Article Directory
foreword
Record the process of completing multiple linear regression using TensorFlow1.x and TensorFlow2.x.
1. Data processing
The Boston house price data set is used here, which contains 506 samples, the input is 12 housing information features, and the output is house price.
Use the pandas library to read the csv file, normalize the data to eliminate the difference in the magnitude of different dimensions, and divide the training set and test set to evaluate the training results.
import pandas as pd
import numpy as np
from sklearn.model_selection import train_test_split
#数据读取
df = pd.read_csv(r'database/boston.csv', header=0)
x_data = np.array(df.values)[:,:12]
y_data = np.array(df.values)[:,12]
#数据归一化
for i in range(12):
x_data[:,i] = x_data[:,i] / (np.max(x_data[:,i]) - np.min(x_data[:,i]))
#数据集划分
x_train, x_test, y_train, y_test = train_test_split(x_data, y_data, test_size=0.3)
#维度变换
x_train = x_train.reshape((-1, 12))
x_test = x_test.reshape((-1, 12))
y_train = y_train.reshape((-1, 1))
y_test = y_test.reshape((-1, 1))
Two, TensorFlow1.x
1. Define the model
import tensorflow.compat.v1 as tf
import matplotlib.pyplot as plt
from sklearn.utils import shuffle
tf.disable_eager_execution()
#使用命名空间对节点打包
with tf.name_scope('Model'):
#创建变量
x = tf.placeholder(tf.float32, [None, 12], name='X')
y = tf.placeholder(tf.float32, [None, 1], name='Y')
w = tf.Variable(tf.random.normal((12,1)), name='w')
b = tf.Variable(tf.random.normal((1, 1)), name='b')
def model(x, w, b):
return tf.matmul(x, w) + b
#预测节点
pred = model(x, w, b)
2. Training model
Train using mini-batch gradient descent, shuffling the order of the training set after each epoch.
#训练参数
train_epoch = 100
learning_rate = 0.01
batch_size = 100
batch_num = (x_train.shape[0] // batch_size)
#损失函数
step = 0
display_step = 5
loss_list_test = []
loss_list_train = []
with tf.name_scope('LossFunction'):
loss_function = tf.reduce_mean(tf.square(y - pred))
#定义优化器
optimizer = tf.train.GradientDescentOptimizer(learning_rate)\
.minimize(loss_function)
#变量初始化
sess = tf.Session()
init = tf.global_variables_initializer()
sess.run(init)
iterative training
for epoch in range(train_epoch):
for batch in range(batch_num):
xi = x_train[batch * batch_size:(batch + 1) * batch_size]
yi = y_train[batch * batch_size:(batch + 1) * batch_size]
sess.run(optimizer, feed_dict={
x:xi, y:yi})
step = step + 1
if step % display_step == 0:
loss_train = sess.run(loss_function,\
feed_dict={
x:x_train, y:y_train})
loss_test= sess.run(loss_function,\
feed_dict={
x:x_test, y:y_test})
loss_list_train.append(loss_train)
loss_list_test.append(loss_test)
#print('w=', sess.run(w), '\n', 'b=', sess.run(b))
#打乱训练集顺序
x_train, y_train = shuffle(x_train, y_train)
3. Results visualization
plt.plot(loss_list_train, 'b-')
plt.plot(loss_list_test, 'r-')
print('train_epoch=', train_epoch)
print('learning_rate', learning_rate)
print('batch_size=', batch_size)
The loss function of the test set decreases faster than the training set
. Increase the number of training rounds, reduce the batch sample size, and the loss function further decreases.
Set the test set ratio to 0.99, and only use 5 samples as the training set. After several rounds of training, The loss function of the training set tends to 0, and the loss function of the test set increases, resulting in overfitting.
4. Model prediction
Randomly draw samples from the test set to make predictions
i = np.random.randint(0, 50)
print('第%i个样本：' % i)
print('预测值：', sess.run(pred, feed_dict={
x:x_test[i].reshape((1, 12))}))
print('实际值：', y_test[i])
sess.close()
The difference is big or small
5. TensorBoard visualization
Add after variable initialization:
#设置存储目录
tf.reset_default_graph()
log_dir = 'G://log'
#记录损失值
sum_loss_op = tf.summary.scalar('loss', loss_function)
#合并写入
merged = tf.summary.merge_all()
#文件写入器
write = tf.summary.FileWriter(log_dir, sess.graph)
Add the loss value to the summary:
loss_train, sum_loss = sess.run([loss_function, sum_loss_op],\
feed_dict={
x:x_train, y:y_train})
write.add_summary(sum_loss, epoch)
closure:
write.close()
Enter the log directory in Anaconda Prompt, run TensorBoard, and visit the URL.
You can see the loss value and calculation graph
3. TensorFlow2.x
1. Define the model
import tensorflow as tf
import matplotlib.pyplot as plt
def model(x, w, b):
return tf.matmul(x, w) + b
def loss_function(x, y, w, b):
pred = model(x, w, b)
loss = tf.reduce_mean(tf.square(y - pred))
return loss
def grad(x, y, w, b):
with tf.GradientTape() as tape:
loss = loss_function(x, y, w, b)
return tape.gradient(loss, [w, b])
w = tf.Variable(tf.random.normal((12,1)), dtype=tf.float32)
b = tf.Variable(tf.random.normal((1,1)), dtype=tf.float32)
Matrix multiplication needs to be converted to Tensor
x_train = tf.cast(x_train, tf.float32)
x_test = tf.cast(x_test, tf.float32)
y_train = tf.cast(y_train, tf.float32)
y_test = tf.cast(y_test, tf.float32)
2. Training model
#训练参数
train_epoch = 100
learning_rate = 0.01
batch_size = 100
batch_num = x_train.shape[0] // batch_size
step = 0
display_step = 5
loss_list_train = []
loss_list_test = []
#创建优化器
optimizer = tf.keras.optimizers.SGD(learning_rate)
iterative training
for epoch in range(train_epoch):
for batch in range(batch_num):
xi = x_train[batch*batch_size : (batch+1)*batch_size]
yi = y_train[batch*batch_size : (batch+1)*batch_size]
grads = grad(xi, yi, w, b)
#应用梯度
optimizer.apply_gradients(zip(grads, [w,b]))
step = step + 1
if step % display_step == 0:
loss_list_train.append(loss_function(x_train, y_train, w, b))
loss_list_test.append(loss_function(x_test, y_test, w, b))
#使用tf.random.shuffle打乱Tensor类型的数据集
train_data = tf.concat([x_train, y_train], axis=1)
train_data = tf.random.shuffle(train_data)
x_train = train_data[:, :12]
y_train = tf.reshape(train_data[:, 12], (-1,1))
3. Results visualization
plt.plot(loss_list_train, 'b-')
plt.plot(loss_list_test, 'r-')
print('train_epoch=', train_epoch)
print('learning_rate', learning_rate)
print('batch_size=', batch_size)
4. Model prediction
i = np.random.randint(0, 50)
pred = model(tf.reshape(x_test[i], (1,12)), w, b).numpy()
print('第%i个样本：' % i)
print('预测值：', pred)
print('实际值：', y_test[i].numpy())
Summarize
There are some differences in syntax between TensorFlow1.x and TensorFlow2.x. When using TensorBoard for display, you need to delete the previous log file; when performing matrix multiplication, you need to pay attention to the data type and dimension; due to the small data set, linear regression is used, and the model The accuracy needs to be optimized.