TensorFlow实现随机训练和批量训练的方法

# 随机训练和批量训练

#----------------------------------

#

# This python function illustrates two different training methods:

# batch and stochastic training. For each model, we will use

# a regression model that predicts one model variable.

import matplotlib.pyplot as plt

import numpy as np

import tensorflow as tf

from tensorflow.python.framework import ops

ops.reset_default_graph()

# 随机训练:

# Create graph

sess = tf.Session()

# 声明数据

x_vals = np.random.normal(1, 0.1, 100)

y_vals = np.repeat(10., 100)

x_data = tf.placeholder(shape=[1], dtype=tf.float32)

y_target = tf.placeholder(shape=[1], dtype=tf.float32)

# 声明变量 (one model parameter = A)

A = tf.Variable(tf.random_normal(shape=[1]))

# 增加操作到图

my_output = tf.multiply(x_data, A)

# 增加L2损失函数

loss = tf.square(my_output - y_target)

# 初始化变量

init = tf.global_variables_initializer()

sess.run(init)

# 声明优化器

my_opt = tf.train.GradientDescentOptimizer(0.02)

train_step = my_opt.minimize(loss)

loss_stochastic = []

# 运行迭代

for i in range(100):

 rand_index = np.random.choice(100)

 rand_x = [x_vals[rand_index]]

 rand_y = [y_vals[rand_index]]

 sess.run(train_step, feed_dict={x_data: rand_x, y_target: rand_y})

 if (i+1)%5==0:

  print('Step #' + str(i+1) + ' A = ' + str(sess.run(A)))

  temp_loss = sess.run(loss, feed_dict={x_data: rand_x, y_target: rand_y})

  print('Loss = ' + str(temp_loss))

  loss_stochastic.append(temp_loss)

# 批量训练:

# 重置计算图

ops.reset_default_graph()

sess = tf.Session()

# 声明批量大小

# 批量大小是指通过计算图一次传入多少训练数据

batch_size = 20

# 声明模型的数据、占位符

x_vals = np.random.normal(1, 0.1, 100)

y_vals = np.repeat(10., 100)

x_data = tf.placeholder(shape=[None, 1], dtype=tf.float32)

y_target = tf.placeholder(shape=[None, 1], dtype=tf.float32)

# 声明变量 (one model parameter = A)

A = tf.Variable(tf.random_normal(shape=[1,1]))

# 增加矩阵乘法操作（矩阵乘法不满足交换律）

my_output = tf.matmul(x_data, A)

# 增加损失函数

# 批量训练时损失函数是每个数据点L2损失的平均值

loss = tf.reduce_mean(tf.square(my_output - y_target))

# 初始化变量

init = tf.global_variables_initializer()

sess.run(init)

# 声明优化器

my_opt = tf.train.GradientDescentOptimizer(0.02)

train_step = my_opt.minimize(loss)

loss_batch = []

# 运行迭代

for i in range(100):

 rand_index = np.random.choice(100, size=batch_size)

 rand_x = np.transpose([x_vals[rand_index]])

 rand_y = np.transpose([y_vals[rand_index]])

 sess.run(train_step, feed_dict={x_data: rand_x, y_target: rand_y})

 if (i+1)%5==0:

  print('Step #' + str(i+1) + ' A = ' + str(sess.run(A)))

  temp_loss = sess.run(loss, feed_dict={x_data: rand_x, y_target: rand_y})

  print('Loss = ' + str(temp_loss))

  loss_batch.append(temp_loss)

plt.plot(range(0, 100, 5), loss_stochastic, 'b-', label='Stochastic Loss')

plt.plot(range(0, 100, 5), loss_batch, 'r--', label='Batch Loss, size=20')

plt.legend(loc='upper right', prop={'size': 11})

plt.show()