参考:
1. https://morvanzhou.github.io/tutorials/machine-learning/tensorflow/2-4-variable/
2. 加载模型的几种方法
https://blog.csdn.net/u011026329/article/details/79190347
3. https://blog.csdn.net/CV_YOU/article/details/80698942
1. 创建数据
import tensorflow as tf
import numpy as np
x_data = np.random.rand(100).astype(np.float32)
y_data = x_data*0.1 + 0.3
2. 搭建模型,给出预测的值,Weight,biases
Weight = tf.Variable(tf.random_uniform([1],-1.0,1.0))
biases = tf.Variable(tf.zeros[1])
y = Weight * x_data + biases
3. 计算误差
loss = tf.reduce_mean(tf.square(y-y_data))
4. 传播误差
optimizer = tf.train.GradientDescentOptimizer(0.5)
train = optimizer.minimize(loss)
5. 初始化
init = tf.global_variables_initializer()
6. Session
sess = tf.Sessipon()
sess.run(init)
for step in range(201):
sess.run(train)
if step % 20 == 0
print(step,sess,run(Weights),sess.run(biases))