深度学习与人脸识别系列（4）__利用caffe训练深度学习模型

一：下载训练集和测试集

训练集的下载地址:http://www.cbsr.ia.ac.cn/english/CASIA-WebFace-Database.html

测试集的下载地址: http://vis-www.cs.umass.edu/lfw/

二:利用linux脚本生成训练集

 #!/bin/bash


 #-----------------------------------------------------------------------------------------


 #生成训练集和验证集
 #made by 郭开


 #-----------------------------------------------------------------------------------------


 #保存图片的路径
 PATH=/media/gk/9ec75485-26b1-471f-9b7b-d18554ca3fdd/aa
 echo "start..."
 #遍历文件夹
 for name in $PATH/webface_img/*;do
         var=0
 #遍历文件夹中的图片
         for file_name in $name/*;do
             var=$(($var+1));
             str=$file_name
             #保存图片路径
             str=${str#*img}
             #保存图片lable
             lable=${str#*/}
             lable=${lable%%/*}
             if [ "$var" = "1" ] || [ "$var" = "3" ] || [ "$var" = "5" ]; then
             #验证集
             echo $str" "$lable>>/home/gk/val.txt
             else
             #测试集
             echo $str" "$lable>>/home/gk/train.txt
             fi
 done
 done
 echo "Done."

生成的文件如下图:

三：将图片转换成LMDB格式

 #!/usr/bin/env sh


 #-----------------------------------------------------------------------------------------


 # 将图片批量生成lmbd格式的数据存储
 #made by 郭开


 #-----------------------------------------------------------------------------------------

 #保存生成的lmdb的目录
 EXAMPLE=/media/gk/9ec75485-26b1-471f-9b7b-d18554ca3fdd/aa/lmdb_webface

 #train.txt和val.txt所在的目录
 DATA=/home/gk

 #转换图片的工具所在的目录
 TOOLS=/home/gk/caffe-master/build/tools

 #图片所在的目录
 TRAIN_DATA_ROOT=/media/gk/9ec75485-26b1-471f-9b7b-d18554ca3fdd/aa/webface_img

 VAL_DATA_ROOT=/media/gk/9ec75485-26b1-471f-9b7b-d18554ca3fdd/aa/webface_img

 # 设置 RESIZE=true 可以把图片resize成想要的尺寸。
 RESIZE=true
 if $RESIZE; then
   RESIZE_HEIGHT=227
   RESIZE_WIDTH=227
 else
   RESIZE_HEIGHT=0
   RESIZE_WIDTH=0
 fi


 if [ ! -d "$TRAIN_DATA_ROOT" ]; then
   echo "Error: TRAIN_DATA_ROOT is not a path to a directory: $TRAIN_DATA_ROOT"
   echo "Set the TRAIN_DATA_ROOT variable in create_imagenet.sh to the path" \
        "where the ImageNet training data is stored."
   exit 1
 fi


 if [ ! -d "$VAL_DATA_ROOT" ]; then
   echo "Error: VAL_DATA_ROOT is not a path to a directory: $VAL_DATA_ROOT"
   echo "Set the VAL_DATA_ROOT variable in create_imagenet.sh to the path" \
        "where the ImageNet validation data is stored."
   exit 1
 fi


 echo "Creating train lmdb..."


 GLOG_logtostderr=1 $TOOLS/convert_imageset \
     --resize_height=$RESIZE_HEIGHT \
     --resize_width=$RESIZE_WIDTH \
     --shuffle \
     $TRAIN_DATA_ROOT \
     $DATA/train.txt \
     $EXAMPLE/train_lmdb


 echo "Creating val lmdb..."


 GLOG_logtostderr=1 $TOOLS/convert_imageset \
     --resize_height=$RESIZE_HEIGHT \
     --resize_width=$RESIZE_WIDTH \
     --shuffle \
     $VAL_DATA_ROOT \
     $DATA/val.txt \
     $EXAMPLE/val_lmdb


 echo "Done."

