边学边总结。
背景：
在基于WiFi指纹数据库的定位算法中，为了减小计算量，需要将指纹数据库进行分区。数据库形式如下所示：
（Rss_1,Rss_2,.....Rss_n,(x_j,y_j),part_j）
其中Rss_i为第i个AP的信号强度，（x_j,y_j）是位置坐标，part_j是该位置所属分区号。
本文基于室内空间特征将指纹库分为了四个区，然后基于TensorFlow框架，搭建神经网络进行训练，并用tensorboard将数据可视化。
输入为：
（Rss_1,Rss_2,.....Rss_n）
输出为：
part_i
加载数据：
#coding: utf8
from numpy import genfromtxt, zeros
def load_data(filename):
with open(filename, 'rb') as dataset:
X = genfromtxt(dataset,delimiter=',',usecols=range(28))
with open(filename, 'rb') as dataset:
y = genfromtxt(dataset,delimiter=',',usecols=(30))
result=[ver(j) for j in y]
result = [x.T[0] for x in result]
a = X.min()
b = X.max()
X -= a # 对 X 进行归一化处理
X /= b
my_data = list(zip(X,result))
return(my_data)
def load_data_wrapper():
training_data = load_data(r'C:\Users\hyl\Desktop\Second_158\Classification_Model\30columns\train_6320_30.csv')
test_data = load_data(r'C:\Users\hyl\Desktop\Second_158\Classification_Model\30columns\test_1550_301.csv')
return (training_data,test_data)
def ver(j):
j = int(j)
e = zeros((4,1))
e[j]=1.0
return e
搭建网络：
# -*- coding: utf-8 -*-
import datas_loader as dl
import tensorflow as tf
from random import shuffle
traind,testd = dl.load_data_wrapper() # 载入数据集
# trd = [x[0] for x in traind] # 训练数据 6320*28
# trd_label = [x[1] for x in traind] # 训练数据的标签 6320*4
ted = [x[0] for x in testd] # 测试数据 1550*28
ted_label = [x[1] for x in testd] # 测试数据的标签 1550*4
batch_size = 40 # 每个批次的大小
n_batch = len(traind)//batch_size # 总批次
# 可视化函数
def variable_summaries(var):
with tf.name_scope("summaries"):
mean = tf.reduce_mean(var)
tf.summary.scalar('mean',mean)
with tf.name_scope('stddev'):
stddev = tf.sqrt(tf.reduce_mean(tf.square(var-mean)))
tf.summary.scalar('stddev',stddev) # 标准差
tf.summary.scalar('max',tf.reduce_max(var)) # 最大值
tf.summary.histogram('histogram',var) # 直方图
# 定义两个 placeholder
with tf.name_scope("input"):
x = tf.placeholder(tf.float32,[None,28])
y = tf.placeholder(tf.float32,[None,4])
# 创建网络
with tf.name_scope('layer'):
with tf.name_scope('wigths'):
w1 = tf.Variable(tf.zeros([28,4]))
variable_summaries(w1)
with tf.name_scope('biases'):
b1 = tf.Variable(tf.zeros([4]))
variable_summaries(b1)
with tf.name_scope('softmax'):
z = tf.nn.softmax(tf.matmul(x,w1)+b1)
# 二次代价函数
with tf.name_scope('loss'):
loss = tf.reduce_mean(tf.nn.softmax_cross_entropy_with_logits(labels=y, logits=z))
tf.summary.scalar('loss',loss)
# 训练
train_step = tf.train.GradientDescentOptimizer(0.005).minimize(loss)
init = tf.global_variables_initializer() # 初始化
# 结果存放在一个布尔型列表中
correct_prediction = tf.equal(tf.argmax(y,1),tf.argmax(z,1))
# 求准确率
with tf.name_scope('accuracy'):
accuracy = tf.reduce_mean(tf.cast(correct_prediction,tf.float32))
tf.summary.scalar('accuracy',accuracy)
# 合并所有的summary
merged = tf.summary.merge_all()
# 定义图
with tf.Session() as sess:
sess.run(init)
writer = tf.summary.FileWriter('logs/',sess.graph)
for epoch in range(15):
shuffle(traind) # 将训练数据顺序打乱
trd = [x[0] for x in traind] # 训练数据 6320*28
trd_label = [x[1] for x in traind] # 训练数据的标签 6320*4
for batch in range(n_batch-1):
trd_i = trd[batch_size*batch:batch_size*(batch+1)]
trd_label_i = trd_label[batch_size*batch:batch_size*(batch+1)]
# merged的返回值存在summary中
summary,_ = sess.run([merged,train_step],feed_dict={x:trd,y:trd_label})
writer.add_summary(summary,epoch) # 将summary写入到文件中
acc = sess.run(accuracy,feed_dict={x:ted,y:ted_label}) # 测试精度
print('Iter'+str(epoch)+',Accuracy: '+str(acc))
print ('end!')
训练结果与可视化：
可以看到准确度达到了95.7%。
用tensorboard查看详细数据：
数据流：
用TensorFlow搭建网络方便多了。