Tensorflow线性回归

源代码:


import tensorflow as tf
import numpy as np
import matplotlib.pyplot as plt
import os
os.environ["CUDA_VISIBLE_DEVICES"]="0"

#设置训练参数,learning_rate=0.01,training_epochs=1000,display_step=50
learning_rate=0.01
training_epochs=1000
display_step=50
#创建训练数据
train_X=np.asarray([3.3,4.4,5.5,6.71,6.93,4.168,9.779,6.182,7.59,2.167,
7.042,10.791,5.313,7.997,5.654,9.27,3.1])
train_Y=np.asarray([1.7,2.76,2.09,3.19,1.694,1.573,3.366,2.596,2.53,1.221,
2.827,3.465,1.65,2.904,2.42,2.94,1.3])
n_samples=train_X.shape[0]
#构造计算图,使用变量Variable构造变量X,Y,代码如下:
X=tf.placeholder("float")
Y=tf.placeholder("float")
#设置模型的初始权重
W=tf.Variable(np.random.randn(),name="weight")
b=tf.Variable(np.random.randn(),name='bias')
#构造线性回归模型
pred=tf.add(tf.multiply(X,W),b)
#求损失函数,即均方差
cost=tf.reduce_sum(tf.pow(pred-Y,2))/(2*n_samples)
#使用梯度下降法求最小值,即最优解
optimizer=tf.train.GradientDescentOptimizer(learning_rate).minimize(cost)
#初始化全部变量
init =tf.global_variables_initializer()
#使用tf.Session()创建Session会话对象,会话封装了Tensorflow运行时的状态和控制。
with tf.Session() as sess:
sess.run(init)
#调用会话对象sess的run方法,运行计算图,即开始训练模型。
#Fit all training data
for epoch in range(training_epochs):
for (x,y) in zip(train_X,train_Y):
sess.run(optimizer,feed_dict={X:x,Y:y})

#Display logs per epoch step
if (epoch+1) % display_step==0:
c=sess.run(cost,feed_dict={X:train_X,Y:train_Y})
print("Epoch:" ,'%04d' %(epoch+1),"cost=","{:.9f}".format(c),"W=",sess.run(W),"b=",sess.run(b))
#打印训练模型的代价函数。
training_cost=sess.run(cost,feed_dict={X:train_X,Y:train_Y})
print("Train cost=",training_cost,"W=",sess.run(W),"b=",sess.run(b))
#可视化,展现线性模型的最终结果。
plt.plot(train_X,train_Y,'ro',label='Original data')
plt.plot(train_X,sess.run(W)*train_X+sess.run(b),label="Fitting line")
plt.legend()
plt.show()
 

结果截图:

 

 

 

 遇到的问题:

This application failed to start because it could not find or load the Qt platform plugin “windows”.
Reinstalling the application may fix this problem.

解决方法:

把platforms文件夹拷贝到python.exe同级目录下。

posted on 2021-01-09 11:00  嘻嘻_嘻  阅读(122)  评论(0编辑  收藏  举报