tensorflow linear regression code implementation

# -*-coding: utf-8 -*-
# @Auther       :xxx
# @Time         :2021/11/12 19:10
# @Function     :
import tensorflow as tf
import numpy as np
tf.compat.v1.disable_eager_execution() #保证session能正常运行
x_data=np.random.rand(100).astype(np.float32) #create x数据集
y_data=x_data * 0.1 +0.3 #create y数据集
#create tensorflow structure start#
Weights=tf.Variable(tf.random.uniform([1],-2.0,2.0)) #设置w值维度和取值范围
biases=tf.Variable(tf.zeros([1])) #设置初始biases维度为1，初始值为0
#create tensorflow structure start#
y=Weights*x_data+biases #获取模拟的y值
loss = tf.reduce_mean(tf.square(y-y_data)) #写出损失函数
Optimizer = tf.compat.v1.train.GradientDescentOptimizer(0.5) #设置训练效率为0.5
train=Optimizer.minimize(loss)
#模型已经搭建好
init=tf.compat.v1.global_variables_initializer() #模型初始化
sess=tf.compat.v1.Session() #获取session对象
sess.run(init) #执行初始化
for step in range(400):
	sess.run(train)
	if step % 20==0:
		print(step,sess.run(Weights),sess.run(biases))

result