TensorFlow實現隨機訓練和批量訓練的方法

本篇文章主要介紹了TensorFlow實現隨機訓練和批量訓練的方法，現在分享給大家，也給大家做個參考。一起來看看吧

TensorFlow更新模型變數。它能一次操作一個數據點，也可以一次操作大量數據。一個訓練例子上的操作可能導致比較「古怪」的學習過程，但使用大批量的訓練會造成計算成本昂貴。到底選用哪一種訓練類型對機器學習演算法的收斂性非常關鍵。

為了TensorFlow計算變數梯度來讓反向傳播工作，我們必須測量一個或多個樣本的損失。

隨機訓練會一次隨機抽樣訓練資料和目標資料對完成訓練。另一個可選項是，一次大批量訓練取平均損失來進行梯度計算，批量訓練大小可以一次上擴到整個資料集。這裡將顯示如何擴展前面的迴歸演算法的例子—使用隨機訓練和批次訓練。

批量訓練和隨機訓練的不同之處在於它們的最佳化器方法和收斂。

# 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()

輸出：

#Step #5 A = [ 1.47604525]
Loss = [ 72.55678558]
Step #10 A = [ 3.01128507]
Loss = [ 48.22986221]
Step #15 A = [ 4.27042341]
Loss = [ 28.97912598]##Step #20 Aoss = [129843 = [Step#Loss. [ 16.44779968]
Step #25 A = [ 6.17473984]
Loss = [ 16.373312]
Step #30 A = [ 6.89866304]
Loss = [Step #30 A = [ 6.89866304]
Loss = [Step #30710546491 7.39849901]
Loss = [ 6.42773056]
Step #40 A = [ 7.84618378]
Loss = [ 5.92940331]
Step #45 A = [Loss = [ 5.92940331]
Step #45 A = [ 8.15109782#109782.109782.209782.109782.# #Step #50 A = [ 8.54818344]
Loss = [ 7.11651039]
Step #55 A = [ 8.82354641]
Loss = [ 1.47823763]##Step
#Loss. Loss = [ 3.08244276]
Step #65 A = [ 9.24868107]
Loss = [ 0.01143846]
Step #70 A = [ 9.36772251]##Loss#Step #70 A = [ 9.36772251]##Loss#Step. = [ 9.49171734]
Loss = [ 3.90913701]
Step #80 A = [ 9.6622715]
Loss = [ 4.80727625]
Step #85 A = [Loss = [ 4.80727625]
Step #85 A = [ 9.7378692625]
Step #85 A = [ 9.7378699.378693.
Step #90 A = [ 9.81853104]
Loss = [ 0.14876099]
Step #95 A = [ 9.90371323]
Loss = [ 0.01657014]##Step #10869. ##Loss = [ 0.444787]
Step #5 A = [[ 2.34371352]]
Loss = 58.766
Step #10 A = [[ 3.74766445]]
Loss = 38.4875# 15 A = [[ 4.88928795]]
Loss = 27.5632
Step #20 A = [[ 5.82038736]]
Loss = 17.9523
Step #25 A = [[ 6.589. = 13.3245
Step #30 A = [[ 7.20851326]]
Loss = 8.68099
Step #35 A = [[ 7.71694899]]
Loss = 4.60659## 8.1296711]]
Loss = 4.70107
Step #45 A = [[ 8.47107315]]
Loss = 3.28318
Step #50 A = [[ 8.74283409]#. Step #55 A = [[ 8.98811722]]
Loss = 2.66906
Step #60 A = [[ 9.18062305]]
Loss = 3.26207
Step #65 A = [[ 9.3165025]# #Loss = 2.55459
Step #70 A = [[ 9.43130589]]
Loss = 1.95839
Step #75 A = [[ 9.55670166]]
Loss = 1.46504#> [[ 9.6354847]]
Loss = 1.49021
Step #85 A = [[ 9.73470974]]
Loss = 1.53289
Step #90 A = [[ 9.77956581]#1.51. ##Step #95 A = [[ 9.83666706]]
Loss = 0.819207
Step #100 A = [[ 9.85569191]]
Loss = 1.2197












訓練類型

優點

#隨機訓練

脫離局部最小一般需更多次迭代才收斂耗費更多運算資源#相關推薦：淺談tensorflow1.0 池​​化層（pooling)和全連接層(dense)淺聊Tensorflow模型的儲存與復原載入

	批次訓練	快速得到最小損失

以上是TensorFlow實現隨機訓練和批量訓練的方法的詳細內容。更多資訊請關注PHP中文網其他相關文章！