tensorflow单变量线性回归

import tensorflow as tf
import matplotlib.pyplot as plt
import numpy as np
import os
# 取消红字
os.environ["TF_CPP_MIN_LOG_LEVEL"] = '2'
def model(x, w, b):
    return tf.multiply(x, w)+b
if __name__ == "__main__":
    np.random.seed(5)
    x_data = np.linspace(-1, 1, 100)
    y_data = 2*x_data+1.0 + np.random.randn(*x_data.shape) *0.4
    # 画图
    plt.scatter(x_data, y_data)     # 散点图
    plt.plot(x_data, 1.0+2*x_data, color='r', linewidth=3)


    x = tf.placeholder('float', name='x')
    y = tf.placeholder('float', name='y')
    w = tf.Variable(1.0, name='w0')
    b = tf.Variable(0.0, name='b0')
    pred = model(x, w, b)

    train_epochs = 10
    learning_rate = 0.01
    loss_function = tf.reduce_mean(tf.square(y-pred))
    optimizer = tf.train.GradientDescentOptimizer(learning_rate).minimize(loss_function)
    init = tf.global_variables_initializer()
    with tf.Session() as sess:
        sess.run(init)
        for epoch in range (train_epochs):
            for xs,ys in zip(x_data, y_data):
                _, loss = sess.run([optimizer, loss_function], feed_dict={x:xs, y:ys})
            b0tmp = b.eval(sess)
            w0tmp = w.eval(sess)
            plt.plot(x_data, b0tmp + w0tmp * x_data, color='b', linewidth=3)
            print(b0tmp, w0tmp)
    plt.show()