TensorFlow实战5——TensorFlow实现AlexNet

128 阅读 0 评论 85 点赞

我是靠谱客的博主凶狠手套，这篇文章主要介绍TensorFlow实战5——TensorFlow实现AlexNet，现在分享给大家，希望可以做个参考。


1 #coding = utf-8

2

3 from datetime import datetime

4 import math

5 import time

6 import tensorflow as tf

7

8 batch_size = 32

9 num_batches = 1000
 10
 11 def print_activations(t):
 12
'''打印每一个卷积层或池化层输出tensor的尺寸
 13 
t:tensor t.op.name：tensor的名称 ;
 14 
t.get-shape.as_list()：tensor尺寸'''
 15
print(t.op.name, '', t.get_shape().as_list())
 16
 17 def interence(images):
 18
'''input: images; return: 最后一层pool5及parameters
 19
'''
 20
parameters = []
 21
 22
with tf.name_scope('conv1') as scope:
 23
#定义第一个卷积层，卷积核尺寸为11x11，颜色通道为3，卷积核数量为64
 24
kernel = tf.Variable(tf.truncated_normal([11, 11, 3, 64],
 25
dtype=tf.float32, stddev=1e-1, name='weights'))
 26
#对输入的images进行卷积操作，strides步长设置为4x4
 27
conv = tf.nn.conv2d(images, kernel, [1, 4, 4, 1], padding='SAME')
 28
#biases全部初始化为0
 29
biases = tf.Variable(tf.constant(0.0, shape=[64], dtype=tf.float32),
 30
trainable=True, name='biases')
 31
#将卷积结果conv和biases
 32
bias = tf.nn.bias_add(conv, biases)
 33
#rele对结果进行非线性处理
 34
conv1 = tf.nn.relu(bias, name=scope)
 35 
print_activations(conv1)
 36
#将这一层的参数kernel和biases添加到parameters
 37
parameters += [kernel, biases]
 38
#LRN层，depth_radius=4，等都是AlexNet论文中推荐值
 39
lrn1 = tf.nn.lrn(conv1, 4, bias=1.0, alpha=0.001/9, beta=0.75, name='lrn1')
 40
pool1 = tf.nn.max_pool(lrn1, ksize=[1, 3, 3, 1], strides=[1, 2, 2, 1],
 41
padding='VALID', name='pool1')
 42
 43 
print_activations(pool1)
 44
 45
with tf.name_scope('conv2') as scope:
 46
#定义第二个卷积层，卷积核尺寸为5x5，输入通道为64，卷积核数量为192
 47
kernel = tf.Variable(tf.truncated_normal([5, 5, 64, 192],
 48
dtype=tf.float32, stddev=1e-1, name='weights'))
 49
#对输入的images进行卷积操作，strides步长设置为1x1
 50
conv = tf.nn.conv2d(pool1, kernel, [1, 1, 1, 1], padding='SAME')
 51
#biases全部初始化为0
 52
biases = tf.Variable(tf.constant(0.0, shape=[192], dtype=tf.float32),
 53
trainable=True, name='biases')
 54
#将卷积结果conv和biases
 55
bias = tf.nn.bias_add(conv, biases)
 56
#rele对结果进行非线性处理
 57
conv2 = tf.nn.relu(bias, name=scope)
 58
 59
#将这一层的参数kernel和biases添加到parameters
 60
parameters += [kernel, biases]
 61
 62 
print_activations(conv2)
 63
#LRN层，depth_radius=4，等都是AlexNet论文中推荐值
 64
lrn2 = tf.nn.lrn(conv2, 4, bias=1.0, alpha=0.001/9, beta=0.75, name='lrn2')
 65
pool2 = tf.nn.max_pool(lrn2, ksize=[1, 3, 3, 1], strides=[1, 2, 2, 1],
 66
padding='VALID', name='pool2')
 67
 68 
print_activations(pool2)
 69
 70
with tf.name_scope('conv3') as scope:
 71
#定义第三个卷积层，卷积核尺寸为5x5，输入通道为64，卷积核数量为192
 72
kernel = tf.Variable(tf.truncated_normal([3, 3, 192, 384],
 73
dtype=tf.float32, stddev=1e-1, name='weights'))
 74
#对输入的images进行卷积操作，strides步长设置为1x1
 75
conv = tf.nn.conv2d(pool2, kernel, [1, 1, 1, 1], padding='SAME')
 76
#biases全部初始化为0
 77
biases = tf.Variable(tf.constant(0.0, shape=[384], dtype=tf.float32),
 78
trainable=True, name='biases')
 79
#将卷积结果conv和biases
 80
bias = tf.nn.bias_add(conv, biases)
 81
#rele对结果进行非线性处理
 82
conv3 = tf.nn.relu(bias, name=scope)
 83
 84
#将这一层的参数kernel和biases添加到parameters
 85
parameters += [kernel, biases]
 86
 87 
print_activations(conv3)
 88
 89
 90
with tf.name_scope('conv4') as scope:
 91
#定义第四个卷积层，卷积核尺寸为3x3，输入通道为384，卷积核数量为256
 92
kernel = tf.Variable(tf.truncated_normal([3, 3, 384, 256],
 93
dtype=tf.float32, stddev=1e-1, name='weights'))
 94
#对输入的images进行卷积操作，strides步长设置为1x1
 95
conv = tf.nn.conv2d(conv3, kernel, [1, 1, 1, 1], padding='SAME')
 96
#biases全部初始化为0
 97
biases = tf.Variable(tf.constant(0.0, shape=[256], dtype=tf.float32),
 98
trainable=True, name='biases')
 99
#将卷积结果conv和biases
100
bias = tf.nn.bias_add(conv, biases)
101
#rele对结果进行非线性处理
102
conv4 = tf.nn.relu(bias, name=scope)
103
104
#将这一层的参数kernel和biases添加到parameters
105
parameters += [kernel, biases]
106
107 
print_activations(conv4)
108
109
with tf.name_scope('conv5') as scope:
110
#定义第五个卷积层，卷积核尺寸为3x3，输入通道为256，卷积核数量为256
111
kernel = tf.Variable(tf.truncated_normal([3, 3, 256, 256],
112
dtype=tf.float32, stddev=1e-1, name='weights'))
113
#对输入的images进行卷积操作，strides步长设置为1x1
114
conv = tf.nn.conv2d(conv4, kernel, [1, 1, 1, 1], padding='SAME')
115
#biases全部初始化为0
116
biases = tf.Variable(tf.constant(0.0, shape=[256], dtype=tf.float32),
117
trainable=True, name='biases')
118
#将卷积结果conv和biases
119
bias = tf.nn.bias_add(conv, biases)
120
#rele对结果进行非线性处理
121
conv5 = tf.nn.relu(bias, name=scope)
122
123
#将这一层的参数kernel和biases添加到parameters
124
parameters += [kernel, biases]
125
126 
print_activations(conv5)
127
128
pool5 = tf.nn.max_pool(conv5, ksize=[1, 3, 3, 1], strides=[1, 2, 2, 1],
129
padding='VALID', name='pool5')
130 
print_activations(pool5)
131
return pool5, parameters
132
133 def time_tensorflow_run(session, target, info_string):
134
'''评估AlexNet每轮计算时间
135 
target:评测的运算算子
136 
info_string：评测的名称'''
137
num_steps_burn_in = 10#预热轮数，给程序热身
138
total_duration = 0.0#总时间
139
total_duration_squared =0.0#计算方差
140
141
for i in range(num_batches + num_steps_burn_in):
142
143
start_time = time.time()
144
_ = session.run(target)
145
duration = time.time()-start_time
146
#在初始热身的num_steps_burn_in次迭代后每10轮显示当前迭代所需要的时间
147
if i >= num_steps_burn_in:
148
if not i%10:
149
print('%s: step %d, duration = %.3f' %
150
(datetime.now(), i-num_steps_burn_in, duration))
151
total_duration +=duration
152
total_duration_squared += duration*duration
153
mn = total_duration/num_batches#每轮迭代平均耗时
154
vr = total_duration_squared/num_batches-mn*mn
155
#平均耗时标准差
156
sd = math.sqrt(vr)
157
158
print('%s: %s across %d steps, %.3f +/-%.3f sec/batch' %
159 
(datetime.now(), info_string, num_batches, mn, sd))
160
161 def run_benchmark():
162
163 
with tf.Graph().as_default():
164
image_size = 224
165
'''batch_size:每轮迭代样本数
166 
image_size:图片尺寸
167 
3：图片颜色通道数'''
168
images = tf.Variable(tf.random_normal([batch_size,
169 
image_size,
170
image_size, 3],
171
dtype=tf.float32,
172
stddev=1e-1))
173
pool5, parameters = interence(images)
174
175
init = tf.global_variables_initializer()
176
sess = tf.Session()
177 
sess.run(init)
178
179
time_tensorflow_run(sess, pool5, "Forward")
180
181
objective = tf.nn.l2_loss(pool5)
182
grad = tf.gradients(objective, parameters)
183
time_tensorflow_run(sess, grad, "Forward-backward")
184
185 run_benchmark()

