人脸图像采集,AR则让虚拟进入实际

人脸属性检测。人脸属性辩识、人脸感情分析。https://www.betaface.com/wpa/
在线人脸识别测试。给出人年龄、是否有胡子、情感(喜上眉梢、正常、生气、愤怒)、性别、是否带眼镜、肤色。

1.3 获得symbol list

c:\cygwin64\bin>x86_64-w64-mingw32-readelf.exe -s task.o

Symbol table '.symtab' contains 53 entries:
   Num:    Value  Size Type    Bind   Vis      Ndx Name
     3: 00000000    16 OBJECT  LOCAL  DEFAULT   11 s_array
     4: 00000000     4 OBJECT  LOCAL  DEFAULT    8 s_variable0
     5: 00000000     4 OBJECT  LOCAL  DEFAULT   10 s_variable2
    45: 00000000     0 FUNC    GLOBAL DEFAULT  UND __aeabi_memcpy
    46: 00000000     0 FUNC    GLOBAL DEFAULT  UND __aeabi_memset
    47: 00000000     0 FUNC    GLOBAL DEFAULT  UND free
    48: 00000000     0 FUNC    GLOBAL DEFAULT  UND malloc
    49: 0000000f    60 FUNC    GLOBAL DEFAULT   12 heap_task
    50: 00000000     4 OBJECT  GLOBAL DEFAULT    9 n_variable1
    51: 00000001    14 FUNC    GLOBAL DEFAULT   12 normal_task
    52: 00000001    16 FUNC    GLOBAL DEFAULT   13 ram_task

  分析symbol
list可见大家在task.c里定义的函数和全局变量的音信,其中Value申明的是各symbol对象(函数/全局变量)在存储器中的分配地址,由于object文件并没有通过链接,所以那里地址音讯是对事情没有什么益处的(待分配的)。翻看到第六节课executable文件里2.2.4一节,便可看到那个symbol对象Value的值初步变得真实有效了。那就表明了怎么object文件是relocatable的。

“近日,所有的人造智能技术,不管多先进,都属于弱人工智能,只好在某一个世界做的跟人大约,而不可见超过人类。”

数量预处理。脚本把数量处理成TFRecords格式。https://github.com/dpressel/rude-carnie/blob/master/preproc.py
https://github.com/GilLevi/AgeGenderDeepLearning/tree/master/Folds文件夹,已经对训练集、测试集划分、标注。gender\_train.txt、gender\_val.txt
图片列表 Adience 数据集处理TFRecords文件。图片处理为大小256×256
JPEG编码RGB图像。tf.python_io.TFRecordWriter写入TFRecords文件,输出文件output_file。

1.1 获得file header

c:\cygwin64\bin>x86_64-w64-mingw32-readelf.exe -h task.o
ELF Header:
  Magic:   7f 45 4c 46 01 01 01 00 00 00 00 00 00 00 00 00
  Class:                             ELF32
  Data:                              2's complement, little endian
  Version:                           1 (current)
  OS/ABI:                            UNIX - System V
  ABI Version:                       0
  Type:                              REL (Relocatable file)
  Machine:                           ARM
  Version:                           0x1
  Entry point address:               0x0
  Start of program headers:          0 (bytes into file)
  Start of section headers:          8283 (bytes into file)
  Flags:                             0x5000000, Version5 EABI
  Size of this header:               52 (bytes)
  Size of program headers:           32 (bytes)
  Number of program headers:         0
  Size of section headers:           40 (bytes)
  Number of section headers:         85
  Section header string table index: 1

  分析file header可见task.o是REL类型ELF文件,其一共包涵85个section
header,没有program header。

公海赌船网站 1

人脸检测。https://github.com/davidsandberg/facenet

  大家好,我是豹哥,猎豹的豹,犀利哥的哥。明日豹哥给大家讲的是嵌入式开发里的relocatable文件(object,
library)

那两年百度的韬略重心偏移到AI那更技术化的取向,李彦宏把人工智能分成三个阶段,第一阶段,弱人工智能。第二等级,强人工智能。第三品级,超人工智能。

def main(args):
with tf.Graph().as_default():
with tf.Session() as sess:

AR在百度内一初始被划到AI业务系统下,并且推出了DuMix
AR开放平台的公测,号称“最AI的AR
SDK”。如今带有了:SDK、内容管理平台和内容创作工具(官方叫生产工具,可能是为着强调开发功用;但大家都知晓,好东西都是要靠“创”出来的,所以自己个人更愿意的是撰写工具)。

weights = tf.Variable(tf.truncated_normal([2048, 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(net, weights), biases, name=scope.name)
_activation_summary(output)
return output
def levi_hassner_bn(nlabels, images, pkeep, is_training):
batch_norm_params = {
“is_training”: is_training,
“trainable”: True,
# Decay for the moving averages.
“decay”: 0.9997,
# Epsilon to prevent 0s in variance.
“epsilon”: 0.001,
# Collection containing the moving mean and moving variance.
“variables_collections”: {
“beta”: None,
“gamma”: None,
“moving_mean”: [“moving_vars”],
“moving_variance”: [“moving_vars”],
}
}
weight_decay = 0.0005
weights_regularizer =
tf.contrib.layers.l2_regularizer(weight_decay)
with tf.variable_scope(“LeviHassnerBN”, “LeviHassnerBN”, [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),
normalizer_fn=batch_norm,
normalizer_params=batch_norm_params):
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′)
conv2 = convolution2d(pool1, 256, [5, 5], [1, 1], padding=’SAME’,
scope=’conv2′)
pool2 = max_pool2d(conv2, 3, 2, padding=’VALID’, scope=’pool2′)
conv3 = convolution2d(pool2, 384, [3, 3], [1, 1], padding=’SAME’,
biases_initializer=tf.constant_initializer(0.), scope=’conv3′)
pool3 = max_pool2d(conv3, 3, 2, padding=’VALID’, scope=’pool3′)
# can use tf.contrib.layer.flatten
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:

