用tensorflow实现弹性网络回归算法
作者:xckkcxxck 时间:2023-07-21 16:52:18
本文实例为大家分享了tensorflow实现弹性网络回归算法,供大家参考,具体内容如下
python代码:
#用tensorflow实现弹性网络算法(多变量)
#使用鸢尾花数据集,后三个特征作为特征,用来预测第一个特征。
#1 导入必要的编程库,创建计算图,加载数据集
import matplotlib.pyplot as plt
import tensorflow as tf
import numpy as np
from sklearn import datasets
from tensorflow.python.framework import ops
ops.get_default_graph()
sess = tf.Session()
iris = datasets.load_iris()
x_vals = np.array([[x[1], x[2], x[3]] for x in iris.data])
y_vals = np.array([y[0] for y in iris.data])
#2 声明学习率,批量大小,占位符和模型变量,模型输出
learning_rate = 0.001
batch_size = 50
x_data = tf.placeholder(shape=[None, 3], dtype=tf.float32) #占位符大小为3
y_target = tf.placeholder(shape=[None, 1], dtype=tf.float32)
A = tf.Variable(tf.random_normal(shape=[3,1]))
b = tf.Variable(tf.random_normal(shape=[1,1]))
model_output = tf.add(tf.matmul(x_data, A), b)
#3 对于弹性网络回归算法,损失函数包括L1正则和L2正则
elastic_param1 = tf.constant(1.)
elastic_param2 = tf.constant(1.)
l1_a_loss = tf.reduce_mean(abs(A))
l2_a_loss = tf.reduce_mean(tf.square(A))
e1_term = tf.multiply(elastic_param1, l1_a_loss)
e2_term = tf.multiply(elastic_param2, l2_a_loss)
loss = tf.expand_dims(tf.add(tf.add(tf.reduce_mean(tf.square(y_target - model_output)), e1_term), e2_term), 0)
#4 初始化变量, 声明优化器, 然后遍历迭代运行, 训练拟合得到参数
init = tf.global_variables_initializer()
sess.run(init)
my_opt = tf.train.GradientDescentOptimizer(learning_rate)
train_step = my_opt.minimize(loss)
loss_vec = []
for i in range(1000):
rand_index = np.random.choice(len(x_vals), size=batch_size)
rand_x = 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)%250 == 0:
print('Step#' + str(i+1) +'A = ' + str(sess.run(A)) + 'b=' + str(sess.run(b)))
print('Loss= ' +str(temp_loss))
#现在能观察到, 随着训练迭代后损失函数已收敛。
plt.plot(loss_vec, 'k--')
plt.title('Loss per Generation')
plt.xlabel('Generation')
plt.ylabel('Loss')
plt.show()
本文参考书《Tensorflow机器学习实战指南》
来源:http://blog.csdn.net/xckkcxxck/article/details/78992345
标签:tensorflow,回归算法
![](/images/zang.png)
![](/images/jiucuo.png)
猜你喜欢
python中pd.Series()函数的使用
2023-10-04 08:28:05
![](https://img.aspxhome.com/file/2023/3/134993_0s.png)
SQL Server 2008数据挖掘查询任务
2009-03-16 16:50:00
redis查看连接数及php模拟并发创建redis连接的方法
2023-11-16 11:47:14
Python深度学习实战PyQt5菜单和工具栏功能作用
2021-04-04 16:09:40
![](https://img.aspxhome.com/file/2023/9/76899_0s.png)
Python实现简单猜数字游戏
2021-03-22 14:31:50
Go语言的变量定义详情
2024-04-27 15:41:03
Python字符串和文件操作常用函数分析
2023-07-25 08:42:23
pytorch中交叉熵损失(nn.CrossEntropyLoss())的计算过程详解
2021-06-03 09:28:09
![](https://img.aspxhome.com/file/2023/4/80644_0s.jpg)
TensorFlow中权重的随机初始化的方法
2023-01-02 06:11:32
python条件语句和while循环语句
2023-08-31 06:17:56
![](https://img.aspxhome.com/file/2023/1/62581_0s.png)
python实战小游戏之考验记忆力
2023-02-23 14:29:54
![](https://img.aspxhome.com/file/2023/9/133899_0s.png)
Python 批量合并多个txt文件的实例讲解
2022-09-18 07:39:47
python 基本结构语句(函数和模块)
2023-06-14 00:37:56
![](https://img.aspxhome.com/file/2023/5/85175_0s.png)
MySQL中登录与退出超全图文讲解
2024-01-19 20:24:43
![](https://img.aspxhome.com/file/2023/7/89927_0s.png)
在ASP中改善动态分页的性能
2008-05-08 14:27:00
python代码过长的换行方法
2022-12-25 07:19:59
Go语言Handler详细说明
2024-04-27 15:32:50
![](https://img.aspxhome.com/file/2023/9/134049_0s.png)
python标准库OS模块详解
2022-08-21 21:47:06
![](https://img.aspxhome.com/file/2023/2/134612_0s.png)
JS实现选项卡实例详解
2024-04-19 10:43:37
![](https://img.aspxhome.com/file/2023/7/135807_0s.jpg)
Python 做曲线拟合和求积分的方法
2021-03-03 01:46:07