人脸识别CNN网络微调流程

版权声明：本文为博主原创文章，未经博主允许不得转载。 https://blog.csdn.net/yudiemiaomiao/article/details/78708896

目标
微调论文”A Lightened CNN for Deep Face Representation”中的29层caffe网络。

数据
自己收集的包含500人的亚洲人脸数据集；

训练数据准备
1.获得500人微调数据集之后，使用python源码工具将数据集划分为训练集和验证集：

#!---* coding: utf-8 --*--
#!/usr/bin/python

"""
将数据集随机分成训练集、验证集、测试集

"""

from PIL import Image, ImageFile
import random
import os, time
import logging



logger = logging.getLogger(__name__)
ImageFile.LOAD_TRUNCATED_IMAGES = True


class CreateDataSet:
      """
      创建train、val、test数据集
      """
      def __init__(self):
          pass


      @staticmethod
      def randNumber(li,num):
          temp_li=li
          res=random.sample(li,num)
          for i in res:
              temp_li.remove(i)
          #print ("res len=%d"%len(res))
          #print ("temp_li len=%d"%len(temp_li))
          return res,temp_li


      @staticmethod
      def openImage(image):
          return Image.open(image, mode="r")

      @staticmethod
      def saveImage(image, path):
          image.save(path)


def makeDir(path):
      try:
          if not os.path.exists(path):
                if not os.path.isfile(path):
                   # os.mkdir(path)
                    os.makedirs(path)
                    return 0
          else:
                return 1
      except Exception as e:
          print (str(e))
          return -2


def save(image, des_path, class_name,file_name): 
      temp_name=os.path.join(des_path,class_name)
      file_name=os.path.join(temp_name,file_name)
      CreateDataSet.saveImage(image, file_name)


is_create_test=0
ratio=0.1

def create(path, new_path):
      """
        多线程处理事务
        :param src_path: 资源文件
        :param des_path: 目的地文件
        :return:
      """
      train_sample_path=os.path.join(new_path, "train")
      val_sample_path=os.path.join(new_path, "val")
      test_sample_path=os.path.join(new_path, "test")

      if (os.path.isdir(new_path)):
          if makeDir(train_sample_path) == -1: 
               print ('create train dir failure')
               return -1    
          if makeDir(val_sample_path) == -1: 
               print ('create val dir failure')
               return -1   
          if(is_create_test==1):
               if makeDir(test_sample_path) == -1: 
                    print ('create test dir failure')
                    return -1    
      else:
          print ('the input param new_path is not the dir')
          return -1
      if os.path.isdir(path):
          class_names = os.listdir(path)
      else:
          print ('the input param path is not the dir')
          return -1
      for name in class_names:
          print ("process class name=%s"%name)
          tmp_class_name = os.path.join(path, name)
          val_sample_num=0;
          test_sample_num=0;
          val_total_sample_num=0;
          test_total_sample_num=0;
          if (os.path.isdir(tmp_class_name)):
                image_names=os.listdir(tmp_class_name)
                total=len(image_names)
                li = [i for i in range(total)] 
                val_total_sample_num=int(total*ratio)
                val_name_list,remain_list=CreateDataSet.randNumber(li,val_total_sample_num)
                if(is_create_test==1):
                      test_total_sample_num=int(total*ratio)    
                      test_name_list,remain_list=CreateDataSet.randNumber(remain_list,test_total_sample_num)
                #read val sample
                if makeDir(os.path.join(val_sample_path,name)) == -1: 
                    print ('create val class dir failure')
                    return -1 
                print ("val sample number=%d"%val_total_sample_num)
                #print val_name_list
                while(val_sample_num<val_total_sample_num):
                      index=val_name_list[val_sample_num]
                      temp_img_name=os.path.join(tmp_class_name,image_names[index])
                      if(os.path.isfile(temp_img_name)):
                            image = CreateDataSet.openImage(temp_img_name)
                            save(image,val_sample_path,name,image_names[index])
                      val_sample_num=val_sample_num+1
                #read  test sample
                if(is_create_test==1):
                      if makeDir(os.path.join(test_sample_path,name)) == -1: 
                           print ('create test class dir failure')
                           return -1 
                      print ("test sample number=%d"%test_total_sample_num)
                      #print test_name_list
                while(test_sample_num<test_total_sample_num):
                      index=test_name_list[test_sample_num]
                      temp_img_name=os.path.join(tmp_class_name,image_names[index])
                      if(os.path.isfile(temp_img_name)):
                            image = CreateDataSet.openImage(temp_img_name)
                            save(image,test_sample_path,name,image_names[index])
                      test_sample_num=test_sample_num+1
                #read train sample
                if makeDir(os.path.join(train_sample_path,name)) == -1: 
                    print ('create train class dir failure')
                    return -1 
                print ("train sample number=%d"%len(remain_list))
                #print remain_list
                for train in remain_list:
                      temp_img_name=os.path.join(tmp_class_name,image_names[train])
                      if(os.path.isfile(temp_img_name)):
                            image = CreateDataSet.openImage(temp_img_name)
                            save(image,train_sample_path,name,image_names[train])
                print ("finish")

if __name__ == '__main__':
        create("H:\\Finetuning-500","H:\\Finetuning-500_new")

