tensorFlow 2.0 线性回归示例

介绍

代码介绍

  • 线性回归,y=Wx+b,W表示权重,b表示偏置
from __future__ import absolute_import, division, print_function
import tensorflow as tf
import numpy as np
import matplotlib.pyplot as plt


# 学习率
learning_rate = 0.01

# 迭代次数
training_steps = 1000

display_step = 50

# 训练数据
X = np.array([3.3,4.4,5.5,6.71,6.93,4.168,9.779,6.182,7.59,2.167,
              7.042,10.791,5.313,7.997,5.654,9.27,3.1])
Y = np.array([1.7,2.76,2.09,3.19,1.694,1.573,3.366,2.596,2.53,1.221,
              2.827,3.465,1.65,2.904,2.42,2.94,1.3])

#  取出数组X的长度
n_samples = X.shape[0]

# 随机初始化权重,偏置
W = tf.Variable(np.random.randn(), name="weight")
b = tf.Variable(np.random.randn(), name="bias")


# 线性回归(Wx+b)
def linear_regression(x):
    return W * x + b


# 均方差
def mean_square(y_pred,y_true):
    return tf.reduce_sum(tf.pow(y_pred - y_true, 2)) / (2 * n_samples)


# 随机梯度下降优化器
optimizer = tf.optimizers.SGD(learning_rate)


# 优化过程
def run_optimization():
    # 将计算封装在GradientTape中以实现自动微分
    with tf.GradientTape() as g:
        pred = linear_regression(X)
        loss = mean_square(pred, Y)

    # 计算梯度
    # print("loss is ", loss)
    gradients = g.gradient(loss, [W, b])

    # 按gradients更新 W 和 b
    optimizer.apply_gradients(zip(gradients, [W, b]))


# 针对给定训练步骤数开始训练
for step in range(1, training_steps + 1):
    # 运行优化以更新W和b值
    run_optimization()

    if step % display_step == 0:
        pred = linear_regression(X)
        loss = mean_square(pred, Y)
        print("step: %i, loss: %f, W: %f, b: %f" % (step, loss, W.numpy(), b.numpy()))

# 绘制图
plt.plot(X, Y, 'ro', label='Original data')
plt.plot(X, np.array(W * X + b), label='Fitted line')
plt.legend()
plt.show()

  • 另外一个版本是指定权重和偏置的:y= x * 0.1 + 0.3 ,权重0.1 偏置0.3
from __future__ import absolute_import, division, print_function
import tensorflow as tf
import numpy as np
import matplotlib.pyplot as plt


# 学习率
learning_rate = 0.05

# 迭代次数
training_steps = 1000

display_step = 20

# 训练数据
x_data = np.random.rand(100).astype(np.float32) 
y_data = x_data * 0.1 + 0.3 #权重0.1 偏置0.3

# 随机初始化权重,偏置
# 权重和偏置
Weights = tf.Variable(tf.random.uniform([1], -1.0, 1.0))

biases = tf.Variable(tf.zeros([1]))


# 随机梯度下降优化器
optimizer = tf.optimizers.SGD(learning_rate)


# 优化过程
def run_optimization():
    # 将计算封装在GradientTape中以实现自动微分
    with tf.GradientTape() as g:
      
        # 预测值y
        y = Weights * x_data + biases
        
        # 损失函数
        loss = tf.reduce_mean(tf.square(y-y_data))

    # 计算梯度
    # print("loss is ", loss)
    gradients = g.gradient(loss, [Weights, biases])

    # 按gradients更新 W 和 b
    optimizer.apply_gradients(zip(gradients, [Weights, biases]))


# 针对给定训练步骤数开始训练
for step in range(1, training_steps + 1):
    # 运行优化以更新W和b值
    run_optimization()

    if step % display_step == 0:
        # 预测值y
        y = Weights * x_data + biases
        
        # 损失函数
        loss = tf.reduce_mean(tf.square(y-y_data))


        print("step: %i, loss: %f, W: %f, b: %f" % (step, loss, Weights.numpy(), biases.numpy()))

# 绘制图
plt.plot(x_data, y_data, 'ro', label='Original data')
plt.plot(x_data, np.array(Weights * x_data + biases), label='Fitted line')
plt.legend()
plt.show()
  • 打印结果发现,权重基本向0.1,偏置基本向0.3靠拢
step: 20, loss: 0.031721, W: -0.491671, b: 0.560534
step: 40, loss: 0.021747, W: -0.396559, b: 0.561665
step: 60, loss: 0.016477, W: -0.331112, b: 0.530155
step: 80, loss: 0.012491, W: -0.275286, b: 0.500551
...
step: 920, loss: 0.000000, W: 0.098881, b: 0.300598
step: 940, loss: 0.000000, W: 0.099026, b: 0.300521
step: 960, loss: 0.000000, W: 0.099152, b: 0.300453
step: 980, loss: 0.000000, W: 0.099261, b: 0.300395
step: 1000, loss: 0.000000, W: 0.099357, b: 0.300344

其他

©著作权归作者所有,转载或内容合作请联系作者
平台声明:文章内容(如有图片或视频亦包括在内)由作者上传并发布,文章内容仅代表作者本人观点,简书系信息发布平台,仅提供信息存储服务。

推荐阅读更多精彩内容