1.MNIST数据
MNIST数据集是NIST数据集的一个子集，包含60000张图片作为训练数据，10000张图片作为测试数据。每张图片大小为28x28。详细介绍：http:yann.lecun.com/exdb/mnist 。
TensorFlow提供了一个类来处理MNIST数据。这个类会自动下载并转化MNIST数据的格式，将数据从原始的数据包中解析成训练和测试神经网络时使用的格式。
在MNIST数据集上实现 激活函数、隐藏层、指数衰减学习率、正则化、滑动平均模型 ：
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
# -*- coding: utf-8 -*-
# @Time : 2017-12-11 19:29
# @Author : Storm
# @File : chapter05-01.py
import tensorflow as tf
from tensorflow.examples.tutorials.mnist import input_data
# MNIST数据集相关的常数
INPUT_NODE = 784 # 输入层的节点数。对于MNIST数据集，这个就等于图片的像素。
OUTPUT_NODE = 10 # 输出层的节点数。等于类别的数目（0~9 这10个数字）。
# 配置神经网络的参数
LAYER1_NODE = 500 # 隐藏层节点数。
BATCH_SIZE = 100 # batch的数据个数。
LEARNING_RATE_BASE = 0.8 # 基础学习率
LEARNING_RATE_DECAY = 0.99 # 学习率的衰减率
REGULARIZATION_RATE = 0.0001 # 正则化项在损失函数中的系数
TRAINING_STEPS = 50000 # 训练轮数
MOVING_AVERAGE_DECAY = 0.99 # 滑动平均衰减率
# 一个辅助函数，给定神经网络的输入和所有参数，计算神经网络的前向传播结果
def inference(input_tensor, avg_class, weights1, biases1, weights2, biases2):
# 不使用滑动平均类
if avg_class == None:
layer1 = tf.nn.relu(tf.matmul(input_tensor, weights1) + biases1)
return tf.matmul(layer1, weights2) + biases2
else:
# 使用滑动平均类
layer1 = tf.nn.relu(tf.matmul(input_tensor, avg_class.average(weights1)) + avg_class.average(biases1))
return tf.matmul(layer1, avg_class.average(weights2)) + avg_class.average(biases2)
# 训练模型的过程
def train(mnist):
x = tf.placeholder(tf.float32, [None, INPUT_NODE], name='x-input')
y_ = tf.placeholder(tf.float32, [None, OUTPUT_NODE], name='y-input')
# 生成隐藏层的参数。
weights1 = tf.Variable(tf.truncated_normal([INPUT_NODE, LAYER1_NODE], stddev=0.1))
biases1 = tf.Variable(tf.constant(0.1, shape=[LAYER1_NODE]))
# 生成输出层的参数。
weights2 = tf.Variable(tf.truncated_normal([LAYER1_NODE, OUTPUT_NODE], stddev=0.1))
biases2 = tf.Variable(tf.constant(0.1, shape=[OUTPUT_NODE]))
# 计算不含滑动平均类的前向传播结果
y = inference(x, None, weights1, biases1, weights2, biases2)
# 定义训练轮数及相关的滑动平均类
global_step = tf.Variable(0, trainable=False)
variable_averages = tf.train.ExponentialMovingAverage(MOVING_AVERAGE_DECAY, global_step)
variables_averages_op = variable_averages.apply(tf.trainable_variables())
average_y = inference(x, variable_averages, weights1, biases1, weights2, biases2)
# 计算交叉熵及其平均值
cross_entropy = tf.nn.sparse_softmax_cross_entropy_with_logits(logits=y, labels=tf.argmax(y_, 1))
cross_entropy_mean = tf.reduce_mean(cross_entropy)
# 损失函数的计算
regularizer = tf.contrib.layers.l2_regularizer(REGULARIZATION_RATE)
regularaztion = regularizer(weights1) + regularizer(weights2)
loss = cross_entropy_mean + regularaztion
# 设置指数衰减的学习率。
learning_rate = tf.train.exponential_decay(
LEARNING_RATE_BASE,
global_step,
mnist.train.num_examples / BATCH_SIZE,
LEARNING_RATE_DECAY,
staircase=True)
# 优化损失函数
train_step = tf.train.GradientDescentOptimizer(learning_rate).minimize(loss, global_step=global_step)
# 反向传播更新参数和更新每一个参数的滑动平均值
with tf.control_dependencies([train_step, variables_averages_op]):
train_op = tf.no_op(name='train')
# 计算正确率
correct_prediction = tf.equal(tf.argmax(average_y, 1), tf.argmax(y_, 1))
accuracy = tf.reduce_mean(tf.cast(correct_prediction, tf.float32))
# 初始化会话，并开始训练过程。
with tf.Session() as sess:
tf.global_variables_initializer().run()
validate_feed = {x: mnist.validation.images, y_: mnist.validation.labels}
test_feed = {x: mnist.test.images, y_: mnist.test.labels}
# 循环的训练神经网络。
for i in range(TRAINING_STEPS):