一、解析object文件

  task.o文件大小有11683bytes,而从源文件里看其仅包括4个变量和3个函数,可知更加多的数据是记录性数据。

其官网给出的试用申请界面则协助公司和个体二种重点项目,列出的问卷项中,大家可以看看它对AR的部分知情:

数据预处理。校准代码
https://github.com/davidsandberg/facenet/blob/master/src/align/align\_dataset\_mtcnn.py

检测所用数据集校准为和预训练模型所用数据集大小相同。
安装环境变量

  前三节课里,豹哥都是在给我们介绍嵌入式开发中的input文件。从今日那节课起初,豹哥就陆续为我们讲output文件。上一节课project文件里讲说到project文件是一个承接的文本,后天豹哥就为大家讲project生成的率先类output文件:relocatable文件。

当前亟待商家才能申请入驻开放平台,这从开发者生态建设上看犹如不怎么偏保守了。

if FLAGS.face_detection_model:
print(‘Using face detector (%s) %s’ % (FLAGS.face_detection_type,
FLAGS.face_detection_model))
face_detect = face_detection_model(FLAGS.face_detection_type,
FLAGS.face_detection_model)
face_files, rectangles = face_detect.run(FLAGS.filename)
print(face_files)
files += face_files
config = tf.ConfigProto(allow_soft_placement=True)
with tf.Session(config=config) as sess:
label_list = AGE_LIST if FLAGS.class_type == ‘age’ else
GENDER_LIST
nlabels = len(label_list)
print(‘Executing on %s’ % FLAGS.device_id)
model_fn = select_model(FLAGS.model_type)
with tf.device(FLAGS.device_id):

二、关于library文件

  本质上library文件跟object文件是一律的,都是未经链接器链接的文书。library文件的利用场景是,在有些独特场所,你不想把你的C源代码开放给别人阅读和无限制修改,然而你又需求分享你的代码给旁人利用,怎么化解那个问题?library文件就是缓解这一个题材的,可以依靠编译器的取舍(IAR下是Options->General
Options->Output->Output
file里挑选Library(默认是executable)),那么添加进整个工程的所有源文件会被汇编封装成一个.a文书(即library文件),那时候你只须要将该.a文件以及配套API头文件分享给外人即可。旁人只必要加上你的.a文件以及配套.h文件进她协调的工程,便可直接调用你的API。

  至此,嵌入式开发里的relocatable文件(object,
library)文件豹哥便介绍完结了,掌声在何地~~~

AR能力急需

  • 识图触发
  • 2D跟踪
  • SLAM
  • 手势交互
  • 3D识别
  • Logo识别
  • 人脸识别
  • 身体识别
  • 多目标
  • 语言交互
  • 连天扫描
  • LBS触发

自我当下做的毕业设计是化学晶体结构教学可视化设计,基于虚拟现实技术将晶体结构做成交互体现,在那时候看来那不啻有点大题小作,盖上虚拟现实的帽子,只为已毕一个交互式的3D突显课件,但把当下的显得界面从电脑屏幕转移到学生书本上的一副晶体结构图和一个手机app,学生拿手机扫一下那一个晶体结构图,就可以在二弟大上显现立体互动式学习体验,那不就是一种AR应用了吧?

def parse_arguments(argv):
parser = argparse.ArgumentParser()


AR(Augmented
Reality),普通话翻译增强现实。按自己原来的学问体系,VR/AR的技能构成是如出一辙的,只是追求的方向差异。VR是杜撰笼罩现实、让虚拟就是现实性;AR则让虚拟进入实际。二者最后看似不一样,但又不约而同,虚拟与现实的界限被破绽百出,唯心与唯物的管理学辩论进入下一个循环。

人脸检测。检测、定位图片人脸,重返高业饿啊人脸框坐标。对人脸分析、处理的第一步。“滑动窗口”,选取图像矩形区域作滑动窗口,窗口中提取特征对图像区域描述,依照特征描述判断窗口是否人脸。不断遍历需求着眼窗口。

  文件涉及:source文件

AR应用场景

  • 营销活动
  • 摄像直播
  • 文化教育
  • 观光外出
  • 游戏游戏
  • 电商导购
  • 失业家装
  • 穿着试戴

if step % 1000 == 0 or (step + 1) == num_steps:
saver.save(sess, checkpoint_path, global_step=step)
if __name__ == ‘__main__’:
tf.app.run()

  relocatable文件,即可重定向文件,那些文件是由编译器汇编源文件(.c/.s)而成的。直接生成的重定向文件叫object
file,经过包装的重定向文件称为library
file。可重定向文件属于ELF文件的分层,关于ELF文件的详细解释可知第六节课executable文件
  本文主演object file和library
file,仅是一个中档的联网文件,其本身也无法被ARM直接执行,需通过第二步转换,即链接,所以那多少个文件都是链接器的输入文件。让大家来大致解析一下那多个公文。在先导分析之前大家先回到上一节课project文件的最终成立的demo工程上,编译那几个demo工程得以收获如下.o文件,那一个文件全是object文件,每一个源文件都对应一个object文件,本文以task.o为例讲解relocatable文件。

saver = tf.train.Saver()
saver.restore(sess, model_checkpoint_path)

