-
Notifications
You must be signed in to change notification settings - Fork 1
Expand file tree
/
Copy pathbp_train.py
More file actions
237 lines (215 loc) · 7.94 KB
/
bp_train.py
File metadata and controls
237 lines (215 loc) · 7.94 KB
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
# coding:UTF-8
'''
Date:20160831
@author: zhaozhiyong
'''
import numpy as np
from math import sqrt
def load_data(file_name):
'''导入数据
input: file_name(string):文件的存储位置
output: feature_data(mat):特征
label_data(mat):标签
n_class(int):类别的个数
'''
# 1、获取特征
f = open(file_name) # 打开文件
feature_data = []
label_tmp = []
for line in f.readlines():
feature_tmp = []
lines = line.strip().split("\t")
for i in xrange(len(lines) - 1):
feature_tmp.append(float(lines[i]))
label_tmp.append(int(lines[-1]))
feature_data.append(feature_tmp)
f.close() # 关闭文件
# 2、获取标签
m = len(label_tmp)
n_class = len(set(label_tmp)) # 得到类别的个数
label_data = np.mat(np.zeros((m, n_class)))
for i in xrange(m):
label_data[i, label_tmp[i]] = 1
return np.mat(feature_data), label_data, n_class
def sig(x):
'''Sigmoid函数
input: x(mat/float):自变量，可以是矩阵或者是任意实数
output: Sigmoid值(mat/float):Sigmoid函数的值
'''
return 1.0 / (1 + np.exp(-x))
def partial_sig(x):
'''Sigmoid导函数的值
input: x(mat/float):自变量，可以是矩阵或者是任意实数
output: out(mat/float):Sigmoid导函数的值
'''
m, n = np.shape(x)
out = np.mat(np.zeros((m, n)))
for i in xrange(m):
for j in xrange(n):
out[i, j] = sig(x[i, j]) * (1 - sig(x[i, j]))
return out
def hidden_in(feature, w0, b0):
'''计算隐含层的输入
input: feature(mat):特征
w0(mat):输入层到隐含层之间的权重
b0(mat):输入层到隐含层之间的偏置
output: hidden_in(mat):隐含层的输入
'''
m = np.shape(feature)[0]
hidden_in = feature * w0
for i in xrange(m):
hidden_in[i, ] += b0
return hidden_in
def hidden_out(hidden_in):
'''隐含层的输出
input: hidden_in(mat):隐含层的输入
output: hidden_output(mat):隐含层的输出
'''
hidden_output = sig(hidden_in)
return hidden_output;
def predict_in(hidden_out, w1, b1):
'''计算输出层的输入
input: hidden_out(mat):隐含层的输出
w1(mat):隐含层到输出层之间的权重
b1(mat):隐含层到输出层之间的偏置
output: predict_in(mat):输出层的输入
'''
m = np.shape(hidden_out)[0]
predict_in = hidden_out * w1
for i in xrange(m):
predict_in[i, ] += b1
return predict_in
def predict_out(predict_in):
'''输出层的输出
input: predict_in(mat):输出层的输入
output: result(mat):输出层的输出
'''
result = sig(predict_in)
return result
def bp_train(feature, label, n_hidden, maxCycle, alpha, n_output):
'''计算隐含层的输入
input: feature(mat):特征
label(mat):标签
n_hidden(int):隐含层的节点个数
maxCycle(int):最大的迭代次数
alpha(float):学习率
n_output(int):输出层的节点个数
output: w0(mat):输入层到隐含层之间的权重
b0(mat):输入层到隐含层之间的偏置
w1(mat):隐含层到输出层之间的权重
b1(mat):隐含层到输出层之间的偏置
'''
m, n = np.shape(feature)
# 1、初始化
w0 = np.mat(np.random.rand(n, n_hidden))
w0 = w0 * (8.0 * sqrt(6) / sqrt(n + n_hidden)) - \
np.mat(np.ones((n, n_hidden))) * \
(4.0 * sqrt(6) / sqrt(n + n_hidden))
b0 = np.mat(np.random.rand(1, n_hidden))
b0 = b0 * (8.0 * sqrt(6) / sqrt(n + n_hidden)) - \
np.mat(np.ones((1, n_hidden))) * \
(4.0 * sqrt(6) / sqrt(n + n_hidden))
w1 = np.mat(np.random.rand(n_hidden, n_output))