四：计算图片的mean或者设置scale：0.00390625

 #!/usr/bin/env sh


 #-----------------------------------------------------------------------------------------


 # 计算图像均值
 #made by 郭开


 #-----------------------------------------------------------------------------------------
 #lmdb格式的文件所在的路径
 EXAMPLE=/media/gk/9ec75485-26b1-471f-9b7b-d18554ca3fdd/aa/lmdb_webface
 #均值文件保存的路径
 DATA=/media/gk/44CA719BCA718A46
 #转换图片的工具所在的目录
 TOOLS=/home/gk/caffe-master/build/tools

 $TOOLS/compute_image_mean $EXAMPLE/train_lmdb \
   $DATA/mean.binaryproto

 echo "Done."

五：训练模型

./build/tools/caffe train --solver=models/bvlc_reference_caffenet/solver.prototxt

slover.prototxt

 net: "/home/gk/caffe-master/examples/vgg/train.prototxt"
 test_iter: 100
 test_interval: 1000


 base_lr: 0.001
 lr_policy: "step"
 gamma: 0.95
 stepsize:  100000
 momentum: 0.9
 weight_decay: 0.0005
 display: 100
 max_iter:  5000000
 snapshot:  50000
 snapshot_prefix: "/home/gk/caffe-master/examples/DeepID/snapshot"
 solver_mode: GPU
 device_id:0
 #debug_info: true

tarin.prototxt

 name: "VGG_FACE_16_layers"
 layer {
   top: "data_1"
   top: "label_1"
   name: "data_1"
   type: "Data"
   data_param {
     source: "/media/gk/9ec75485-26b1-471f-9b7b-d18554ca3fdd/aa/webface_lmdb/train"
     backend:LMDB
     batch_size: 128
   }
   transform_param {
      mean_file: "/media/gk/9ec75485-26b1-471f-9b7b-d18554ca3fdd/aa/webface_lmdb/mean.binaryproto"
      mirror: true
   }
   include: { phase: TRAIN }
 }


 layer {
   top: "data_1"
   top: "label_1"
   name: "data_1"
   type: "Data"
   data_param {
     source: "/media/gk/9ec75485-26b1-471f-9b7b-d18554ca3fdd/aa/webface_lmdb/val"
     backend:LMDB
     batch_size: 128
   }
   transform_param {
     mean_file: "/media/gk/9ec75485-26b1-471f-9b7b-d18554ca3fdd/aa/webface_lmdb/mean.binaryproto"
     mirror: true
   }
   include: {
     phase: TEST
   }
 }


