py-faster-rcnn算法caffe配置，训练及应用到自己的数据集

下载faster r-cnn
git clone --recursive https://github.com/rbgirshick/py-faster-rcnn.git 进入py-faster-rcnn/lib
make

结果如下图：



进入py-faster-rcnn/caffe-fast-rcnn

cp Makefile.config.example MAkefile.config

然后配置Makefile.config文件，可参考我的Makefile.config

## Refer to http://caffe.berkeleyvision.org/installation.html # Contributions simplifying and improving our build system are welcome!

# cuDNN acceleration switch (uncomment to build with cuDNN).
USE_CUDNN := 1

# CPU-only switch (uncomment to build without GPU support).
# CPU_ONLY := 1

# uncomment to disable IO dependencies and corresponding data layers
# USE_OPENCV := 0
# USE_LEVELDB := 0
# USE_LMDB := 0

# uncomment to allow MDB_NOLOCK when reading LMDB files (only if necessary)
#	You should not set this flag if you will be reading LMDBs with any
#	possibility of simultaneous read and write
# ALLOW_LMDB_NOLOCK := 1

# Uncomment if you're using OpenCV 3
# OPENCV_VERSION := 3

# To customize your choice of compiler, uncomment and set the following.
# N.B. the default for Linux is g++ and the default for OSX is clang++
# CUSTOM_CXX := g++

# CUDA directory contains bin/ and lib/ directories that we need.
CUDA_DIR := /usr/local/cuda
# On Ubuntu 14.04, if cuda tools are installed via
# "sudo apt-get install nvidia-cuda-toolkit" then use this instead:
# CUDA_DIR := /usr

# CUDA architecture setting: going with all of them.
# For CUDA < 6.0, comment the *_50 lines for compatibility.
CUDA_ARCH := -gencode arch=compute_30,code=sm_30 \
-gencode arch=compute_35,code=sm_35 \
-gencode arch=compute_50,code=sm_50 \
-gencode arch=compute_50,code=compute_50 \
-gencode arch=compute_53,code=compute_53 \
-gencode arch=compute_61,code=compute_61

# BLAS choice:
# atlas for ATLAS (default)
# mkl for MKL
# open for OpenBlas
BLAS := open
# Custom (MKL/ATLAS/OpenBLAS) include and lib directories.
# Leave commented to accept the defaults for your choice of BLAS
# (which should work)!
# BLAS_INCLUDE := /path/to/your/blas
# BLAS_LIB := /path/to/your/blas

# Homebrew puts openblas in a directory that is not on the standard search path
# BLAS_INCLUDE := $(shell brew --prefix openblas)/include
# BLAS_LIB := $(shell brew --prefix openblas)/lib

# This is required only if you will compile the matlab interface.
# MATLAB directory should contain the mex binary in /bin.
MATLAB_DIR := /usr/local/MATLAB/R2013b
# MATLAB_DIR := /Applications/MATLAB_R2012b.app

# NOTE: this is required only if you will compile the python interface.
# We need to be able to find Python.h and numpy/arrayobject.h.
PYTHON_INCLUDE := /usr/include/python2.7 \
/usr/lib64/python2.7/site-packages/numpy/core/include \
/usr/lib/python2.7/dist-packages/numpy/core/include
# Anaconda Python distribution is quite popular. Include path:
# Verify anaconda location, sometimes it's in root.
# ANACONDA_HOME := $(HOME)/anaconda
# PYTHON_INCLUDE := $(ANACONDA_HOME)/include \
# $(ANACONDA_HOME)/include/python2.7 \
# $(ANACONDA_HOME)/lib/python2.7/site-packages/numpy/core/include \

# Uncomment to use Python 3 (default is Python 2)
# PYTHON_LIBRARIES := boost_python3 python3.5m
# PYTHON_INCLUDE := /usr/include/python3.5m \
#                 /usr/lib/python3.5/dist-packages/numpy/core/include

