tensorflow实现线性回归

import tensorflow as tf
import numpy as np
import matplotlib.pyplot as plt

train_X = np.linspace(-1, 1, 100)

train_Y = 2 * train_X + np.random.rand(*train_X.shape) * 0.3

plt.plot(train_X, train_Y, "r.", label="original data")  # r.代表红色小点，可尝试g+替换成绿色加号
plt.legend()  # 添加图例
plt.show()

X = tf.placeholder("float")
Y = tf.placeholder("float")

W = tf.Variable(tf.random_normal([1]), name="weight")
b = tf.Variable(tf.zeros([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)

training_epochs = 20
display_step = 2

with tf.Session() as sess:
    sess.run(tf.global_variables_initializer())
    plotdata = {"batchsize": [], "loss": []}
    for epoch in range(1, training_epochs+1):
        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: train_X, Y: train_Y})
            print("epoch:", epoch, "cost:", loss, "W:", sess.run(W), "b:", sess.run(b))

    print("finished")
    print("cost=", sess.run(cost, feed_dict={X: train_X, Y: train_Y}), "w=", sess.run(W), "b=", sess.run(b))

    plt.plot(train_X, train_Y, 'r.', label="original data")
    plt.plot(train_X, sess.run(W)*train_X + sess.run(b), label="fittedline")
    plt.legend()
    plt.show()