TensorFlow实现创建分类器
作者:lilongsy 时间:2022-03-02 03:15:43
本文实例为大家分享了TensorFlow实现创建分类器的具体代码,供大家参考,具体内容如下
创建一个iris数据集的分类器。
加载样本数据集,实现一个简单的二值分类器来预测一朵花是否为山鸢尾。iris数据集有三类花,但这里仅预测是否是山鸢尾。导入iris数据集和工具库,相应地对原数据集进行转换。
# Combining Everything Together
#----------------------------------
# This file will perform binary classification on the
# iris dataset. We will only predict if a flower is
# I.setosa or not.
#
# We will create a simple binary classifier by creating a line
# and running everything through a sigmoid to get a binary predictor.
# The two features we will use are pedal length and pedal width.
#
# We will use batch training, but this can be easily
# adapted to stochastic training.
import matplotlib.pyplot as plt
import numpy as np
from sklearn import datasets
import tensorflow as tf
from tensorflow.python.framework import ops
ops.reset_default_graph()
# 导入iris数据集
# 根据目标数据是否为山鸢尾将其转换成1或者0。
# 由于iris数据集将山鸢尾标记为0,我们将其从0置为1,同时把其他物种标记为0。
# 本次训练只使用两种特征:花瓣长度和花瓣宽度,这两个特征在x-value的第三列和第四列
# iris.target = {0, 1, 2}, where '0' is setosa
# iris.data ~ [sepal.width, sepal.length, pedal.width, pedal.length]
iris = datasets.load_iris()
binary_target = np.array([1. if x==0 else 0. for x in iris.target])
iris_2d = np.array([[x[2], x[3]] for x in iris.data])
# 声明批量训练大小
batch_size = 20
# 初始化计算图
sess = tf.Session()
# 声明数据占位符
x1_data = tf.placeholder(shape=[None, 1], dtype=tf.float32)
x2_data = tf.placeholder(shape=[None, 1], dtype=tf.float32)
y_target = tf.placeholder(shape=[None, 1], dtype=tf.float32)
# 声明模型变量
# Create variables A and b (0 = x1 - A*x2 + b)
A = tf.Variable(tf.random_normal(shape=[1, 1]))
b = tf.Variable(tf.random_normal(shape=[1, 1]))
# 定义线性模型:
# 如果找到的数据点在直线以上,则将数据点代入x2-x1*A-b计算出的结果大于0;
# 同理找到的数据点在直线以下,则将数据点代入x2-x1*A-b计算出的结果小于0。
# x1 - A*x2 + b
my_mult = tf.matmul(x2_data, A)
my_add = tf.add(my_mult, b)
my_output = tf.subtract(x1_data, my_add)
# 增加TensorFlow的sigmoid交叉熵损失函数(cross entropy)
xentropy = tf.nn.sigmoid_cross_entropy_with_logits(logits=my_output, labels=y_target)
# 声明优化器方法
my_opt = tf.train.GradientDescentOptimizer(0.05)
train_step = my_opt.minimize(xentropy)
# 创建一个变量初始化操作
init = tf.global_variables_initializer()
sess.run(init)
# 运行迭代1000次
for i in range(1000):
rand_index = np.random.choice(len(iris_2d), size=batch_size)
# rand_x = np.transpose([iris_2d[rand_index]])
# 传入三种数据:花瓣长度、花瓣宽度和目标变量
rand_x = iris_2d[rand_index]
rand_x1 = np.array([[x[0]] for x in rand_x])
rand_x2 = np.array([[x[1]] for x in rand_x])
#rand_y = np.transpose([binary_target[rand_index]])
rand_y = np.array([[y] for y in binary_target[rand_index]])
sess.run(train_step, feed_dict={x1_data: rand_x1, x2_data: rand_x2, y_target: rand_y})
if (i+1)%200==0:
print('Step #' + str(i+1) + ' A = ' + str(sess.run(A)) + ', b = ' + str(sess.run(b)))