if i % 1000 == 0:
validate_acc = sess.run(accuracy, feed_dict=validate_feed)
print("After %d training step(s), validation accuracy using average model is %g " % (i, validate_acc))
xs, ys = mnist.train.next_batch(BATCH_SIZE)
sess.run(train_op, feed_dict={x: xs, y_: ys})
test_acc = sess.run(accuracy, feed_dict=test_feed)
print(("After %d training step(s), test accuracy using average model is %g" % (TRAINING_STEPS, test_acc)))
def main(argv=None):
mnist = input_data.read_data_sets("./datasets/MNIST_data", one_hot=True)
train(mnist)
if __name__ == '__main__':
main()
2.变量管理
TensorFlow提供了通过变量名称来创建或者获取一个变量的机制。这样 在不同的函数中可以直接通过变量的名字来使用变量，而不需要将变量通过参数的形式到处传递。tf.get_variable和tf.variable_scope两个函数。
通过tf.variable_scope函数可以控制tf.get_variable函数的语义：
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
import tensorflow as tf
# 在名字为foo的命名空间内创建名字为v的变量
with tf.variable_scope("foo"):
v = tf.get_variable("v", [1], initializer=tf.constant_initializer(1.0))
# 因为在命名空间foo中已经存在名字为v的变量，所以下面的代码会出错
# with tf.variable_scope("foo"):
# v = tf.get_variable("v", [1])
# 在生成上下文管理器时，将参数reuse设置为True。这样tf.get_variable函数将直接获取已经声明的变量。
with tf.variable_scope("foo", reuse=True):
v1 = tf.get_variable("v", [1])
print(v == v1) #True
# 将参数reuse设置为True时，tf.get_variable将只能获取已经创建过的变量。下面的语句会出错。
# with tf.variable_scope("bar", reuse=True):
# v = tf.get_variable("v", [1])
嵌套上下文管理器中的reuse参数的使用:
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
with tf.variable_scope("root"):
print(tf.get_variable_scope().reuse)
with tf.variable_scope("foo", reuse=True):
print(tf.get_variable_scope().reuse)
# 新建一个嵌套的上下文管理器，不指定reuse，这是reuse会与外面一层保持一致
with tf.variable_scope("bar"):
print(tf.get_variable_scope().reuse)
print(tf.get_variable_scope().reuse)
# False
# True
# True
# False
通过variable_scope来管理变量,可以通过变量的名称来获取变量:
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
v1 = tf.get_variable("v", [1])
print(v1.name) # v:0
with tf.variable_scope("foo", reuse=True):
v2 = tf.get_variable("v", [1])
print(v2.name) # foo/v:0
with tf.variable_scope("foo"):
with tf.variable_scope("bar"):
v3 = tf.get_variable("v", [1])
print(v3.name) # foo/bar/v:0
v4 = tf.get_variable("v1", [1])
print(v4.name) # v1:0
with tf.variable_scope("", reuse=True):
v5 = tf.get_variable("foo/bar/v", [1])
print(v5 == v3) # True
v6 = tf.get_variable("v1", [1])
print(v6 == v4) # True
3.模型持久化
TensorFlow提供了一个非常简单的API来保存和还原一个神经网络模型，tf.train.Saver类。
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
# -*- coding: utf-8 -*-
# @Time : 2017-12-12 20:28
# @Author : Storm
# @File : chapter05-03.py
# 模型持久化
import tensorflow as tf
# 1. 保存计算两个变量和的模型。
v1 = tf.Variable(tf.constant(1.0, shape=[1]), name="v1")
v2 = tf.Variable(tf.constant(2.0, shape=[1]), name="v2")
result = v1 + v2
init_op = tf.global_variables_initializer()
saver = tf.train.Saver()
with tf.Session() as sess:
sess.run(init_op)
saver.save(sess, "Saved_model/model.ckpt")
# 2. 加载保存了两个变量和的模型。
with tf.Session() as sess:
saver.restore(sess, "Saved_model/model.ckpt")
print(sess.run(result))
# 3. 直接加载持久化的图。
saver = tf.train.import_meta_graph("Saved_model/model.ckpt.meta")
with tf.Session() as sess:
saver.restore(sess, "Saved_model/model.ckpt")
print(sess.run(tf.get_default_graph().get_tensor_by_name("add:0")))
# 4. 变量重命名。
v1 = tf.Variable(tf.constant(1.0, shape=[1]), name="other-v1")
