$ sudo cp Makefile.config.example Makefile.config # 備份配置檔案

$ sudo gedit Makefile.config  # 修改編譯檔案

`````````````````````````````````````````````````````````````````````````````

## 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 := 1
# 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_20,code=sm_20 \
-gencode arch=compute_20,code=sm_21 \
-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

# BLAS choice:
# atlas for ATLAS (default)
# mkl for MKL
# open for OpenBlas
BLAS := mkl
# 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_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/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)/anaconda2
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 usr/include/hdf5/serial/
LIBRARY_DIRS := $(PYTHON_LIB) /usr/local/lib /usr/lib /usr/lib/x86_64-linux-gnu /usr/lib/x86_64-linux-gnu/hdf5/serial

# If Homebrew is installed at a non standard location (for example your home directory) and you use it for general dependencies
# INCLUDE_DIRS += $(shell brew --prefix)/include
# LIBRARY_DIRS += $(shell brew --prefix)/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

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 ?= @

``````````````````````````````````````````````````````````````````````````````````````````````````````

在Makefile中，由於faster rcnn用的是老版本的caffe，不支援cudnnv5，所以需要修改。

Makefile: 找到第397行，NVCCFLAGS += -ccbin=$(CXX) -Xcompiler -fPIC $(COMMON_FLAGS)修改為NVCCFLAGS += -D_FORCE_INLINES -ccbin=$(CXX) -Xcompiler -fPIC $(COMMON_FLAGS) (添加了-D_FORCE_INLINES引數 更新用到的caffe：原版py-faster-rcnn依賴的caffe比較老，不支援cudnnv5,那就更新下對應的原始碼。 用最新caffe原始碼的以下檔案替換掉faster rcnn 的對應檔案 include/caffe/layers/cudnn_relu_layer.hpp, src/caffe/layers/cudnn_relu_layer.cpp, src/caffe/layers/cudnn_relu_layer.cu include/caffe/layers/cudnn_sigmoid_layer.hpp, src/caffe/layers/cudnn_sigmoid_layer.cpp, src/caffe/layers/cudnn_sigmoid_layer.cu include/caffe/layers/cudnn_tanh_layer.hpp, src/caffe/layers/cudnn_tanh_layer.cpp, src/caffe/layers/cudnn_tanh_layer.cu 用caffe原始碼中的這個檔案替換掉faster rcnn 對應檔案 include/caffe/util/cudnn.hpp 將 faster rcnn 中的 src/caffe/layers/cudnn_conv_layer.cu 檔案中的所有 cudnnConvolutionBackwardData_v3 函式名替換為 cudnnConvolutionBackwardData cudnnConvolutionBackwardFilter_v3函式名替換為 cudnnConvolutionBackwardFilter

然後執行 make -j8

最後執行 make pycaffe

7、編譯成功之後

在全部編譯成功之後，還不能完全代表環境配置正確。先跑一個demo，訓練或者識別，先試一下，環境是否正常。這編譯成功只是代表著程式碼環境沒有了問題，如果需要訓練或者識別，要下載VOC資料集和與訓練模型。

1️⃣下載VOC2007資料集

解壓，然後，將該資料集放在py-faster-rcnn\data下，用你的資料集替換VOC2007資料集。（替換Annotations，ImageSets和JPEGImages）

（用你的Annotations，ImagesSets和JPEGImages替換py-faster-rcnn\data\VOCdevkit2007\VOC2007中對應資料夾）

2️⃣下載ImageNet資料集下預訓練得到的模型引數（用來初始化）

解壓，然後將該檔案放在py-faster-rcnn\data下

配置好環境之後，訓練自己製作的資料集 1、將自己製作的資料集（pic和xml）放到faster-rcnn的根目錄下的data中。其中Annotation用來存放xml檔案，JPEGImages用來存放圖片，ImagesSets用來存放參與訓練的檔名。在所有參與訓練的檔案中，有一部分的比例是Trainval，其餘是test。然後Trainval中又有一部分是train，另外一部分是val。訓練需要將檔案隨機的分配給trianval和test，所以需要一個指令碼將參與訓練的檔案隨機按照比例分配。在這裡是一個matlab的程式。 2、安置好待訓練的資料集之後，需要根據自己訓練的分類的類別修改相應的配置。 對於不同的訓練方式，需要更改的地方不同。 ①alt_opt訓練方式 a，修改 py-faster-rcnn/models/pascal_voc/ZF/faster_rcnn_alt_opt資料夾下的四個階段的訓練檔案。 stage1_fast_rcnn_train.pt stage1_rpn_train.pt stage2_fast_rcnn_train.pt stage2_rpn_train.pt faster_rcnn_test.pt 主要修改裡面的num_output數值。 b，修改py-faster-rcnn/lib/datasets資料夾下面的pascal_voc.py檔案 主要修改self._classes = ('__background__','自己的標籤1','自己的標籤2','自己的標籤3') ②end2end訓練方式 a，修改py-faster-rcnn/models/pascal_voc/VGG_CNN_M_1024/faster_rcnn_end2end資料夾裡面的 train.prototxt solver.prototxt test.prototxt 三個檔案 b，修改py-faster-rcnn/lib/datasets資料夾下面的pascal_voc.py檔案 主要修改self._classes = ('__background__','自己的標籤1','自己的標籤2','自己的標籤3') 3、修改迭代次數 ①、alt_opt訓練方式 修改py-faster-rcnn\tools資料夾下的train_faster_rcnn_alt_opt.py檔案。 max_iters = [80000, 40000, 80000, 40000]分別代表四個階段 ②、end2end訓練方式 直接修改experiments/scripts/faster_rcnn_end2end.sh裡面的iters變數的值。 4、開始訓練 ./experiments/scripts/faster_rcnn_alt_opt.sh 0 ZF pascal_voc   ./experiments/scripts/faster_rcnn_end2end.sh 0 VGG_CNN_M_1024 pascal_voc   類似於這樣的命令，在faster-rcnn的根目錄下執行指令碼檔案，後面的0代表的是GPU的編號，ZF是選用的網路，也可以是VGG_CNN_M_1024也可以是VGG16。pascal_voc是指資料集的格式。兩種訓練方式都一樣。 注意：在開始訓練之前一定要記得刪除output和兩個cache。 5、測試自己的測試圖片 a、將訓練好的模型拷貝到相應的位置。將訓練得到的caffemodel（在output資料夾下面的不同訓練方式的資料夾西面）拷貝至py-faster-rcnn\data\faster_rcnn_models。 b、將要測試的圖片拷貝到data下面的demo資料夾下面。 c、執行./toos/demo.py --net vgg_cnn 遇到的問題

“fatal error: hdf5.h: 沒有那個檔案或目錄”解決方法

Step 1

在Makefile.config檔案的第85行，新增/usr/include/hdf5/serial/ 到 INCLUDE_DIRS，也就是把下面第一行程式碼改為第二行程式碼。

INCLUDE_DIRS := $(PYTHON_INCLUDE) /usr/local/include

• INCLUDE_DIRS:= $(PYTHON_INCLUDE) /usr/local/include /usr/include/hdf5/serial/

Step 2

在Makefile檔案的第173行，把 hdf5_hl 和hdf5修改為hdf5_serial_hl 和 hdf5_serial，也就是把下面第一行程式碼改為第二行程式碼。

LIBRARIES += glog gflags protobuf boost_system boost_filesystem m hdf5_hl hdf5

LIBRARIES += glog gflags protobuf boost_system boost_filesystem m hdf5_serial_hl hdf5_serial