tensorflow学习过程
第一天
教程:https://morvanzhou.github.io/tutorials/machine-learning/tensorflow/2-1-structure/
import tensorflow as tf
import numpy as np
##create data
x_data = np.random.rand(100).astype(np.float32)
y_data = x_data*0.1+0.3
#create tensorflow structure start
Weights = tf.Variable(tf.random_uniform([1],-1.0,1.0))
biases = tf.Variable(tf.zeros([1]))
y = Weights*x_data + biases
##计算y-y_data,方差(loss)
loss = tf.reduce_mean(tf.square(y-y_data))
##构建优化器
##学习效率0.5
optimizer = tf.train.GradientDescentOptimizer(0.5)
train = optimizer.minimize(loss)
init = tf.initialize_all_variables()
##以上结构已经搭建完成
sess = tf.Session()
sess.run(init) #初始化函数
for step in range(201):
sess.run(train)
if step % 20 == 0:
print(step,sess.run(Weights),sess.run(biases))
大概可以分成五个步骤
1.构建/收集/处理数据
2.搭建网络
3.构建loss计算方案
4.构建优化器
5.运行训练模型