所得的训练集和验证集放置Finetuning-500_new中。

2.利用gen_train_val_txt.py生成训练集和验证集的图片列表及其对应标签的txt文件(label标签需从0开始)；将Finetuning-500_new放置/home/Data文件夹下，并在caffe-master/examples/下新建文件夹Finetuning-500，将gen_train_val_txt.py放置该文件夹下；

#!---* coding: utf-8 --*--
#!/usr/bin/python
import os
class CaffeData:
    def __init__(self):
        pass
    @staticmethod
    def create_train_txt(train_data_path,train_txt_path):
        txt_path = train_txt_path + '/' + r'train.txt'
        f = open(txt_path, "w")
        count = 0
        for dir_name in os.listdir(val_data_path):
            #   count=0
            for file_name in os.listdir(os.path.join(val_data_path, dir_name)):
            #   count=count+1
            #   img_file_path='/'+dir_name+'/'+file_name+" "+dir_name
            #   img_file_path='/'+dir_name+'/'+file_name
                img_file_path = '/' + dir_name + '/' + file_name + " " + str(count)
                f.write(img_file_path + '\n')
          # print '{} class: {}'.format(dir_name,count)
            count = count + 1

    @staticmethod
    def create_val_txt(val_data_path,val_txt_path):
        txt_path=val_txt_path +'/'+r'val.txt'
        f=open(txt_path,"w")
        count=0
        for dir_name in os.listdir(val_data_path):
        #   count=0
            for file_name in os.listdir(os.path.join(val_data_path,dir_name)):
#               count=count+1
#               img_file_path='/'+dir_name+'/'+file_name+" "+dir_name
          #     img_file_path='/'+dir_name+'/'+file_name
                img_file_path = '/'+dir_name+'/'+file_name+" "+ str(count)
                f.write(img_file_path+'\n')
#       print '{} class: {}'.format(dir_name,count)
        count=count+1

if __name__ == '__main__':
    CaffeData.create_train_txt(r'/home/Data/Finetuning-500_new/train',r'/home/yi_miao/caffe-master/examples/Finetuning-500')
    CaffeData.create_val_txt(r'/home/Data/Finetuning-500_new/val',r'/home/yi_miao/caffe-master/examples/Finetuning-500')

#finetuning 数据集

生成的训练集和验证集的图片列表及其对应标签的txt文件内容如下：

利用CreateLmdb.sh脚本文件生成训练集和验证集的lmdb数据格式，CreateLmdb.sh位于caffe-master/examples/Finetuning-500下；

#!/bin/sh

CAFFE_ROOT='/***/caffe-master/'
TOOLS=$CAFFE_ROOT/build/tools

EXAMPLE=$CAFFE_ROOT/examples/Finetuning-500
TRAIN_TXT=$EXAMPLE/train.txt
VAL_TXT=$EXAMPLE/val.txt


DATA=$CAFFE_ROOT/data/Finetuning-500
TRAIN_DATA_ROOT=/home/Data/Finetuning-500_new/train
VAL_DATA_ROOT=/home/Data/Finetuning-500_new/val
TRAIN_DATA_LMDB=$DATA/train_lmdb
VAL_DATA_LMDB=$DATA/val_lmdb


IMG_WIDTH=144
IMG_HEIGHT=144

# Set RESIZE=true to resize the images. Leave as false if images have already been resized using another tool.
RESIZE=true

if $RESIZE; then
    RESIZE_HEIGHT=$IMG_HEIGHT
    RESIZE_WIDTH=$IMG_WIDTH
else
    RESIZE_HEIGHT=0
    RESIZE_WIDTH=0
fi


if [ -d "$TRAIN_DATA_LMDB" ]; then
    rm -rf $TRAIN_DATA_LMDB
fi

if [ -d "$VAL_DATA_LMDB" ]; then
    rm -rf $VAL_DATA_LMDB
fi

if [ ! -d "$TRAIN_DATA_ROOT" ]; then
    echo "Error: TRAIN_DATA_ROOT is not a path to a directory: $TRAIN_DATA_ROOT"
    exit 1
fi

if [ ! -d "$VAL_DATA_ROOT" ]; then
   echo "Error: VAL_DATA_ROOT is not a path to a directory: $VAL_DATA_ROOT"
   exit 1
fi


echo $RESIZE_HEIGHT
echo $RESIZE_WIDTH

echo "Creating train lmdb..."

