本文将遍历批量数据点并让TensorFlow更新斜率和y截距。这次将使用Scikit Learn的内建iris数据集。特别地,我们将用数据点(x值代表花瓣宽度,y值代表花瓣长度)找到最优直线。选择这两种特征是因为它们具有线性关系,在后续结果中将会看到。本文将使用L2正则损失函数。
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
|
# 用TensorFlow实现线性回归算法
#----------------------------------
#
# This function shows how to use TensorFlow to
# solve linear regression.
# y = Ax + b
#
# We will use the iris data, specifically:
# y = Sepal Length
# x = Petal Width
import matplotlib.pyplot as plt
import numpy as np
import tensorflow as tf
from sklearn import datasets
from tensorflow.python.framework import ops
ops.reset_default_graph()
# Create graph
sess = tf.Session()
# Load the data
# iris.data = [(Sepal Length, Sepal Width, Petal Length, Petal Width)]
iris = datasets.load_iris()
x_vals = np.array([x[ 3 ] for x in iris.data])
y_vals = np.array([y[ 0 ] for y in iris.data])
# 批量大小
batch_size = 25
# Initialize 占位符
x_data = tf.placeholder(shape = [ None , 1 ], dtype = tf.float32)
y_target = tf.placeholder(shape = [ None , 1 ], dtype = tf.float32)
# 模型变量
A = tf.Variable(tf.random_normal(shape = [ 1 , 1 ]))
b = tf.Variable(tf.random_normal(shape = [ 1 , 1 ]))
# 增加线性模型,y=Ax+b
model_output = tf.add(tf.matmul(x_data, A), b)
# 声明L2损失函数,其为批量损失的平均值。
loss = tf.reduce_mean(tf.square(y_target - model_output))
# 声明优化器 学习率设为0.05
my_opt = tf.train.GradientDescentOptimizer( 0.05 )
train_step = my_opt.minimize(loss)
# 初始化变量
init = tf.global_variables_initializer()
sess.run(init)
# 批量训练遍历迭代
# 迭代100次,每25次迭代输出变量值和损失值
loss_vec = []
for i in range ( 100 ):
rand_index = np.random.choice( len (x_vals), size = batch_size)
rand_x = np.transpose([x_vals[rand_index]])
rand_y = np.transpose([y_vals[rand_index]])
sess.run(train_step, feed_dict = {x_data: rand_x, y_target: rand_y})
temp_loss = sess.run(loss, feed_dict = {x_data: rand_x, y_target: rand_y})
loss_vec.append(temp_loss)
if (i + 1 ) % 25 = = 0 :
print ( 'Step #' + str (i + 1 ) + ' A = ' + str (sess.run(A)) + ' b = ' + str (sess.run(b)))
print ( 'Loss = ' + str (temp_loss))
# 抽取系数
[slope] = sess.run(A)
[y_intercept] = sess.run(b)
# 创建最佳拟合直线
best_fit = []
for i in x_vals:
best_fit.append(slope * i + y_intercept)
# 绘制两幅图
# 拟合的直线
plt.plot(x_vals, y_vals, 'o' , label = 'Data Points' )
plt.plot(x_vals, best_fit, 'r-' , label = 'Best fit line' , linewidth = 3 )
plt.legend(loc = 'upper left' )
plt.title( 'Sepal Length vs Pedal Width' )
plt.xlabel( 'Pedal Width' )
plt.ylabel( 'Sepal Length' )
plt.show()
# Plot loss over time
# 迭代100次的L2正则损失函数
plt.plot(loss_vec, 'k-' )
plt.title( 'L2 Loss per Generation' )
plt.xlabel( 'Generation' )
plt.ylabel( 'L2 Loss' )
plt.show()
|
结果:
1
2
3
4
5
6
7
8
|
Step #25 A = [[ 1.93474162]] b = [[ 3.11190438]]
Loss = 1.21364
Step #50 A = [[ 1.48641717]] b = [[ 3.81004381]]
Loss = 0.945256
Step #75 A = [[ 1.26089203]] b = [[ 4.221035]]
Loss = 0.254756
Step #100 A = [[ 1.1693294]] b = [[ 4.47258472]]
Loss = 0.281654
|
以上就是本文的全部内容,希望对大家的学习有所帮助,也希望大家多多支持服务器之家。
原文链接:https://blog.csdn.net/lilongsy/article/details/79360458