TensorFlow练习16: 根据大脸判断性别和年龄

转载 于 2017-04-02 18:42:21 发布 · 1.4k 阅读 · 3

部署运行你感兴趣的模型镜像

本帖使用TensorFlow做一个根据脸部推断照片人物年龄和性别的练习，网上有很多类似app。

训练数据 – Adience数据集

Adience数据集来源为Flickr相册，由用户使用iPhone或者其它智能手机设备拍摄，该数据集主要用于进行年龄和性别的未经过滤的面孔估计。同时，里面还进行了相应的landmark的标注，其中包含2284个类别和26580张图片。

Adience数据集下载地址：http://www.openu.ac.il/home/hassner/Adience/data.html#agegender

由于数据源ftp站点被墙，我只能使用梯子，下载过程非常漫长和痛苦。为了让你免受折磨，我传了一份到网盘。

代码

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
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
import os
import glob
import tensorflow as tf # 0.12
from tensorflow . contrib . layers import *
from tensorflow . contrib . slim . python . slim . nets . inception_v3 import inception_v3_base
import numpy as np
from random import shuffle
 
age_table = [ '(0, 2)' , '(4, 6)' , '(8, 12)' , '(15, 20)' , '(25, 32)' , '(38, 43)' , '(48, 53)' , '(60, 100)' ]
sex_table = [ 'f' , 'm' ]    # f:女; m:男
 
# AGE==True 训练年龄模型，False,训练性别模型
AGE = False
 
if AGE == True :
lables_size = len ( age_table ) # 年龄
else :
lables_size = len ( sex_table ) # 性别
 
face_set_fold = 'AdienceBenchmarkOfUnfilteredFacesForGenderAndAgeClassification'
 
fold_0_data = os.path . join ( face_set_fold , 'fold_0_data.txt' )
fold_1_data = os.path . join ( face_set_fold , 'fold_1_data.txt' )
fold_2_data = os.path . join ( face_set_fold , 'fold_2_data.txt' )
fold_3_data = os.path . join ( face_set_fold , 'fold_3_data.txt' )
fold_4_data = os.path . join ( face_set_fold , 'fold_4_data.txt' )
 
face_image_set = os.path . join ( face_set_fold , 'aligned' )
 
def parse_data ( fold_x_data ) :
data_set = [ ]
 
with open ( fold_x_data , 'r' ) as f :
line_one = True
for line in f :
tmp = [ ]
if line_one == True :
line_one = False
continue
 
tmp . append ( line . split ( '\t' ) [ 0 ] )
tmp . append ( line . split ( '\t' ) [ 1 ] )
tmp . append ( line . split ( '\t' ) [ 3 ] )
tmp . append ( line . split ( '\t' ) [ 4 ] )
 
file_path = os.path . join ( face_image_set , tmp [ 0 ] )
if os.path . exists ( file_path ) :
filenames = glob . glob ( file_path + "/*.jpg" )
for filename in filenames :
if tmp [ 1 ] in filename :
break
if AGE == True :
if tmp [ 2 ] in age_table :
data_set . append ( [ filename , age_table . index ( tmp [ 2 ] ) ] )
else :
if tmp [ 3 ] in sex_table :
data_set . append ( [ filename , sex_table . index ( tmp [ 3 ] ) ] )
 
return data_set
 
data_set_0 = parse_data ( fold_0_data )
data_set_1 = parse_data ( fold_1_data )
data_set_2 = parse_data ( fold_2_data )
data_set_3 = parse_data ( fold_3_data )
data_set_4 = parse_data ( fold_4_data )
 
data_set = data_set_0 + data_set_1 + data_set_2 + data_set_3 + data_set_4
shuffle ( data_set )
 