v2 = tf.Variable(tf.constant(2.0, shape=[1]), name="other-v2")
saver = tf.train.Saver({"v1": v1, "v2": v2})
滑动平均类的保存：
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
# -*- coding: utf-8 -*-
# @Time : 2017-12-12 20:37
# @Author : Storm
# @File : chapter05-04.py
# 滑动平均类的保存
import tensorflow as tf
# 1.使用滑动平均。
v = tf.Variable(0, dtype=tf.float32, name="v")
for variables in tf.global_variables():
print(variables.name)
ema = tf.train.ExponentialMovingAverage(0.99)
maintain_averages_op = ema.apply(tf.global_variables())
for variables in tf.global_variables():
print(variables.name)
# 2.保存滑动平均模型。
saver = tf.train.Saver()
with tf.Session() as sess:
init_op = tf.global_variables_initializer()
sess.run(init_op)
sess.run(tf.assign(v, 10))
sess.run(maintain_averages_op)
# 保存的时候会将v:0 v/ExponentialMovingAverage:0这两个变量都存下来。
saver.save(sess, "Saved_model/model2.ckpt")
print(sess.run([v, ema.average(v)]))
# 3.加载滑动平均模型。
v = tf.Variable(0, dtype=tf.float32, name="v")
# 通过变量重命名将原来变量v的滑动平均值直接赋值给v。
saver = tf.train.Saver({"v/ExponentialMovingAverage": v})
with tf.Session() as sess:
saver.restore(sess, "Saved_model/model2.ckpt")
print(sess.run(v))
variables_to_restore函数的使用样例:
1
2
3
4
5
6
7
8
9
10
11
12
13
import tensorflow as tf
v = tf.Variable(0, dtype=tf.float32, name="v")
ema = tf.train.ExponentialMovingAverage(0.99)
print(ema.variables_to_restore())
# {'v/ExponentialMovingAverage': <tf.Variable 'v:0' shape=() dtype=float32_ref>}
saver = tf.train.Saver({"v/ExponentialMovingAverage": v})
with tf.Session() as sess:
saver.restore(sess, "Saved_model/model2.ckpt")
print(sess.run(v))
# 0.0999999
4.TensorFlow最佳实践样例程序
每隔一段时间保存一次模型训练的中间结果，将训练和测试分成两个独立的程序，将前向传播过程抽象成一个单独的库函数。
minst_inference.py，定义了前向传播的过程以及神经网络中的参数：
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
# -*- coding: utf-8 -*-
# @Time : 2017-12-14 10:28
# @Author : Storm
# @File : mnist_inference.py
import tensorflow as tf
INPUT_NODE = 784
OUTPUT_NODE = 10
LAYER1_NODE = 500
def get_weight_variable(shape, regularizer):
weights = tf.get_variable("weights", shape, initializer=tf.truncated_normal_initializer(stddev=0.1))
if regularizer != None: tf.add_to_collection('losses', regularizer(weights))
return weights
def inference(input_tensor, regularizer):
with tf.variable_scope('layer1'):
weights = get_weight_variable([INPUT_NODE, LAYER1_NODE], regularizer)
biases = tf.get_variable("biases", [LAYER1_NODE], initializer=tf.constant_initializer(0.0))
layer1 = tf.nn.relu(tf.matmul(input_tensor, weights) + biases)
with tf.variable_scope('layer2'):
weights = get_weight_variable([LAYER1_NODE, OUTPUT_NODE], regularizer)
biases = tf.get_variable("biases", [OUTPUT_NODE], initializer=tf.constant_initializer(0.0))
layer2 = tf.matmul(layer1, weights) + biases
return layer2
mnist_train.py，定义了神经网络的训练过程：
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
# -*- coding: utf-8 -*-
# @Time : 2017-12-14 10:29
# @Author : Storm
# @File : mnist_train.py
import tensorflow as tf
from tensorflow.examples.tutorials.mnist import input_data
import mnist_inference
import os
BATCH_SIZE = 100
LEARNING_RATE_BASE = 0.8
LEARNING_RATE_DECAY = 0.99
REGULARIZATION_RATE = 0.0001
TRAINING_STEPS = 30000
MOVING_AVERAGE_DECAY = 0.99
MODEL_SAVE_PATH = "MNIST_model/"
MODEL_NAME = "mnist_model"
def train(mnist):