 1 conv1
[32, 56, 56, 64]
 2 pool1
[32, 27, 27, 64]
 3 conv2
[32, 27, 27, 192]
 4 pool2
[32, 13, 13, 192]
 5 conv3
[32, 13, 13, 384]
 6 conv4
[32, 13, 13, 256]
 7 conv5
[32, 13, 13, 256]
 8 pool5
[32, 6, 6, 256]
 9 2017-12-20 23:31:19.926000: step 990, duration = 0.197
10 2017-12-20 23:31:19.926000: Forward-backward across 1000 steps, 0.196 +/-0.019 sec/batch
11 2017-12-20 23:31:20.122000: Forward-backward across 1000 steps, 0.196 +/-0.018 sec/batch
12 2017-12-20 23:31:20.319000: Forward-backward across 1000 steps, 0.197 +/-0.017 sec/batch
13 2017-12-20 23:31:20.515000: Forward-backward across 1000 steps, 0.197 +/-0.016 sec/batch
14 2017-12-20 23:31:20.711000: Forward-backward across 1000 steps, 0.197 +/-0.014 sec/batch
15 2017-12-20 23:31:20.907000: Forward-backward across 1000 steps, 0.197 +/-0.013 sec/batch
16 2017-12-20 23:31:21.104000: Forward-backward across 1000 steps, 0.197 +/-0.011 sec/batch
17 2017-12-20 23:31:21.299000: Forward-backward across 1000 steps, 0.197 +/-0.010 sec/batch
18 2017-12-20 23:31:21.494000: Forward-backward across 1000 steps, 0.198 +/-0.007 sec/batch
19 2017-12-20 23:31:21.690000: Forward-backward across 1000 steps, 0.198 +/-0.004 sec/batch