TF——线性回归

注释很清楚：

import tensorflow as tf
import os
import numpy as np
import matplotlib.pyplot as plt
os.environ["CUDA_VISIBLE_DEVICES"]="0"
learning_rate=0.01
training_epochs=1000
display_step=50
if __name__ =='__main__':
   train_X = np.asarray(
       [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])
   train_Y = np.asarray(
       [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])
   n_sample=train_X.shape[0]#维度——几行
   print(n_sample)
   '''变量'''
   X=tf.placeholder("float")
   Y=tf.placeholder("float")
   '''模型'''
   W=tf.Variable(np.random.randn(),name="weight")#标准正态分布
   b = tf.Variable(np.random.randn(), name="bias")
   '''线性回归模型
    pred=x*k+b
   '''
   mul=tf.multiply(X,W)
   pred=tf.add(mul,b)

   '''标准方差：
   z=(Y-y)^2+...../n
   '''
   print(2*n_sample)
   cost=tf.reduce_sum(tf.pow(pred-Y,2))/(2*n_sample)

   '''梯度下降法 去最小值，获得最有解'''
   optimizer = tf.train.GradientDescentOptimizer(learning_rate).minimize(cost)
   init = tf.global_variables_initializer()
   with tf.Session() as sess:
       sess.run(init)
       '''训练模型'''
       for epoch in range(training_epochs):
           for(x,y) in zip(train_X,train_Y):
               sess.run(optimizer,feed_dict={X:x,Y:y})

               if(epoch+1)%display_step==0:
                   c=sess.run(cost,feed_dict={X:train_X,Y:train_Y})
                   print("训练次数:", '%04d' % (epoch + 1),
                         "标准差=", "{:.9f}".format(c),
                         "斜率=", sess.run(W),
                         "截距=",sess.run(b))
       print("PPPPPPPPPPPPPPPPPPPPPPPPP")
       training_cost = sess.run(cost, feed_dict={X: train_X, Y: train_Y})
       print("标准差=", training_cost, "斜率=", sess.run(W), "截距=", sess.run(b))
       plt.plot(train_X,train_Y,'ro',label="DATA")
       plt.plot(train_X, sess.run(W)*train_X+sess.run(b), label="Line",color="blue")
       plt.legend()
       plt.show()