1.2 获得section header

c:\cygwin64\bin>x86_64-w64-mingw32-readelf.exe -S task.o
There are 85 section headers, starting at offset 0x205b:

Section Headers:
  [Nr] Name              Type            Addr     Off    Size   ES Flg Lk Inf Al
  [ 0]                   NULL            00000000 000034 000000 00      0   0  0
  [ 1] .shstrtab         STRTAB          00000000 000034 0001eb 00      0   0  0
  [ 2] .symtab           SYMTAB          00000000 00021f 000350 10      3  45  0
  [ 3] .strtab           STRTAB          00000000 00056f 000248 00      0   0  0
  [ 8] .bss              NOBITS          00000000 000e1c 000004 00  WA  0   0  4
  [ 9] .noinit           NOBITS          00000000 000e1c 000004 00  WA  0   0  4
  [10] .data             PROGBITS        00000000 000e1c 000004 00  WA  0   0  4
  [11] .bss              NOBITS          00000000 000e20 000010 00  WA  0   0  4
  [12] .text             PROGBITS        00000000 000e20 000058 00  AX  0   0  4
  [13] .textrw           PROGBITS        00000000 000e78 000010 00 WAX  0   0  4
Key to Flags:
  W (write), A (alloc), X (execute), M (merge), S (strings), I (info),
  L (link order), O (extra OS processing required), G (group), T (TLS),
  C (compressed), x (unknown), o (OS specific), E (exclude),
  y (purecode), p (processor specific)

  分析section header可见该task.o里的逐一常见section(.bss, .noinit,
.data, .text,
.textrw)的大小,各类段的含义详见第四节课linker文件

人脸识别分类。

D:\myProject\bsp\builds\demo\Release\Obj\main.o
D:\myProject\bsp\builds\demo\Release\Obj\reset.o
D:\myProject\bsp\builds\demo\Release\Obj\startup.o
D:\myProject\bsp\builds\demo\Release\Obj\startup_MKL25Z4.o
D:\myProject\bsp\builds\demo\Release\Obj\system_MKL25Z4.o
D:\myProject\bsp\builds\demo\Release\Obj\task.o -o

人脸图像特征提取。人脸图像信息数字化,人脸图像转变为一串数字(特征向量)。如,眼睛左侧、嘴唇右侧、鼻子、下巴地方,特征点间欧氏距离、曲率、角度提取出特色分量,相关特征连接成长特征向量。

writer = None
output = None
if FLAGS.target:
print(‘Creating output file %s’ % FLAGS.target)
output = open(FLAGS.target, ‘w’)
writer = csv.writer(output)
writer.writerow((‘file’, ‘label’, ‘score’))
image_files = list(filter(lambda x: x is not None, [resolve_file(f)
for f in files]))
print(image_files)
if FLAGS.single_look:
classify_many_single_crop(sess, label_list, softmax_output, coder,
images, image_files, writer)
else:
for image_file in image_files:
classify_one_multi_crop(sess, label_list, softmax_output, coder,
images, image_file, writer)
if output is not None:
output.close()

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

校准命令

# Read the file containing the pairs used for testing
# 1. 读入从前的pairs.txt文件
# 读入后如[[‘Abel_Pacheco’,’1′,’4′]]
pairs = lfw.read_pairs(os.path.expanduser(args.lfw_pairs))
# Get the paths for the corresponding images
# 获取文件路径和是否匹配关系对
paths, actual_issame =
lfw.get_paths(os.path.expanduser(args.lfw_dir), pairs,
args.lfw_file_ext)
# Load the model
# 2. 加载模型
facenet.load_model(args.model)

预训练模型20170216-091149.zip
https://drive.google.com/file/d/0B5MzpY9kBtDVZ2RpVDYwWmxoSUk
训练集 MS-Celeb-1M数据集
https://www.microsoft.com/en-us/research/project/ms-celeb-1m-challenge-recognizing-one-million-celebrities-real-world/
。微软人脸识别数据库,名家榜采用前100万名流,搜索引擎采集每个名家100张人脸图片。预陶冶模型准确率0.993+-0.004。

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 levi_hassner(nlabels, images, pkeep, is_training):
weight_decay = 0.0005
weights_regularizer =
tf.contrib.layers.l2_regularizer(weight_decay)
with tf.variable_scope(“LeviHassner”, “LeviHassner”, [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:

for step in xrange(num_steps):
start_time = time.time()
_, loss_value = sess.run([train_op, total_loss])
duration = time.time() – start_time
assert not np.isnan(loss_value), ‘Model diverged with loss = NaN’
# 每10步记录一次摘要文件,保存一个检查点文件
if step % 10 == 0:
num_examples_per_step = FLAGS.batch_size
examples_per_sec = num_examples_per_step / duration
sec_per_batch = float(duration)

with tf.variable_scope(‘output’) as scope:

images = tf.placeholder(tf.float32, [None, RESIZE_FINAL,
RESIZE_FINAL, 3])
logits = model_fn(nlabels, images, 1, False)
init = tf.global_variables_initializer()

检测。python src/validate_on_lfw.py datasets/lfw/lfw_mtcnnpy_160
models
条件比较,采取facenet/data/pairs.txt,官方随机生成多少,匹配和不匹配人名和图纸编号。