# 绘图
# 获取斜率/截距
# Pull out slope/intercept
[[slope]] = sess.run(A)
[[intercept]] = sess.run(b)
# 创建拟合线
x = np.linspace(0, 3, num=50)
ablineValues = []
for i in x:
ablineValues.append(slope*i+intercept)
# 绘制拟合曲线
setosa_x = [a[1] for i,a in enumerate(iris_2d) if binary_target[i]==1]
setosa_y = [a[0] for i,a in enumerate(iris_2d) if binary_target[i]==1]
non_setosa_x = [a[1] for i,a in enumerate(iris_2d) if binary_target[i]==0]
non_setosa_y = [a[0] for i,a in enumerate(iris_2d) if binary_target[i]==0]
plt.plot(setosa_x, setosa_y, 'rx', ms=10, mew=2, label='setosa')
plt.plot(non_setosa_x, non_setosa_y, 'ro', label='Non-setosa')
plt.plot(x, ablineValues, 'b-')
plt.xlim([0.0, 2.7])
plt.ylim([0.0, 7.1])
plt.suptitle('Linear Separator For I.setosa', fontsize=20)
plt.xlabel('Petal Length')
plt.ylabel('Petal Width')
plt.legend(loc='lower right')
plt.show()
输出:
Step #200 A = [[ 8.70572948]], b = [[-3.46638322]]
Step #400 A = [[ 10.21302414]], b = [[-4.720438]]
Step #600 A = [[ 11.11844635]], b = [[-5.53361702]]
Step #800 A = [[ 11.86427212]], b = [[-6.0110755]]
Step #1000 A = [[ 12.49524498]], b = [[-6.29990339]]
来源:http://blog.csdn.net/lilongsy/article/details/79261129
标签:TensorFlow,分类器
![](/images/zang.png)
![](/images/jiucuo.png)
猜你喜欢
Python操作json数据的一个简单例子
2022-10-23 17:09:37
python工具快速为音视频自动生成字幕(使用说明)
2021-04-14 15:15:26
python代码实现扫码关注公众号登录的实战
2021-11-18 04:40:43
![](https://img.aspxhome.com/file/2023/3/66403_0s.png)
Python selenium 三种等待方式详解(必会)
2021-03-13 16:03:33
python一些性能分析的技巧
2023-07-24 17:55:36
oracle 合并查询 事务 sql函数小知识学习
2023-07-13 15:07:28
php调用快递鸟接口实例代码
2023-11-17 13:48:49
![](https://img.aspxhome.com/file/2023/3/55743_0s.png)
Python学习笔记之open()函数打开文件路径报错问题
2021-10-05 23:25:34
![](https://img.aspxhome.com/file/2023/9/101199_0s.png)
javascript面向对象技术基础(四)
2010-02-07 13:15:00
![](https://img.aspxhome.com/file/UploadPic/20102/7/201027131925891s.jpg)
python线程、进程和协程详解
2023-03-02 14:00:39
Python深拷贝浅拷贝图文示例清晰整理
2022-05-05 11:26:40
![](https://img.aspxhome.com/file/2023/1/99691_0s.jpg)
使用 Django Highcharts 实现数据可视化过程解析
2022-12-27 19:18:51
![](https://img.aspxhome.com/file/2023/8/99238_0s.png)
Python编程基础之输入与输出
2021-03-03 10:06:07
![](https://img.aspxhome.com/file/2023/3/68883_0s.png)
python中py文件与pyc文件相互转换的方法实例
2021-03-29 13:15:27
![](https://img.aspxhome.com/file/2023/5/72165_0s.png)
瀑布流布局浅析
2011-09-16 20:18:09
python正则表达式中匹配次数与贪心问题详解(+ ?*)
2021-04-24 20:52:04
![](https://img.aspxhome.com/file/2023/6/82686_0s.png)
Session.TimeOut的最大取值是1440,超出会报错
2011-03-31 11:19:00
Python制作简易版小工具之计算天数的实现思路
2023-10-29 08:12:07
![](https://img.aspxhome.com/file/2023/4/91874_0s.png)
python multiprocessing模块用法及原理介绍
2021-01-27 06:22:44
asp如何利用当前时间生成随机函数?
2010-01-01 15:44:00