# We need to be able to find libpythonX.X.so or .dylib.
PYTHON_LIB := /usr/lib
# PYTHON_LIB := $(ANACONDA_HOME)/lib

# Homebrew installs numpy in a non standard path (keg only)
# PYTHON_INCLUDE += $(dir $(shell python -c 'import numpy.core; print(numpy.core.__file__)'))/include
# PYTHON_LIB += $(shell brew --prefix numpy)/lib

# Uncomment to support layers written in Python (will link against Python libs)
WITH_PYTHON_LAYER := 1

# Whatever else you find you need goes here.
INCLUDE_DIRS := $(PYTHON_INCLUDE) /usr/local/include
LIBRARY_DIRS := $(PYTHON_LIB) /usr/local/lib /usr/lib

# If Homebrew is installed at a non standard location (for example your home directory) and you use it for general dependencies
INCLUDE_DIRS += /usr/local/hdf5/include
LIBRARY_DIRS += /usr/local/hdf5/lib

# Uncomment to use `pkg-config` to specify OpenCV library paths.
# (Usually not necessary -- OpenCV libraries are normally installed in one of the above $LIBRARY_DIRS.)
# USE_PKG_CONFIG := 1

# N.B. both build and distribute dirs are cleared on `make clean`
BUILD_DIR := build
DISTRIBUTE_DIR := distribute

# Uncomment for debugging. Does not work on OSX due to https://github.com/BVLC/caffe/issues/171 # DEBUG := 1

# The ID of the GPU that 'make runtest' will use to run unit tests.
TEST_GPUID := 0

# enable pretty build (comment to see full commands)
Q ?= @

执行：make all -j8
结果如下图：



执行:make pycaffe
结果如下图：



下载在VOC2007trainval上预训练的faster r-cnn检测器：
执行：
./data/scripts/fetch_faster_rcnn_models.sh
下载的模型如图所示：



运行演示脚本，
./tools/demo.py
检测结果如下图：（脚本用的是VGG16_faster_rcnn_final.caffemodel）





下载VOCdevkit训练，验证，测试数据集：
wget http://host.robots.ox.ac.uk/pascal/VOC/voc2007/VOCtrainval_06-Nov-2007.tar wget http://host.robots.ox.ac.uk/pascal/VOC/voc2007/VOCtest_06-Nov-2007.tar wgethttp://host.robots.ox.ac.uk/pascal/VOC/voc2007/VOCdevkit_08-Jun-2007.tar
提取压缩文件放到VOCdevkit文件夹下：
tar xvf VOCtrainval_06-Nov-2007.tar
tar xvf VOCtest_06-Nov-2007.tar
tar xvf VOCdevkit_08-Jun-2007.tar
文件夹的结构如下图所示：



为VOCdevkit创建VOCdevkit2007快捷方式，

cd data
ln -s $VOCdevkit VOCdevkit2007
格式如下图所示：



下载在ImageNet上预训练好的模型：
执行：
./data/scripts/fetch_imagenet_models.sh
下载的模型如下图所示：（ResNet.v2.caffemodel是我额外再下载的）



下面开始用voc2007进行训练，执行：
./experiments/scripts/faster_rcnn_end2end.sh [GPU_ID] [NET] [--set ...]
./experiments/scripts/faster_rcnn_end2end.sh 0 ZF pascal_voc(联合训练)
./experiments/scripts/faster_rcnn_alt_opt.sh 0 ZF pascal_voc(分步训练)
下面开始用faster r-cnn来训练自己的数据集（我使用的是faster_rcnn_end2end.sh来执行训练）：