LFW(Labeled Faces in the Wild
Home)数据集。http://vis-www.cs.umass.edu/lfw/
。美利坚联邦合众国加州圣地亚哥分校大学阿姆斯特分校总括机视觉实验室整理。13233张图纸,5749人。4096人只有一张图片,1680人多于一张。每张图片尺寸250×250。人脸图片在每个人物名字文件夹下。

output /= batch_sz
best = np.argmax(output) # 最可能性能分类
best_choice = (label_list[best], output[best])
print(‘Guess @ 1 %s, prob = %.2f’ % best_choice)

Florian Schroff、Dmitry Kalenichenko、James Philbin论文《FaceNet: A
Unified Embedding for Face Recognition and Clustering》
https://arxiv.org/abs/1503.03832
https://github.com/davidsandberg/facenet/wiki/Validate-on-lfw

参考资料:
《TensorFlow技术解析与实战》

教练模型。https://github.com/dpressel/rude-carnie/blob/master/train.py

for N in {1..4}; do python src/align/align_dataset_mtcnn.py
~/datasets/lfw/raw ~/datasets/lfw/lfw_mtcnnpy_160 –image_size 160
–margin 32 –random_order –gpu_memory_fraction 0.25 & done

人脸关键点检测。定位、再次来到人脸五官、概略关键点坐标地点。人脸概况、眼睛、眉毛、嘴唇、鼻子轮廓。Face++提供高达106点关键点。人脸关键点定位技术,级联形回归(cascaded
shape regression,
CSR)。人脸识别,基于DeepID网络布局。DeepID网络布局类似卷积神经网络布局,尾数第二层,有DeepID层,与卷积层4、最大池化层3相连,卷积神经网络层数越高视野域越大,既考虑部分特征,又考虑全局特征。输入层
31x39x1、卷积层1 28x36x20(卷积核4x4x1)、最大池化层1
12x18x20(过滤器2×2)、卷积层2 12x16x20(卷积核3x3x20)、最大池化层2
6x8x40(过滤器2×2)、卷积层3 4x6x60(卷积核3x3x40)、最大池化层2
2x3x60(过滤器2×2)、卷积层4 2x2x80(卷积核2x2x60)、DeepID层
1×160、全连接层 Softmax。《Deep Learning Face Representation from
Predicting 10000 Classes》
http://mmlab.ie.cuhk.edu.hk/pdf/YiSun\_CVPR14.pdf

if os.path.isfile(abspath) and any([abspath.endswith(‘.’ + ty) for ty
in (‘jpg’, ‘png’, ‘JPG’, ‘PNG’, ‘jpeg’)]):
print(abspath)
files.append(abspath)
else:
files.append(FLAGS.filename)
# If it happens to be a list file, read the list and clobber the
files
if any([FLAGS.filename.endswith(‘.’ + ty) for ty in (‘csv’, ‘tsv’,
‘txt’)]):
files = list_images(FLAGS.filename)

欢迎推荐香江机械学习工作机会,我的微信:qingxingfengzi

return [row[0] for row in reader]
def main(argv=None): # pylint: disable=unused-argument
files = []

构建模型。年龄、性别陶冶模型,Gil Levi、Tal Hassner散文《Age and Gender
Classification Using Convolutional Neural
Networks》http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.722.9654&rank=1
。模型 https://github.com/dpressel/rude-carnie/blob/master/model.py
。tenforflow.contrib.slim。

for i in range(1, batch_sz):
output = output + batch_results[i]

十折交叉验证(10-fold cross
validation),精度测试方法。数据集分成10份,轮流将中间9份做陶冶集,1份做测试保,10次结果均值作算法精度揣度。一般需求反复10折交叉验证求均值。

微软脸部图片识别性别、年龄网站 http://how-old.net/
。图片识别年龄、性别。按照问题查找图片。

#image_size = images_placeholder.get_shape()[1] # For some reason
this doesn’t work for frozen graphs
image_size = args.image_size
embedding_size = embeddings.get_shape()[1]

人脸识别技术流程。

Adience
数据集。http://www.openu.ac.il/home/hassner/Adience/data.html\#agegender
。26580张图片,2284类,年龄范围8个区段(0~2、4~6、8~13、15~20、25~32、38~43、48~53、60~),含有噪声、姿势、光照变化。aligned
# 经过剪裁对齐多少,faces #
原始数据。fold_0_data.txt至fold_4_data.txt
整体多少符号。fold_frontal_0_data.txt至fold_frontal_4_data.txt
仅用接近正面态度面部标记。数据结构 user_id
用户Flickr帐户ID、original_image 图片文件名、face_id
人标识符、age、gender、x、y、dx、dy 人脸边框、tilt_ang
切斜角度、fiducial_yaw_angle 基准偏移角度、fiducial_score
基准分数。https://www.flickr.com/

# Run forward pass to calculate embeddings
# 3. 使用前向传来验证
print(‘Runnning forward pass on LFW images’)
batch_size = args.lfw_batch_size
nrof_images = len(paths)
nrof_batches = int(math.ceil(1.0*nrof_images / batch_size)) #
总共批次数
emb_array = np.zeros((nrof_images, embedding_size))
for i in range(nrof_batches):
start_index = i*batch_size
end_index = min((i+1)*batch_size, nrof_images)
paths_batch = paths[start_index:end_index]
images = facenet.load_data(paths_batch, False, False, image_size)
feed_dict = { images_placeholder:images,
phase_train_placeholder:False }
emb_array[start_index:end_index,:] = sess.run(embeddings,
feed_dict=feed_dict)