w1 = w1 * (8.0 * sqrt(6) / sqrt(n_hidden + n_output)) - \
np.mat(np.ones((n_hidden, n_output))) * \
(4.0 * sqrt(6) / sqrt(n_hidden + n_output))
b1 = np.mat(np.random.rand(1, n_output))
b1 = b1 * (8.0 * sqrt(6) / sqrt(n_hidden + n_output)) - \
np.mat(np.ones((1, n_output))) * \
(4.0 * sqrt(6) / sqrt(n_hidden + n_output))
# 2、训练
i = 0
while i <= maxCycle:
# 2.1、信号正向传播
# 2.1.1、计算隐含层的输入
hidden_input = hidden_in(feature, w0, b0) # mXn_hidden
# 2.1.2、计算隐含层的输出
hidden_output = hidden_out(hidden_input)
# 2.1.3、计算输出层的输入
output_in = predict_in(hidden_output, w1, b1) # mXn_output
# 2.1.4、计算输出层的输出
output_out = predict_out(output_in)
# 2.2、误差的反向传播
# 2.2.1、隐含层到输出层之间的残差
delta_output = -np.multiply((label - output_out), partial_sig(output_in))
# 2.2.2、输入层到隐含层之间的残差
delta_hidden = np.multiply((delta_output * w1.T), partial_sig(hidden_input))
# 2.3、 修正权重和偏置
w1 = w1 - alpha * (hidden_output.T * delta_output)
b1 = b1 - alpha * np.sum(delta_output, axis=0) * (1.0 / m)
w0 = w0 - alpha * (feature.T * delta_hidden)
b0 = b0 - alpha * np.sum(delta_hidden, axis=0) * (1.0 / m)
if i % 100 == 0:
print "\t-------- iter: ", i, \
" ,cost: ", (1.0/2) * get_cost(get_predict(feature, w0, w1, b0, b1) - label)
i += 1
return w0, w1, b0, b1
def get_cost(cost):
'''计算当前损失函数的值
input: cost(mat):预测值与标签之间的差
output: cost_sum / m (double):损失函数的值
'''
m,n = np.shape(cost)
cost_sum = 0.0
for i in xrange(m):
for j in xrange(n):
cost_sum += cost[i,j] * cost[i,j]
return cost_sum / m
def get_predict(feature, w0, w1, b0, b1):
'''计算最终的预测
input: feature(mat):特征
w0(mat):输入层到隐含层之间的权重
b0(mat):输入层到隐含层之间的偏置
w1(mat):隐含层到输出层之间的权重
b1(mat):隐含层到输出层之间的偏置
output: 预测值
'''
return predict_out(predict_in(hidden_out(hidden_in(feature, w0, b0)), w1, b1))
def save_model(w0, w1, b0, b1):
'''保存最终的模型
input: w0(mat):输入层到隐含层之间的权重
b0(mat):输入层到隐含层之间的偏置
w1(mat):隐含层到输出层之间的权重
b1(mat):隐含层到输出层之间的偏置
output:
'''
def write_file(file_name, source):
f = open(file_name, "w")
m, n = np.shape(source)
for i in xrange(m):
tmp = []
for j in xrange(n):
tmp.append(str(source[i, j]))
f.write("\t".join(tmp) + "\n")
f.close()
write_file("weight_w0", w0)
write_file("weight_w1", w1)
write_file("weight_b0", b0)
write_file("weight_b1", b1)
def err_rate(label, pre):
'''计算训练样本上的错误率
input: label(mat):训练样本的标签
pre(mat):训练样本的预测值
output: rate[0,0](float):错误率
'''
m = np.shape(label)[0]
err = 0.0
for i in xrange(m):
if label[i, 0] != pre[i, 0]:
err += 1
rate = err / m
return rate
if __name__ == "__main__":
# 1、导入数据
print "--------- 1.load data ------------"
feature, label, n_class = load_data("data.txt")
# 2、训练网络模型
print "--------- 2.training ------------"
w0, w1, b0, b1 = bp_train(feature, label, 20, 1000, 0.1, n_class)
# 3、保存最终的模型
print "--------- 3.save model ------------"
save_model(w0, w1, b0, b1)
# 4、得到最终的预测结果
print "--------- 4.get prediction ------------"
result = get_predict(feature, w0, w1, b0, b1)
print "训练准确性为：", (1 - err_rate(np.argmax(label, axis=1), np.argmax(result, axis=1)))