首先需要修改网络模型文件：
1./py-faster-rcnn/models/pascal_voc/VGG16/faster_rcnn_end2end/train.prototxt

name: "VGG_ILSVRC_16_layers"
layer {
name: 'input-data'
type: 'Python'
top: 'data'
top: 'im_info'
top: 'gt_boxes'
python_param {
module: 'roi_data_layer.layer'
layer: 'RoIDataLayer'
param_str: "'num_classes': 2" #数目为训练类别+1
}
}
layer {
name: 'roi-data'
type: 'Python'
bottom: 'rpn_rois'
bottom: 'gt_boxes'
top: 'rois'
top: 'labels'
top: 'bbox_targets'
top: 'bbox_inside_weights'
top: 'bbox_outside_weights'
python_param {
module: 'rpn.proposal_target_layer'
layer: 'ProposalTargetLayer'
param_str: "'num_classes': 2"
}
}
layer {
name: "cls_score"
type: "InnerProduct"
bottom: "fc7"
top: "cls_score"
param {
lr_mult: 1
}
param {
lr_mult: 2
}
inner_product_param {
num_output: 2
weight_filler {
type: "gaussian"
std: 0.01
}
bias_filler {
type: "constant"
value: 0
}
}
}
layer {
name: "bbox_pred"
type: "InnerProduct"
bottom: "fc7"
top: "bbox_pred"
param {
lr_mult: 1
}
param {
lr_mult: 2
}
inner_product_param {
num_output: 8 #（类别数+1）*4
weight_filler {
type: "gaussian"
std: 0.001
}
bias_filler {
type: "constant"
value: 0
}
}
}

2./py-faster-rcnn/models/pascal_voc/VGG16/faster_rcnn_end2end/test.prototxt

layer {
name: "cls_score"
type: "InnerProduct"
bottom: "fc7"
top: "cls_score"
param {
lr_mult: 1
decay_mult: 1
}
param {
lr_mult: 2
decay_mult: 0
}
inner_product_param {
num_output: 2
weight_filler {
type: "gaussian"
std: 0.01
}
bias_filler {
type: "constant"
value: 0
}
}
}
layer {
name: "bbox_pred"
type: "InnerProduct"
bottom: "fc7"
top: "bbox_pred"
param {
lr_mult: 1
decay_mult: 1
}
param {
lr_mult: 2
decay_mult: 0
}
inner_product_param {
num_output: 8
weight_filler {
type: "gaussian"
std: 0.001
}
bias_filler {
type: "constant"
value: 0
}
}
}

3.修改/home/amax/guowei/py-faster-rcnn/lib/datasets/pascal_voc.py

class pascal_voc(imdb):
def __init__(self, image_set, year, devkit_path=None):
imdb.__init__(self, 'voc_' + year + '_' + image_set)
self._year = year
self._image_set = image_set
self._devkit_path = self._get_default_path() if devkit_path is None \
else devkit_path
self._data_path = os.path.join(self._devkit_path, 'VOC' + self._year)
self._classes = ('__background__', # always index 0
'aeroplane')
self._class_to_ind = dict(zip(self.classes, xrange(self.num_classes)))
self._image_ext = '.jpg'

修改self._classes为你的类别加背景。
4./home/amax/guowei/py-faster-rcnn/lib/datasets/factory.py修改
for year in ['2007', '2012','2001','2002','2006','5000']:
for split in ['train', 'val', 'trainval', 'test']:
name = 'voc_{}_{}'.format(year, split)
__sets[name] = (lambda split=split, year=year: pascal_voc(split, year))
我的数据集叫：VOC5000，所以把5000加到年份当中。
5/home/amax/guowei/py-faster-rcnn/experiments/scripts/faster_rcnn_end2end.sh修改
case $DATASET in
pascal_voc)
TRAIN_IMDB="voc_5000_trainval"
TEST_IMDB="voc_5000_test"
PT_DIR="pascal_voc"
ITERS=4000
;;
把训练数据集和测试数据集改为你的数据集，迭代次数改为4000。
开始训练，执行下面程序：
/experiments/scripts/faster_rcnn_end2end.sh 0 VGG16 pascal_voc
我的numpy更新到了最新版，如果出现和数据类型相关错误，可参考以下：链接：
http://www.itwendao.com/article/detail/380118.html
实验结果如下图：



利用VGG16，迭代了4000次，取得了78.8%的精度。