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()