# 缩放图像的大小
IMAGE_HEIGHT = 227
IMAGE_WIDTH = 227
# 读取缩放图像
jpg_data = tf . placeholder ( dtype = tf . string )
decode_jpg = tf . image . decode_jpeg ( jpg_data , channels = 3 )
resize = tf . image . resize_images ( decode_jpg , [ IMAGE_HEIGHT , IMAGE_WIDTH ] )
resize = tf . cast ( resize , tf . uint8 ) / 255
def resize_image ( file_name ) :
with tf . gfile . FastGFile ( file_name , 'r' ) as f :
image_data = f . read ( )
with tf . Session ( ) as sess :
image = sess . run ( resize , feed_dict = { jpg_data : image_data } )
return image
 
pointer = 0
# 有点慢(先睡了)，应该先处理好图片或使用string_input_producer
def get_next_batch ( data_set , batch_size = 128 ) :
global pointer
batch_x = [ ]
batch_y = [ ]
for i in range ( batch_size ) :
batch_x . append ( resize_image ( data_set [ pointer ] [ 0 ] ) )
batch_y . append ( data_set [ pointer ] [ 1 ] )
pointer += 1
return batch_x , batch_y
 
batch_size = 128
num_batch = len ( data_set ) / / batch _size
 
X = tf . placeholder ( dtype = tf . float32 , shape = [ batch_size , IMAGE_HEIGHT , IMAGE_WIDTH , 3 ] )
Y = tf . placeholder ( dtype = tf . int32 , shape = [ batch_size ] )
 
def conv_net ( nlabels , images , pkeep = 1.0 ) :
weights_regularizer = tf . contrib . layers . l2_regularizer ( 0.0005 )
with tf . variable_scope ( "conv_net" , "conv_net" , [ images ] ) as scope :
with tf . contrib . slim . arg_scope ( [ convolution2d , fully_connected ] , weights_regularizer = weights_regularizer , biases_initializer = tf . constant_initializer ( 1. ) , weights_initializer = tf . random_normal_initializer ( stddev = 0.005 ) , trainable = True ) :
with tf . contrib . slim . arg_scope ( [ convolution2d ] , weights_initializer = tf . random_normal_initializer ( stddev = 0.01 ) ) :
conv1 = convolution2d ( images , 96 , [ 7 , 7 ] , [ 4 , 4 ] , padding = 'VALID' , biases_initializer = tf . constant_initializer ( 0. ) , scope = 'conv1' )
pool1 = max_pool2d ( conv1 , 3 , 2 , padding = 'VALID' , scope = 'pool1' )
norm1 = tf . nn . local_response_normalization ( pool1 , 5 , alpha = 0.0001 , beta = 0.75 , name = 'norm1' )
conv2 = convolution2d ( norm1 , 256 , [ 5 , 5 ] , [ 1 , 1 ] , padding = 'SAME' , scope = 'conv2' )
pool2 = max_pool2d ( conv2 , 3 , 2 , padding = 'VALID' , scope = 'pool2' )
norm2 = tf . nn . local_response_normalization ( pool2 , 5 , alpha = 0.0001 , beta = 0.75 , name = 'norm2' )
conv3 = convolution2d ( norm2 , 384 , [ 3 , 3 ] , [ 1 , 1 ] , biases_initializer = tf . constant_initializer ( 0. ) , padding = 'SAME' , scope = 'conv3' )
pool3 = max_pool2d ( conv3 , 3 , 2 , padding = 'VALID' , scope = 'pool3' )
flat = tf . reshape ( pool3 , [ - 1 , 384 * 6 * 6 ] , name = 'reshape' )
full1 = fully_connected ( flat , 512 , scope = 'full1' )
drop1 = tf . nn . dropout ( full1 , pkeep , name = 'drop1' )
full2 = fully_connected ( drop1 , 512 , scope = 'full2' )
drop2 = tf . nn . dropout ( full2 , pkeep , name = 'drop2' )
with tf . variable_scope ( 'output' ) as scope :
weights = tf . Variable ( tf . random_normal ( [ 512 , nlabels ] , mean = 0.0 , stddev = 0.01 ) , name = 'weights' )
biases = tf . Variable ( tf . constant ( 0.0 , shape = [ nlabels ] , dtype = tf . float32 ) , name = 'biases' )
output = tf . add ( tf . matmul ( drop2 , weights ) , biases , name = scope . name )
return output
 
