本文使用TensorFlow实现最简单的线性回归模型，供大家参考，具体内容如下

线性拟合y=2.7x+0.6，代码如下:

import tensorflow as tfimport numpy as npimport matplotlib.pyplot as plt n = 201 # x点数X = np.linspace(-1, 1, n)[:,np.newaxis] # 等差数列构建X，[:,np.newaxis]这个是shape，这一行构建了一个n维列向量（[1,n]的矩阵）noise = np.random.normal(0, 0.5, X.shape) # 噪声值，与X同型Y = X*2.7 + 0.6 + noise # Y xs = tf.placeholder(tf.float32, [None, 1]) # 下面两行是占位符tf.placeholder(dtype, shape)ys = tf.placeholder(tf.float32, [None, 1]) w = tf.Variable(1.1) # 这两行是weight变量，bias变量，括号中是初始值b = tf.Variable(0.2) ypredict = tf.add(w*xs,b) # 根据 w, b 产生的预测值 loss = tf.reduce_sum(tf.pow(ys-ypredict,2.0))/n # 损失函数，tf.reduce_sum()按某一维度元素求和，默认为按列 optimizer = tf.train.GradientDescentOptimizer(0.01).minimize(loss) # 梯度下降优化器，0.01学习率，最小化losss init = tf.global_variables_initializer() # 初始化所有变量 with tf.Session() as sess: sess.run(init) # 运行初始化 for i in range (1000): # 迭代1000次 sess.run(optimizer, feed_dict = {xs:X,ys:Y}) # 运行优化器，梯度下降用到loss，计算loss需要xs, ys所以后面需要feed_dict if i%50==0: # 每隔50次迭代输出w,b,loss # 下面sess.run(w),sess.run(b)里面没有feed_dict是因为打印w,b不需要xs,ys，而打印loss需要 print ("w:",sess.run(w),"\t b:", sess.run(b), "\t loss:", sess.run(loss,feed_dict={xs:X,ys:Y})) plt.plot(X,X*sess.run(w)+sess.run(b)) # 运行迭代之后绘制拟合曲线，这需要在sess里面运行是因为要用到w,b plt.scatter(X,Y) # 绘制被拟合数据（散点） plt.show() # 绘制图像

结果：

w: 1.1106868 b: 0.2086223 loss: 1.2682248w: 1.5626049 b: 0.4772562 loss: 0.7024503w: 1.8849733 b: 0.57508457 loss: 0.47280872w: 2.1149294 b: 0.61071056 loss: 0.36368176w: 2.278966 b: 0.6236845 loss: 0.30917725w: 2.3959787 b: 0.6284093 loss: 0.2815788w: 2.4794474 b: 0.6301298 loss: 0.26755357w: 2.5389886 b: 0.63075644 loss: 0.26041925w: 2.5814607 b: 0.6309848 loss: 0.2567894w: 2.611758 b: 0.6310678 loss: 0.25494233w: 2.6333694 b: 0.6310981 loss: 0.25400248w: 2.6487865 b: 0.631109 loss: 0.2535242w: 2.659784 b: 0.63111293 loss: 0.25328085w: 2.6676288 b: 0.6311139 loss: 0.25315702w: 2.6732242 b: 0.6311139 loss: 0.25309405w: 2.6772156 b: 0.6311139 loss: 0.25306198w: 2.6800632 b: 0.6311139 loss: 0.25304565w: 2.6820953 b: 0.6311139 loss: 0.25303733w: 2.6835444 b: 0.6311139 loss: 0.25303313w: 2.684578 b: 0.6311139 loss: 0.25303096

以上就是本文的全部内容，希望对大家的学习有所帮助，也希望大家多多支持。