人脸识别,基于人脸部特征消息识别身份的海洋生物识别技术。视频机、视频头采集人脸图像或视频流,自动检测、跟踪图像中脸部,做脸部相关技能处理,人脸检测、人脸关键点检测、人脸验证等。《斯坦福科技评价》(MIT
Technology
Review),前年海内外十大突破性技术榜单,支付宝“刷脸支付”(Paying with Your
Face)入围。

requested_step = FLAGS.requested_step if FLAGS.requested_step else
None

人脸图像预处理。基于人脸检测结果,处理图像,服务特征提取。系统得到人脸图像遭到各样规格限制、随机烦扰,需缩放、旋转、拉伸、光线补偿、灰度变换、直方图均衡化、规范化、几何矫正、过滤、锐化等图像预处理。

checkpoint_path = ‘%s’ % (FLAGS.model_dir)
model_checkpoint_path, global_step =
get_checkpoint(checkpoint_path, requested_step, FLAGS.checkpoint)

if __name__ == ‘__main__’:
tf.app.run()

人脸图像匹配、识别。提取人脸图像特点数据与数据库存储人脸特征模板搜索匹配,依照相似程度对身份消息举办判断,设定阈值,相似度越过阈值,输出匹配结果。确认,一对一(1:1)图像相比较,讲明“你就是您”,金融核实身份、音讯安全球。辨认,一对多(1:N)图像匹配,“N人中找你”,视频流,人走进识别范围就完事辨认,安防领域。

from __future__ import absolute_import
from __future__ import division
from __future__ import print_function
from six.moves import xrange
from datetime import datetime
import time
import os
import numpy as np
import tensorflow as tf
from data import distorted_inputs
from model import select_model
import json
import re
LAMBDA = 0.01
MOM = 0.9
tf.app.flags.DEFINE_string(‘pre_checkpoint_path’, ”,
“””If specified, restore this pretrained model “””
“””before beginning any training.”””)
tf.app.flags.DEFINE_string(‘train_dir’,
‘/home/dpressel/dev/work/AgeGenderDeepLearning/Folds/tf/test_fold_is_0’,
‘Training directory’)
tf.app.flags.DEFINE_boolean(‘log_device_placement’, False,
“””Whether to log device placement.”””)
tf.app.flags.DEFINE_integer(‘num_preprocess_threads’, 4,
‘Number of preprocessing threads’)
tf.app.flags.DEFINE_string(‘optim’, ‘Momentum’,
‘Optimizer’)
tf.app.flags.DEFINE_integer(‘image_size’, 227,
‘Image size’)
tf.app.flags.DEFINE_float(‘eta’, 0.01,
‘Learning rate’)
tf.app.flags.DEFINE_float(‘pdrop’, 0.,
‘Dropout probability’)
tf.app.flags.DEFINE_integer(‘max_steps’, 40000,
‘Number of iterations’)
tf.app.flags.DEFINE_integer(‘steps_per_decay’, 10000,
‘Number of steps before learning rate decay’)
tf.app.flags.DEFINE_float(‘eta_decay_rate’, 0.1,
‘Learning rate decay’)
tf.app.flags.DEFINE_integer(‘epochs’, -1,
‘Number of epochs’)
tf.app.flags.DEFINE_integer(‘batch_size’, 128,
‘Batch size’)
tf.app.flags.DEFINE_string(‘checkpoint’, ‘checkpoint’,
‘Checkpoint name’)
tf.app.flags.DEFINE_string(‘model_type’, ‘default’,
‘Type of convnet’)
tf.app.flags.DEFINE_string(‘pre_model’,
”,#’./inception_v3.ckpt’,
‘checkpoint file’)
FLAGS = tf.app.flags.FLAGS
# Every 5k steps cut learning rate in half
def exponential_staircase_decay(at_step=10000, decay_rate=0.1):
print(‘decay [%f] every [%d] steps’ % (decay_rate, at_step))
def _decay(lr, global_step):
return tf.train.exponential_decay(lr, global_step,
at_step, decay_rate, staircase=True)
return _decay
def optimizer(optim, eta, loss_fn, at_step, decay_rate):
global_step = tf.Variable(0, trainable=False)
optz = optim
if optim == ‘Adadelta’:
optz = lambda lr: tf.train.AdadeltaOptimizer(lr, 0.95, 1e-6)
lr_decay_fn = None
elif optim == ‘Momentum’:
optz = lambda lr: tf.train.MomentumOptimizer(lr, MOM)
lr_decay_fn = exponential_staircase_decay(at_step, decay_rate)
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):
labels = tf.cast(labels, tf.int32)
cross_entropy = tf.nn.sparse_softmax_cross_entropy_with_logits(
logits=logits, labels=labels, name=’cross_entropy_per_example’)
cross_entropy_mean = tf.reduce_mean(cross_entropy,
name=’cross_entropy’)
tf.add_to_collection(‘losses’, cross_entropy_mean)
losses = tf.get_collection(‘losses’)
regularization_losses =
tf.get_collection(tf.GraphKeys.REGULARIZATION_LOSSES)
total_loss = cross_entropy_mean + LAMBDA *
sum(regularization_losses)
tf.summary.scalar(‘tl (raw)’, total_loss)
#total_loss = tf.add_n(losses + regularization_losses,
name=’total_loss’)
loss_averages = tf.train.ExponentialMovingAverage(0.9, name=’avg’)
loss_averages_op = loss_averages.apply(losses + [total_loss])
for l in losses + [total_loss]:
tf.summary.scalar(l.op.name + ‘ (raw)’, l)
tf.summary.scalar(l.op.name, loss_averages.average(l))
with tf.control_dependencies([loss_averages_op]):
total_loss = tf.identity(total_loss)
return total_loss
def main(argv=None):
with tf.Graph().as_default():
model_fn = select_model(FLAGS.model_type)
# Open the metadata file and figure out nlabels, and size of epoch
#
打开元数据文件md.json,这么些文件是在预处理多少时生成。找出nlabels、epoch大小
input_file = os.path.join(FLAGS.train_dir, ‘md.json’)
print(input_file)
with open(input_file, ‘r’) as f:
md = json.load(f)
images, labels, _ = distorted_inputs(FLAGS.train_dir,
FLAGS.batch_size, FLAGS.image_size, FLAGS.num_preprocess_threads)
logits = model_fn(md[‘nlabels’], images, 1-FLAGS.pdrop, True)
total_loss = loss(logits, labels)
train_op = optimizer(FLAGS.optim, FLAGS.eta, total_loss,
FLAGS.steps_per_decay, FLAGS.eta_decay_rate)
saver = tf.train.Saver(tf.global_variables())
summary_op = tf.summary.merge_all()
sess = tf.Session(config=tf.ConfigProto(
log_device_placement=FLAGS.log_device_placement))
tf.global_variables_initializer().run(session=sess)
# This is total hackland, it only works to fine-tune iv3
# 本例可以输入预训练模型Inception V3,可用来微调 Inception V3
if FLAGS.pre_model:
inception_variables = tf.get_collection(
tf.GraphKeys.VARIABLES, scope=”InceptionV3″)
restorer = tf.train.Saver(inception_variables)
restorer.restore(sess, FLAGS.pre_model)
if FLAGS.pre_checkpoint_path:
if tf.gfile.Exists(FLAGS.pre_checkpoint_path) is True:
print(‘Trying to restore checkpoint from %s’ %
FLAGS.pre_checkpoint_path)
restorer = tf.train.Saver()
tf.train.latest_checkpoint(FLAGS.pre_checkpoint_path)
print(‘%s: Pre-trained model restored from %s’ %
(datetime.now(), FLAGS.pre_checkpoint_path))
# 将ckpt文件存储在run-(pid)目录
run_dir = ‘%s/run-%d’ % (FLAGS.train_dir, os.getpid())
checkpoint_path = ‘%s/%s’ % (run_dir, FLAGS.checkpoint)
if tf.gfile.Exists(run_dir) is False:
print(‘Creating %s’ % run_dir)
tf.gfile.MakeDirs(run_dir)
tf.train.write_graph(sess.graph_def, run_dir, ‘model.pb’,
as_text=True)
tf.train.start_queue_runners(sess=sess)
summary_writer = tf.summary.FileWriter(run_dir, sess.graph)
steps_per_train_epoch = int(md[‘train_counts’] /
FLAGS.batch_size)
num_steps = FLAGS.max_steps if FLAGS.epochs < 1 else FLAGS.epochs
* steps_per_train_epoch
print(‘Requested number of steps [%d]’ % num_steps)