x = tf.placeholder(tf.float32, [None, mnist_inference.INPUT_NODE], name='x-input')
y_ = tf.placeholder(tf.float32, [None, mnist_inference.OUTPUT_NODE], name='y-input')
regularizer = tf.contrib.layers.l2_regularizer(REGULARIZATION_RATE)
y = mnist_inference.inference(x, regularizer)
global_step = tf.Variable(0, trainable=False)
variable_averages = tf.train.ExponentialMovingAverage(MOVING_AVERAGE_DECAY, global_step)
variables_averages_op = variable_averages.apply(tf.trainable_variables())
cross_entropy = tf.nn.sparse_softmax_cross_entropy_with_logits(logits=y, labels=tf.argmax(y_, 1))
cross_entropy_mean = tf.reduce_mean(cross_entropy)
loss = cross_entropy_mean + tf.add_n(tf.get_collection('losses'))
learning_rate = tf.train.exponential_decay(
LEARNING_RATE_BASE,
global_step,
mnist.train.num_examples / BATCH_SIZE, LEARNING_RATE_DECAY,
staircase=True)
train_step = tf.train.GradientDescentOptimizer(learning_rate).minimize(loss, global_step=global_step)
with tf.control_dependencies([train_step, variables_averages_op]):
train_op = tf.no_op(name='train')
saver = tf.train.Saver()
with tf.Session() as sess:
tf.global_variables_initializer().run()
for i in range(TRAINING_STEPS):
xs, ys = mnist.train.next_batch(BATCH_SIZE)
_, loss_value, step = sess.run([train_op, loss, global_step], feed_dict={x: xs, y_: ys})
if i % 1000 == 0:
print("After %d training step(s), loss on training batch is %g." % (step, loss_value))
saver.save(sess, os.path.join(MODEL_SAVE_PATH, MODEL_NAME), global_step=global_step)
def main(argv=None):
mnist = input_data.read_data_sets("../datasets/MNIST_data", one_hot=True)
train(mnist)
if __name__ == '__main__':
tf.app.run()
mnist_eval.py，定义了测试过程：
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
# -*- coding: utf-8 -*-
# @Time : 2017-12-14 10:31
# @Author : Storm
# @File : mnist_eval.py
import time
import tensorflow as tf
from tensorflow.examples.tutorials.mnist import input_data
import mnist_inference
import mnist_train
# 加载的时间间隔。
EVAL_INTERVAL_SECS = 10
def evaluate(mnist):
with tf.Graph().as_default() as g:
x = tf.placeholder(tf.float32, [None, mnist_inference.INPUT_NODE], name='x-input')
y_ = tf.placeholder(tf.float32, [None, mnist_inference.OUTPUT_NODE], name='y-input')
validate_feed = {x: mnist.validation.images, y_: mnist.validation.labels}
y = mnist_inference.inference(x, None)
correct_prediction = tf.equal(tf.argmax(y, 1), tf.argmax(y_, 1))
accuracy = tf.reduce_mean(tf.cast(correct_prediction, tf.float32))
variable_averages = tf.train.ExponentialMovingAverage(mnist_train.MOVING_AVERAGE_DECAY)
variables_to_restore = variable_averages.variables_to_restore()
saver = tf.train.Saver(variables_to_restore)
while True:
with tf.Session() as sess:
ckpt = tf.train.get_checkpoint_state(mnist_train.MODEL_SAVE_PATH)
if ckpt and ckpt.model_checkpoint_path:
saver.restore(sess, ckpt.model_checkpoint_path)
global_step = ckpt.model_checkpoint_path.split('/')[-1].split('-')[-1]
accuracy_score = sess.run(accuracy, feed_dict=validate_feed)
print("After %s training step(s), validation accuracy = %g" % (global_step, accuracy_score))
else:
print('No checkpoint file found')
return
time.sleep(EVAL_INTERVAL_SECS)
def main(argv=None):
mnist = input_data.read_data_sets("../datasets/MNIST_data", one_hot=True)
evaluate(mnist)
if __name__ == '__main__':
main()
TensorFlow 实战Google深度学习框架（第五章）