 layers {
   bottom: "data"
   top: "conv1_1"
   name: "conv1_1"
   type: CONVOLUTION
   convolution_param {
     num_output: 64
     pad: 1
     kernel_size: 3
   }
 }
 layers {
   bottom: "conv1_1"
   top: "conv1_1"
   name: "relu1_1"
   type: RELU
 }
 layers {
   bottom: "conv1_1"
   top: "conv1_2"
   name: "conv1_2"
   type: CONVOLUTION
   convolution_param {
     num_output: 64
     pad: 1
     kernel_size: 3
   }
 }
 layers {
   bottom: "conv1_2"
   top: "conv1_2"
   name: "relu1_2"
   type: RELU
 }
 layers {
   bottom: "conv1_2"
   top: "pool1"
   name: "pool1"
   type: POOLING
   pooling_param {
     pool: MAX
     kernel_size: 2
     stride: 2
   }
 }
 layers {
   bottom: "pool1"
   top: "conv2_1"
   name: "conv2_1"
   type: CONVOLUTION
   convolution_param {
     num_output: 128
     pad: 1
     kernel_size: 3
   }
 }
 layers {
   bottom: "conv2_1"
   top: "conv2_1"
   name: "relu2_1"
   type: RELU
 }
 layers {
   bottom: "conv2_1"
   top: "conv2_2"
   name: "conv2_2"
   type: CONVOLUTION
   convolution_param {
     num_output: 128
     pad: 1
     kernel_size: 3
   }
 }
 layers {
   bottom: "conv2_2"
   top: "conv2_2"
   name: "relu2_2"
   type: RELU
 }
 layers {
   bottom: "conv2_2"
   top: "pool2"
   name: "pool2"
   type: POOLING
   pooling_param {
     pool: MAX
     kernel_size: 2
     stride: 2
   }
 }
 layers {
   bottom: "pool2"
   top: "conv3_1"
   name: "conv3_1"
   type: CONVOLUTION
   convolution_param {
     num_output: 256
     pad: 1
     kernel_size: 3
   }
 }
 layers {
   bottom: "conv3_1"
   top: "conv3_1"
   name: "relu3_1"
   type: RELU
 }
 layers {
   bottom: "conv3_1"
   top: "conv3_2"
   name: "conv3_2"
   type: CONVOLUTION
   convolution_param {
     num_output: 256
     pad: 1
     kernel_size: 3
   }
 }
 layers {
   bottom: "conv3_2"
   top: "conv3_2"
   name: "relu3_2"
   type: RELU
 }
 layers {
   bottom: "conv3_2"
   top: "conv3_3"
   name: "conv3_3"
   type: CONVOLUTION
   convolution_param {
     num_output: 256
     pad: 1
     kernel_size: 3
   }
 }
 layers {
   bottom: "conv3_3"
   top: "conv3_3"
   name: "relu3_3"
   type: RELU
 }
 layers {
   bottom: "conv3_3"
   top: "pool3"
   name: "pool3"
   type: POOLING
   pooling_param {
     pool: MAX
     kernel_size: 2
     stride: 2
   }
 }
 layers {
   bottom: "pool3"
   top: "conv4_1"
   name: "conv4_1"
   type: CONVOLUTION
   convolution_param {
     num_output: 512
     pad: 1
     kernel_size: 3
   }
 }
 layers {
   bottom: "conv4_1"
   top: "conv4_1"
   name: "relu4_1"
   type: RELU
 }
 layers {
   bottom: "conv4_1"
   top: "conv4_2"
   name: "conv4_2"
   type: CONVOLUTION
   convolution_param {
     num_output: 512
     pad: 1
     kernel_size: 3
   }
 }
 layers {
   bottom: "conv4_2"
   top: "conv4_2"
   name: "relu4_2"
   type: RELU
 }
 layers {
   bottom: "conv4_2"
   top: "conv4_3"
   name: "conv4_3"
   type: CONVOLUTION
   convolution_param {
     num_output: 512
     pad: 1
     kernel_size: 3
   }
 }
 layers {
   bottom: "conv4_3"
   top: "conv4_3"
   name: "relu4_3"
   type: RELU
 }
 layers {
   bottom: "conv4_3"
   top: "pool4"
   name: "pool4"
   type: POOLING
   pooling_param {
     pool: MAX
     kernel_size: 2
     stride: 2
   }
 }
 layers {
   bottom: "pool4"
   top: "conv5_1"
   name: "conv5_1"
   type: CONVOLUTION
   convolution_param {
     num_output: 512
     pad: 1
     kernel_size: 3
   }
 }
 layers {
   bottom: "conv5_1"
   top: "conv5_1"
   name: "relu5_1"
   type: RELU
 }
 layers {
   bottom: "conv5_1"
   top: "conv5_2"
   name: "conv5_2"
   type: CONVOLUTION
   convolution_param {
     num_output: 512
     pad: 1
     kernel_size: 3
   }
 }
 layers {
   bottom: "conv5_2"
   top: "conv5_2"
   name: "relu5_2"
   type: RELU
 }
 layers {
   bottom: "conv5_2"
   top: "conv5_3"
   name: "conv5_3"
   type: CONVOLUTION
   convolution_param {
     num_output: 512
     pad: 1
     kernel_size: 3
   }
 }