from __future__ import absolute_import
from __future__ import division
from __future__ import print_function
from datetime import datetime
import time
import os
import numpy as np
import tensorflow as tf
from data import distorted_inputs
import re
from tensorflow.contrib.layers import *
from tensorflow.contrib.slim.python.slim.nets.inception_v3 import
inception_v3_base
TOWER_NAME = ‘tower’
def select_model(name):
if name.startswith(‘inception’):
print(‘selected (fine-tuning) inception model’)
return inception_v3
elif name == ‘bn’:
print(‘selected batch norm model’)
return levi_hassner_bn
print(‘selected default model’)
return levi_hassner
def get_checkpoint(checkpoint_path, requested_step=None,
basename=’checkpoint’):
if requested_step is not None:
model_checkpoint_path = ‘%s/%s-%s’ % (checkpoint_path, basename,
requested_step)
if os.path.exists(model_checkpoint_path) is None:
print(‘No checkpoint file found at [%s]’ % checkpoint_path)
exit(-1)
print(model_checkpoint_path)
print(model_checkpoint_path)
return model_checkpoint_path, requested_step
ckpt = tf.train.get_checkpoint_state(checkpoint_path)
if ckpt and ckpt.model_checkpoint_path:
# Restore checkpoint as described in top of this program
print(ckpt.model_checkpoint_path)
global_step =
ckpt.model_checkpoint_path.split(‘/’)[-1].split(‘-‘)[-1]
return ckpt.model_checkpoint_path, global_step
else:
print(‘No checkpoint file found at [%s]’ % checkpoint_path)
exit(-1)
def _activation_summary(x):
tensor_name = re.sub(‘%s_[0-9]*/’ % TOWER_NAME, ”, x.op.name)
tf.summary.histogram(tensor_name + ‘/activations’, x)
tf.summary.scalar(tensor_name + ‘/sparsity’, tf.nn.zero_fraction(x))
def inception_v3(nlabels, images, pkeep, is_training):
batch_norm_公海赌船网站,params = {
“is_training”: is_training,
“trainable”: True,
# Decay for the moving averages.
“decay”: 0.9997,
# Epsilon to prevent 0s in variance.
“epsilon”: 0.001,
# Collection containing the moving mean and moving variance.
“variables_collections”: {
“beta”: None,
“gamma”: None,
“moving_mean”: [“moving_vars”],
“moving_variance”: [“moving_vars”],
}
}
weight_decay = 0.00004
stddev=0.1
weights_regularizer =
tf.contrib.layers.l2_regularizer(weight_decay)
with tf.variable_scope(“InceptionV3”, “InceptionV3”, [images]) as
scope:
with tf.contrib.slim.arg_scope(
[tf.contrib.slim.conv2d, tf.contrib.slim.fully_connected],
weights_regularizer=weights_regularizer,
trainable=True):
with tf.contrib.slim.arg_scope(
[tf.contrib.slim.conv2d],
weights_initializer=tf.truncated_normal_initializer(stddev=stddev),
activation_fn=tf.nn.relu,
normalizer_fn=batch_norm,
normalizer_params=batch_norm_params):
net, end_points = inception_v3_base(images, scope=scope)
with tf.variable_scope(“logits”):
shape = net.get_shape()
net = avg_pool2d(net, shape[1:3], padding=”VALID”, scope=”pool”)
net = tf.nn.dropout(net, pkeep, name=’droplast’)
net = flatten(net, scope=”flatten”)

