tensorflow入门学习 Lesson2-线性模型构建

主函数

import tensorflow as tf
import os
import linear_mode
import lossfunction

os.environ['TF_CPP_MIN_LOG_LEVEL'] = '2'

w = tf.Variable([.1], dtype=tf.float32)
b = tf.Variable([-.1], dtype=tf.float32)  # 创建y=wx+b

tf.compat.v1.disable_eager_execution()
x = tf.compat.v1.placeholder(dtype=tf.float32)  # 创建x节点
y = tf.compat.v1.placeholder(dtype=tf.float32)

tf.compat.v1.disable_eager_execution()
loss = lossfunction.lossfc(w,x,b,y)

init = tf.compat.v1.global_variables_initializer()

tf.compat.v1.disable_eager_execution()
sess = tf.compat.v1.Session()
sess.run(init)
print(sess.run(init))
print(sess.run(linear_mode.linear(w,x,b), {x: [1, 2, 3, 6, 8]}))

调用函数：

线性模型：

import tensorflow as tf

tf.compat.v1.disable_eager_execution()


def linear(o, p, q):
    k = (o*p) + q
    return k

误差函数：

import linear_mode
import tensorflow as tf

tf.compat.v1.disable_eager_execution()


def lossfc(s1,s2,s3,s4):
    loss = tf.reduce_sum(tf.square(linear_mode.linear(s1,s2,s3) - s4))  # 构建损失函数
    return loss