基本Tensorflow示例-预测一条线

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

# 定义输入数据
x_train = np.linspace(-1, 1, 100)
y_train = 2 * x_train + np.random.randn(*x_train.shape) * 0.3

# 可视化训练数据
plt.scatter(x_train, y_train)
plt.xlabel('x')
plt.ylabel('y')
plt.show()

# 定义模型的输入和输出
x = tf.placeholder("float")
y = tf.placeholder("float")

# 定义模型参数
W = tf.Variable(tf.random_normal([1]), name="weight")
b = tf.Variable(tf.zeros([1]), name="bias")

# 定义线性回归模型
pred = tf.add(tf.multiply(x, W), b)

# 定义损失函数（均方差）
cost = tf.reduce_mean(tf.square(pred - y))

# 定义优化器（梯度下降）
optimizer = tf.train.GradientDescentOptimizer(learning_rate=0.01).minimize(cost)

# 定义训练参数
epochs = 100
display_step = 10

# 启动TensorFlow图
with tf.Session() as sess:
    # 初始化所有变量
    sess.run(tf.global_variables_initializer())

    # 开始训练
    for epoch in range(epochs):
        for (x_, y_) in zip(x_train, y_train):
            sess.run(optimizer, feed_dict={x: x_, y: y_})

        # 每隔一定步数显示训练结果
        if (epoch + 1) % display_step == 0:
            c = sess.run(cost, feed_dict={x: x_train, y: y_train})
            print("Epoch:", '%04d' % (epoch + 1), "cost=", "{:.9f}".format(c))

    print("Optimization Finished!")

    # 可视化训练结果
    plt.scatter(x_train, y_train)
    plt.plot(x_train, sess.run(W) * x_train + sess.run(b), 'r')
    plt.xlabel('x')
    plt.ylabel('y')
    plt.show()