# Get input and output tensors
# 获取输入输出张量
images_placeholder =
tf.get_default_graph().get_tensor_by_name(“input:0”)
embeddings =
tf.get_default_graph().get_tensor_by_name(“embeddings:0”)
phase_train_placeholder =
tf.get_default_graph().get_tensor_by_name(“phase_train:0”)

from __future__ import absolute_import
from __future__ import division
from __future__ import print_function
import tensorflow as tf
import numpy as np
import argparse
import facenet
import lfw
import os
import sys
import math
from sklearn import metrics
from scipy.optimize import brentq
from scipy import interpolate

# 4. 盘算准确率、验证率,十折交叉验证办法
tpr, fpr, accuracy, val, val_std, far = lfw.evaluate(emb_array,
actual_issame, nrof_folds=args.lfw_nrof_folds)
print(‘Accuracy: %1.3f+-%1.3f’ % (np.mean(accuracy),
np.std(accuracy)))
print(‘Validation rate: %2.5f+-%2.5f @ FAR=%2.5f’ % (val, val_std,
far))
# 得到auc值
auc = metrics.auc(fpr, tpr)
print(‘Area Under Curve (AUC): %1.3f’ % auc)
# 1获得错误率(eer)
eer = brentq(lambda x: 1. – x – interpolate.interp1d(fpr, tpr)(x), 0.,
1.)
print(‘Equal Error Rate (EER): %1.3f’ % eer)

性别、年龄识别。https://github.com/dpressel/rude-carnie

softmax_output = tf.nn.softmax(logits)
coder = ImageCoder()
# Support a batch mode if no face detection model
if len(files) == 0:
if (os.path.isdir(FLAGS.filename)):
for relpath in os.listdir(FLAGS.filename):
abspath = os.path.join(FLAGS.filename, relpath)

人脸图像采集、检测。人脸图像采集,摄像头把人脸图像采集下来,静态图像、动态图像、分化岗位、分化表情。用户在采访设备拍报范围内,采集设置自动检索并素描。人脸检测属于目的检测(object
detection)。对要检测对象对象概率统计,得到待检测对象特征,建立目的检测模型。用模子匹配输入图像,输出匹配区域。人脸检测是人脸识别预处理,准确标定人脸在图像的岗位大小。人脸图像格局特点丰硕,直方图特征、颜色特征、模板特征、结构特征、哈尔(Hal)特征(Haar-like
feature)。人脸检测挑出有用新闻,用特色检测脸部。人脸检测算法,模板匹配模型、Adaboost模型,艾达boost模型速度。精度综合性能最好,陶冶慢、检测快,可达成视频流实时检测效果。

batch_image_files = image_files[start_offset:end_offset]
print(start_offset, end_offset, len(batch_image_files))
image_batch = make_multi_image_batch(batch_image_files, coder)
batch_results = sess.run(softmax_output,
feed_dict={images:image_batch.eval()})
batch_sz = batch_results.shape[0]
for i in range(batch_sz):
output_i = batch_results[i]
best_i = np.argmax(output_i)
best_choice = (label_list[best_i], output_i[best_i])
print(‘Guess @ 1 %s, prob = %.2f’ % best_choice)
if writer is not None:
f = batch_image_files[i]
writer.writerow((f, best_choice[0], ‘%.2f’ % best_choice[1]))
pg.update()
pg.done()
except Exception as e:
print(e)
print(‘Failed to run all images’)
def classify_one_multi_crop(sess, label_list, softmax_output,
coder, images, image_file, writer):
try:
print(‘Running file %s’ % image_file)
image_batch = make_multi_crop_batch(image_file, coder)
batch_results = sess.run(softmax_output,
feed_dict={images:image_batch.eval()})
output = batch_results[0]
batch_sz = batch_results.shape[0]

export PYTHONPATH=[…]/facenet/src

人脸验证。分析两张人脸同一人可能大小。输入两张人脸,得到置信度分类、相应阈值,评估相似度。

parser.add_argument(‘lfw_dir’, type=str,
help=’Path to the data directory containing aligned LFW face
patches.’)
parser.add_argument(‘–lfw_batch_size’, type=int,
help=’Number of images to process in a batch in the LFW test set.’,
default=100)
parser.add_argument(‘model’, type=str,
help=’Could be either a directory containing the meta_file and
ckpt_file or a model protobuf (.pb) file’)
parser.add_argument(‘–image_size’, type=int,
help=’Image size (height, width) in pixels.’, default=160)
parser.add_argument(‘–lfw_pairs’, type=str,
help=’The file containing the pairs to use for validation.’,
default=’data/pairs.txt’)
parser.add_argument(‘–lfw_file_ext’, type=str,
help=’The file extension for the LFW dataset.’, default=’png’,
choices=[‘jpg’, ‘png’])
parser.add_argument(‘–lfw_nrof_folds’, type=int,
help=’Number of folds to use for cross validation. Mainly used for
testing.’, default=10)
return parser.parse_args(argv)
if __name__ == ‘__main__’:
main(parse_arguments(sys.argv[1:]))