GLOG_logtostderr=1 $TOOLS/convert_imageset \
     --resize_height=$RESIZE_HEIGHT \
     --resize_width=$RESIZE_WIDTH \
     --shuffle \
     --gray=true \
     $TRAIN_DATA_ROOT \
     $TRAIN_TXT \
     $TRAIN_DATA_LMDB\

echo "Creating val lmdb..."

GLOG_logtostderr=1 $TOOLS/convert_imageset \
     --resize_height=$RESIZE_HEIGHT \
     --resize_width=$RESIZE_WIDTH \
     --shuffle \
     --gray=true \
     $VAL_DATA_ROOT \
     $VAL_TXT \
     $VAL_DATA_LMDB 

echo "Done"

利用CreateMeanFile.sh脚本文件生成训练集和验证集的lmdb数据格式，CreateMeanFile.sh位于caffe-master/examples/Finetuning-500下；

#!/bin/sh

CAFFE_ROOT='/***/caffe-master'

TOOLS=$CAFFE_ROOT/build/tools
DATA=$CAFFE_ROOT/data/Finetuning-500
EXAMPLE=$CAFFE_ROOT/examples/Finetuning-500
TRAIN_DATA_LMDB=$DATA/train_lmdb
VAL_DATA_LMDB=$DATA/val_lmdb
TRAIN_MEAN=$DATA/train_data_mean.binaryproto
VAL_MEAN=$DATA/val_data_mean.binaryproto

$TOOLS/compute_image_mean $TRAIN_DATA_LMDB \
  $TRAIN_MEAN 


$TOOLS/compute_image_mean $VAL_DATA_LMDB \
  $VAL_MEAN

使用caffe，微调模型
方法一：
1.修改train_test.prototxt和solver.prototxt文件
以Light CNN29网络模型为例，考虑到数据量较少，LCNN29微调过程中，保留前面层的参数，修改最后一层fc2为fc2_500，将最后预测种类设置为500，添加propagate_down:0参数，微调过程中只训练最后一个全连接fc2_500层，保持前面层的参数不变；

layer{
  name: "fc2_qh_500"  //modify
  type: "InnerProduct"
  bottom: "eltwise_fc1"
  top: "fc2_qh_500"   //modify
  param {
    lr_mult: 1
    decay_mult: 1
  }
  param {
    lr_mult: 2
    decay_mult: 0
  }
  propagate_down:0    //modify
  inner_product_param{
     num_output: 500  //modify
    weight_filler {
       type: "xavier"
  #      type:"gaussian"
  #      std:0.01
    }
    bias_filler {
      type: "constant"
      value: 0.1
    }
  }
}

问题：
测试通过设置propagate_down参数训练的网络模型，由设置fc2层propagate_down为0微调得到的网络模型，虽然成功识别的数量与原始模型差不多，但失败的数量大大增加，根据资料所说：设置fc2层propagate_down为0，只会微调fc2层的参数，前面层的参数理论上保持不变，因此在利用fc1层特征进行人脸识别时效果应该和原始模型一致，但测试结果差异较大，对该参数的具体作用存在疑问，希望有人能答疑解惑。

方法二
希望C层的参数不会改变，但是C前面的AB层的参数会改变，这种情况，只是固定了C层的参数，C层得到的梯度依然会反向传播给前面的B层。只需要将对应的参数blob的学习率调整为0：在layer里面加上param { lr_mult: 0 decay_mult:0}就可以了，比如全连接层里面，这里设置fc2层的lr_mult和decay_mult参数为0：

layer {    
type: "InnerProduct"    
param { 
# 对应第1个参数blob的配置，也就是全连接层的参数矩阵的配置         
  lr_mult: 0 # 学习率为0，其他参数可以看caffe.proto里面的ParamSpec这个类型 
  decay_mult: 0  
 } 
param {    
 # 对应第2个参数blob的配置，也就是全连接层的偏置项的配置   
 lr_mult: 0 # 学习率为0  
 decay_mult: 0 
}

对学习率的设置
初始学习率设置为0.001，并以inv方式进行衰减。发现loss逐渐衰减了，但迭代2万多次后，损失函数值又开始上升，需要调小学习率，将初始学习率设为0.0001

net: "/***/caffe-master/examples/Finetuning-500/train_test.prototxt"
test_iter: 580       # 580*16(batchsize)=9280>4028
test_interval:1340   # 1340*64(batchsize)=85760>85743
test_compute_loss: true

base_lr: 0.0001
#lr_policy:"step"
#gamma:0.1
#stepsize:20000
momentum: 0.9
weight_decay: 0.0005
lr_policy: "inv"
gamma: 0.00005
power: 0.75

display: 50
max_iter: 500000
snapshot: 5000
snapshot_prefix: "/***/caffe-master/examples/Finetuning-500/snapshot/"
solver_mode: GPU
#solver_mode: CPU
debug_info: false

后续逐步增加微调层数进行微调，但由于数据量较少，微调较多的层数效果反而不如微调最后两个全连接层。