TensorFlow——LinearRegression简单模型代码

提示：扫一扫查出行
【扫一扫了解最新限行尾号】
复制提示

代码函数详解

tf.random.truncated_normal()函数

tf.truncated_normal函数随机生成正态分布的数据，生成的数据是截断的正态分布，截断的标准是2倍的stddev。

zip()函数

zip() 函数用于将可迭代对象作为参数，将对象中对应的元素打包成一个个元组，然后返回由这些元组组成的对象。如果各个可迭代对象的元素个数不一致，则返回的对象长度与最短的可迭代对象相同。利用 * 号操作符，与zip相反，进行解压。

import tensorflow as tf

import numpy as np

import matplotlib.pyplot as plt

train_x = np.linspace(-5, 3, 50)

train_y = train_x * 5 + 10 + np.random.random(50) * 10 - 5

plt.plot(train_x, train_y, 'r.')

plt.grid(True)

plt.show()

X = tf.placeholder(dtype=tf.float32)

Y = tf.placeholder(dtype=tf.float32)

w = tf.Variable(tf.random.truncated_normal([1]), name='Weight')

b = tf.Variable(tf.random.truncated_normal([1]), name='bias')

z = tf.multiply(X, w) + b

cost = tf.reduce_mean(tf.square(Y - z))

learning_rate = 0.01

optimizer = tf.train.GradientDescentOptimizer(learning_rate).minimize(cost)

init = tf.global_variables_initializer()

training_epochs = 20

display_step = 2

with tf.Session() as sess:

    sess.run(init)

    loss_list = []

    for epoch in range(training_epochs):

        for (x, y) in zip(train_x, train_y):

            sess.run(optimizer,feed_dict={X:x, Y:y})

        if epoch % display_step == 0:

            loss = sess.run(cost, feed_dict={X:x, Y:y})

            loss_list.append(loss)

            print('Iter: ', epoch, ' Loss: ', loss)

    w_, b_ = sess.run([w, b], feed_dict={X: x, Y: y})

    print(" Finished ")

    print("W: ", w_, " b: ", b_, " loss: ", loss)

    plt.plot(train_x, train_x*w_ + b_, 'g-', train_x, train_y, 'r.')

    plt.grid(True)

    plt.show()