证实模型。https://github.com/dpressel/rude-carnie/blob/master/guess.py

from __future__ import absolute_import
from __future__ import division
from __future__ import print_function
from datetime import datetime
import math
import time
from data import inputs
import numpy as np
import tensorflow as tf
from model import select_model, get_checkpoint
from utils import *
import os
import json
import csv
RESIZE_FINAL = 227
GENDER_LIST =[‘M’,’F’]
AGE_LIST = [‘(0, 2)’,'(4, 6)’,'(8, 12)’,'(15, 20)’,'(25, 32)’,'(38,
43)’,'(48, 53)’,'(60, 100)’]
MAX_BATCH_SZ = 128
tf.app.flags.DEFINE_string(‘model_dir’, ”,
‘Model directory (where training data lives)’)
tf.app.flags.DEFINE_string(‘class_type’, ‘age’,
‘Classification type (age|gender)’)
tf.app.flags.DEFINE_string(‘device_id’, ‘/cpu:0’,
‘What processing unit to execute inference on’)
tf.app.flags.DEFINE_string(‘filename’, ”,
‘File (Image) or File list (Text/No header TSV) to process’)
tf.app.flags.DEFINE_string(‘target’, ”,
‘CSV file containing the filename processed along with best guess and
score’)
tf.app.flags.DEFINE_string(‘checkpoint’, ‘checkpoint’,
‘Checkpoint basename’)
tf.app.flags.DEFINE_string(‘model_type’, ‘default’,
‘Type of convnet’)
tf.app.flags.DEFINE_string(‘requested_step’, ”, ‘Within the model
directory, a requested step to restore e.g., 9000’)
tf.app.flags.DEFINE_boolean(‘single_look’, False, ‘single look at the
image or multiple crops’)
tf.app.flags.DEFINE_string(‘face_detection_model’, ”, ‘Do frontal
face detection with model specified’)
tf.app.flags.DEFINE_string(‘face_detection_type’, ‘cascade’, ‘Face
detection model type (yolo_tiny|cascade)’)
FLAGS = tf.app.flags.FLAGS
def one_of(fname, types):
return any([fname.endswith(‘.’ + ty) for ty in types])
def resolve_file(fname):
if os.path.exists(fname): return fname
for suffix in (‘.jpg’, ‘.png’, ‘.JPG’, ‘.PNG’, ‘.jpeg’):
cand = fname + suffix
if os.path.exists(cand):
return cand
return None
def classify_many_single_crop(sess, label_list, softmax_output,
coder, images, image_files, writer):
try:
num_batches = math.ceil(len(image_files) / MAX_BATCH_SZ)
pg = ProgressBar(num_batches)
for j in range(num_batches):
start_offset = j * MAX_BATCH_SZ
end_offset = min((j + 1) * MAX_BATCH_SZ, len(image_files))

format_str = (‘%s: step %d, loss = %.3f (%.1f examples/sec; %.3f ‘
‘sec/batch)’)
print(format_str % (datetime.now(), step, loss_value,
examples_per_sec, sec_per_batch))
# Loss only actually evaluated every 100 steps?
if step % 100 == 0:
summary_str = sess.run(summary_op)
summary_writer.add_summary(summary_str, step)

nlabels = len(label_list)
if nlabels > 2:
output[best] = 0
second_best = np.argmax(output)
print(‘Guess @ 2 %s, prob = %.2f’ % (label_list[second_best],
output[second_best]))
if writer is not None:
writer.writerow((image_file, best_choice[0], ‘%.2f’ %
best_choice[1]))
except Exception as e:
print(e)
print(‘Failed to run image %s ‘ % image_file)
def list_images(srcfile):
with open(srcfile, ‘r’) as csvfile:
delim = ‘,’ if srcfile.endswith(‘.csv’) else ‘\t’
reader = csv.reader(csvfile, delimiter=delim)
if srcfile.endswith(‘.csv’) or srcfile.endswith(‘.tsv’):
print(‘skipping header’)
_ = next(reader)

人脸识别应用,美图秀秀美颜应用、世纪佳缘查看地下配偶“面相”相似度,支付领域“刷脸支付”,安防领域“人脸鉴权”。Face++、商汤科技,提供人脸识别SDK。

人脸识别优势,非强制性(采集情势不便于被察觉,被识别人脸图像可积极赢得)、非接触性(用户不要求与装备接触)、并发性(可同时三个人脸检测、跟踪、识别)。深度学习前,人脸识别两手续:高维人工特征提取、降维。传统人脸识别技术基于可知光图像。深度学习+大数据(海量有标注人脸数据)为人脸识别领域主流技术途径。神经网络人脸识别技术,大批量样书图像训练识别模型,无需人工接纳特征,样本训练进度自行学习,识别准确率可以直达99%。

相关文章