渐变下降不起作用

Question

我正在学习斯坦福大学的课程，以及＃34; TensorFlow for Deep Learning Research＆＃34;。我已经从以下address获取了代码。在探索tensorflow时我改变了

Y_predicted = X * w + b

作为

Y_predicted = X * X * w + X * u + b

检查非线性曲线是否更好。我添加了

Y_predicted = X * X * w + X * u + b

根据作者对此note(page 3)的建议。但在添加此行并再次运行类似代码后，每个错误值似乎都会 nan 。 任何人都可以指出问题并提出解决方案。

""" Simple linear regression example in TensorFlow
This program tries to predict the number of thefts from 
the number of fire in the city of Chicago
Author: Chip Huyen
Prepared for the class CS 20SI: "TensorFlow for Deep Learning Research"
cs20si.stanford.edu
"""
import os
os.environ['TF_CPP_MIN_LOG_LEVEL']='2'

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

#import utils

DATA_FILE = "slr05.xls"

# Step 1: read in data from the .xls file
book = xlrd.open_workbook(DATA_FILE, encoding_override="utf-8")
sheet = book.sheet_by_index(0)
data = np.asarray([sheet.row_values(i) for i in range(1, sheet.nrows)])
n_samples = sheet.nrows - 1

# Step 2: create placeholders for input X (number of fire) and label Y (number of theft)
X = tf.placeholder(tf.float32, name='X')
Y = tf.placeholder(tf.float32, name='Y')

# Step 3: create weight and bias, initialized to 0
w = tf.Variable(0.0, name='weights')
u = tf.Variable(0.0, name='weights2')
b = tf.Variable(0.0, name='bias')

# Step 4: build model to predict Y
#Y_predicted = X * w + b 
Y_predicted = X ​* ​ X ​* ​ w ​+ ​ X ​* ​ u ​+ ​ b

# Step 5: use the square error as the loss function
loss = tf.square(Y - Y_predicted, name='loss')
# loss = utils.huber_loss(Y, Y_predicted)

# Step 6: using gradient descent with learning rate of 0.01 to minimize loss
optimizer = tf.train.GradientDescentOptimizer(learning_rate=0.001).minimize(loss)

with tf.Session() as sess:
    # Step 7: initialize the necessary variables, in this case, w and b
    sess.run(tf.global_variables_initializer()) 

    writer = tf.summary.FileWriter('./graphs/linear_reg', sess.graph)

    # Step 8: train the model
    for i in range(100): # train the model 100 epochs
        total_loss = 0
        for x, y in data:
            # Session runs train_op and fetch values of loss
            _, l = sess.run([optimizer, loss], feed_dict={X: x, Y:y}) 
            total_loss += l
        print('Epoch {0}: {1}'.format(i, total_loss/n_samples))

    # close the writer when you're done using it
    writer.close() 

    # Step 9: output the values of w and b
    w, u , b = sess.run([w, u , b]) 

# plot the results
X, Y = data.T[0], data.T[1]
plt.plot(X, Y, 'bo', label='Real data')
plt.plot(X, X * x * w + X * u + b, 'r', label='Predicted data')
plt.legend()
plt.show()

Answer 1

糟糕！你的学习率似乎太大了，试试类似learning_rate=0.0000001的东西，它会收敛。这是一个常见问题，特别是在您引入交互功能时，如您的情况：您应该记住x**2的范围会更大（如果原始值为[-100] [100]二次方将是[-10000,10000]），因此对于多项式，对于线性模型而言良好工作的学习率可能太大。查看feature scaling。这张照片给出了一个更直观的解释：

希望它有所帮助！ 安德烈

Answer 2

我是那门课程的人。就像@fr_andres说的那样，你的lr可能太大了。如果这不起作用，请告诉我。