我在处理线性回归问题时没有得到输出。这是一个简单的单变量线性回归问题。我使用了Kaggle的线性回归数据集，
来自这里：Linear Regression on Random Dataset

它没有给出期望的输出。它给出的权重和偏置值是nan

import tensorflow as tfimport matplotlib.pyplot as pltimport numpy as npimport pandas as pd# In[20]:#Getting DataFramestrain_data = pd.read_csv('train.csv')test_data = pd.read_csv('test.csv')#Dropping NaN rowstrain_data.dropna()test_data.dropna()#Getting features and labelsX_train = train_data.iloc[:,0].valuesY_train = train_data.iloc[:,1].valuestest_X = test_data.iloc[:,0].valuestest_Y = test_data.iloc[:,1].values#Plotting Training Dataplt.scatter(X_train,Y_train)# In[58]:#Training the modelX = tf.placeholder(tf.float32,name='X')Y = tf.placeholder(tf.float32,name='Y')W = tf.Variable(tf.random_normal([]),dtype=tf.float32,name='weights')b = tf.Variable(tf.random_normal([]),dtype=tf.float32,name='bias')Y_pred = W*X + bcost = tf.square(Y_pred,name='cost')optimizer = tf.train.GradientDescentOptimizer(learning_rate=0.001).minimize(cost)init = tf.global_variables_initializer()# In[61]:with tf.Session() as sess:    sess.run(init)    for i in range(1000):        sess.run(optimizer,feed_dict={X:X_train,Y:Y_train})    W_out,b_out = sess.run([W,b])    writer = tf.summary.FileWriter('./graphs/linear_reg', sess.graph)print(W_out,b_out)# In[60]:#plt.plot(X_train, W_out*X_train + b_out, color='red')plt.scatter(X_train,Y_train)plt.plot(X_train, W_out*X_train + b_out, color='red')

并且它给出的输出是：

nan nan

权重和偏置值变成了nan。

回答：

你没有为权重和偏置赋值。你定义的权重是

W = tf.Variable(tf.random_normal([]),dtype=tf.float32,name='weights')b = tf.Variable(tf.random_normal([]),dtype=tf.float32,name='bias')

这里，tf.random_normal的输入是一个空数组。因此，W和b都是空的。你需要指定W和b的形状，其中W的形状应为[in_dim, out_dim]，而b的形状应为[out_dim]。请查看tf.random_normal的文档，这里第一个参数是所需张量的形状。