cudnn 5.1版本下跑通 py-faster-rcnn的demo
孟意致
软件环境：
Ubuntu 16.04 + CUDA8.0 + cuDnn5.1 + python 2.7 + OpenCv 3.1
本文的主要目的，是解决在编译py-faster-rcnn的过程中,与cuDnn的v5版本的冲突问题。编译报错是函数错用。最初是把cuDnn换成了v4。后期在跑demo.py时，没能正确检测出物体，也就是没有出带框的图像。一开始以为是plt的问题，后来发现不是，此demo.py在cpu下运行正常，加上gpu选项就不能正常检测物体。
第一阶段，是按照py-faster-rcnn作者的前半部分步骤来进行。相关链接
1.作者提到，在编译Caffe时，至少需要在Makefile.config设置的两点，这里和Caffe的安装相关了，有很多这样的教程。
# In your Makefile.config, make sure to have this line uncommented
WITH_PYTHON_LAYER := 1
# Unrelatedly, it's also recommended that you use CUDNN
USE_CUDNN := 12.你需要安装的软件（用apt-get即可）：
cython, python-opencv, easydict
3.命令行下
# Make sure to clone with --recursive
git clone --recursive https://github.com/rbgirshick/py-faster-rcnn.gitcd $FRCN_ROOT/lib
make==========================================================================分界线==========================================
5.作者用的caffe的版本较旧，为了能和cuDnn v5兼容，需要参考：这里
cd caffe-fast-rcnn
git remote add caffe https://github.com/BVLC/caffe.git
git fetch caffe
git merge -X theirs caffe/master 整合以后，需要修改:
Remove self_.attr("phase") = static_cast<int>(this->phase_); from include/caffe/layers/python_layer.hpp after merging.========================================分界线============================================================================
6.回到原作者的教程。为编译做准备。原作者的Makefile.config文件我不建议用，他里面有一些老旧的设定，比如gcc版本，Matlab的一些设定。我贴上我的来，并把一些坑具体的说说，其实这个配置文件每一项猜起来比较容易。
cd $FRCN_ROOT/caffe-fast-rcnn## 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).使用cuDnn加速
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#我的opencv版本是3.1
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 := atlas
# 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.#下面这个目录和左边的这个头文件关联
PYTHON_INCLUDE := /usr/include/python2.7 \
/usr/local/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)#这里需要设为1
WITH_PYTHON_LAYER := 1
# Whatever else you find you need goes here.#这里是为了能找到hdf5.h的文件，具体位置根据个人情况修改
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/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.)#这里根据一些博文上说应该设为1
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 ?= @编辑好Makefile.config文件以后可以执行：
make -j8 && make pycaffe
find /usr -name xxx.h7. 下面就是下载模型(脚本需要运行两次）和跑demo.py了
cd $FRCN_ROOT
./data/scripts/fetch_faster_rcnn_models.sh
./data/scripts/fetch_faster_rcnn_models.sh
./tools/demo.py
8. https://stackoverflow.com/questions/15745045/how-do-i-resolve-git-saying-commit-your-changes-or-stash-them-before-you-can-me
类似资料：