def training ( ) :
logits = conv_net ( lables_size , X )
 
def optimizer ( eta , loss_fn ) :
global_step = tf . Variable ( 0 , trainable = False )
optz = lambda lr : tf . train . MomentumOptimizer ( lr , 0.9 )
lr_decay_fn = lambda lr , global_step : tf . train . exponential_decay ( lr , global_step , 100 , 0.97 , staircase = True )
return tf . contrib . layers . optimize_loss ( loss_fn , global_step , eta , optz , clip_gradients = 4. , learning_rate_decay_fn = lr_decay_fn )
 
def loss ( logits , labels ) :
cross_entropy = tf . nn . sparse_softmax_cross_entropy_with_logits ( logits , labels )
cross_entropy_mean = tf . reduce_mean ( cross_entropy )
regularization_losses = tf . get_collection ( tf . GraphKeys . REGULARIZATION_LOSSES )
total_loss = cross_entropy_mean + 0.01 * sum ( regularization_losses )
loss_averages = tf . train . ExponentialMovingAverage ( 0.9 )
loss_averages_op = loss_averages . apply ( [ cross_entropy_mean ] + [ total_loss ] )
with tf . control_dependencies ( [ loss_averages_op ] ) :
     total_loss = tf . identity ( total_loss )
return total_loss
# loss
total_loss = loss ( logits , Y )
# optimizer
train_op = optimizer ( 0.001 , total_loss )
 
saver = tf . train . Saver ( tf . global_variables ( ) )
with tf . Session ( ) as sess :
sess . run ( tf . global_variables_initializer ( ) )
 
global pointer
epoch = 0
while True :
pointer = 0
for batch in range ( num_batch ) :
batch_x , batch_y = get_next_batch ( data_set , batch_size )
_ , loss_value = sess . run ( [ train_op , total_loss ] , feed_dict = { X : batch_x , Y : batch_y } )
print ( epoch , batch , loss_value )
saver . save ( sess , 'age.module' if AGE == True else 'sex.module' )
epoch += 1
 
training ( )
 
"""
# 检测性别和年龄
# 把batch_size改为1
def detect_age_or_sex(image_path):
logits = conv_net(lables_size, X)
saver = tf.train.Saver()
 
with tf.Session() as sess:
saver.restore(sess, './age.module' if AGE == True else './sex.module')
softmax_output = tf.nn.softmax(logits)
res = sess.run(softmax_output, feed_dict={X:[resize_image(image_path)]})
res = np.argmax(res)
 
if AGE == True:
return age_table[res]
else:
return sex_table[res]
"""

后续：使用OpenCV检测提取人脸，然后使用训练好的模型判断性别和年龄。

相关资源：

Share the post "TensorFlow练习16: 根据大脸判断性别和年龄"

您可能感兴趣的与本文相关的镜像

TensorFlow-v2.15

TensorFlow-v2.15

TensorFlow

TensorFlow 是由Google Brain 团队开发的开源机器学习框架,广泛应用于深度学习研究和生产环境。 它提供了一个灵活的平台,用于构建和训练各种机器学习模型

评论 2
成就一亿技术人!
拼手气红包6.0元
还能输入1000个字符
 
红包 添加红包
表情包 插入表情
表情包 代码片
 条评论被折叠 查看
添加红包

请填写红包祝福语或标题

个

红包个数最小为10个

元

红包金额最低5元

当前余额3.43元 前往充值 >
需支付：10.00元
成就一亿技术人!
领取后你会自动成为博主和红包主的粉丝 规则
hope_wisdom
发出的红包
实付元
使用余额支付
点击重新获取
扫码支付
钱包余额 0

抵扣说明：

1.余额是钱包充值的虚拟货币，按照1:1的比例进行支付金额的抵扣。
2.余额无法直接购买下载，可以购买VIP、付费专栏及课程。

余额充值