输出的精确度所用到的数据是包里的测试集
二、
def compute_accuracy(v_xs, v_ys) 这个函数用来计算准确度,把测试集里的数传过来
global prediction 把prediction设为全局变量
y_pre = sess.run(prediction, feed_dict={xs: v_xs}) 调用prediction函数对测试集结果预测
correct_prediction = tf.equal(tf.argmax(y_pre,1), tf.argmax(v_ys,1)) tf.argmax是输出该向量中最大数对应的下标,其结 果就是把预测出来的向量转换为预测出来的数字而 ti.equal是对括号里面的数对比,相等输出ture,不 相等输出fault,这样correct_prediction就变成了一个 含有fault和ture的向量
accuracy = tf.reduce_mean(tf.cast(correct_prediction, tf.float32))
#将correct_prediction转化为浮点数(1和0的形式), 求平均数就是其正确率
result = sess.run(accuracy, feed_dict={xs: v_xs, ys: v_ys})
return result
三、
cross_entropy = tf.reduce_mean(-tf.reduce_sum(ys * tf.log(prediction),
reduction_indices=[1]))
交叉熵函数:相关解释
四、