Faster R-CNN安装笔记，只用CPU
转自：http://blog.sina.com.cn/s/blog_679f93560102wpyf.html
- 下载代码和数据
git clone --recursive https://github.com/rbgirshick/py-faster-rcnn.git
- 下载demo模型数据
[root@localhost py-faster-rcnn]# ./data/scripts/fetch_faster_rcnn_models.sh
Downloading Faster R-CNN demo models (695M)...
。。。
Unzipping...
faster_rcnn_models/
faster_rcnn_models/ZF_faster_rcnn_final.caffemodel
faster_rcnn_models/VGG16_faster_rcnn_final.caffemodel
- 编译cython
进入lib目录，修改setup.py，注释掉GPU相关代码，如下
。。。
#CUDA = locate_cuda()
。。。
# self.set_executable('compiler_so', CUDA['nvcc'])
。。。
# Extension('nms.gpu_nms',
# ['nms/nms_kernel.cu', 'nms/gpu_nms.pyx'],
# library_dirs=[CUDA['lib64']],
# libraries=['cudart'],
# language='c++',
# runtime_library_dirs=[CUDA['lib64']],
# # this syntax is specific to this build system
# # we're only going to use certain compiler args with nvcc and not with
# # gcc the implementation of this trick is in customize_compiler() below
# extra_compile_args={'gcc': ["-Wno-unused-function"],
# 'nvcc': ['-arch=sm_35',
# '--ptxas-options=-v',
# '-c',
# '--compiler-options',
# "'-fPIC'"]},
# include_dirs = [numpy_include, CUDA['include']]
# ),
。。。
编译：
[root@localhost lib]# make
- 安装caffe（自带的，不是通用的）
进入caffe-fast-rcnn目录，大部分跟前面caffe安装记录一文一样，修改Makefile.config为
## 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_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 := /usr/include/atlas-x86_64-base
BLAS_LIB := /usr/lib64/atlas
# 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/lib64/python2.7/site-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/lib64
# 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/include
LIBRARY_DIRS := $(PYTHON_LIB) /usr/lib64
# 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 ?= @
修改Makefile
LIBRARIES += satlas tatlas #新版atlas已经不用这两个lib了：cblas atlas
编译caffe和pycaffe
[root@localhost caffe-fast-rcnn]# make -j8 && make pycaffe
- 跑demo
[root@localhost py-faster-rcnn]# ./tools/demo.py
Traceback (most recent call last):
File "./tools/demo.py", line 17, in
from fast_rcnn.config import cfg
File "/root/zhanxiang/work/py-faster-rcnn/tools/../lib/fast_rcnn/config.py", line 23, in
from easydict import EasyDict as edict
ImportError: No module named easydict
缺少Python库easydict，所以安装 pip install easydict
[root@localhost py-faster-rcnn]# ./tools/demo.py
Traceback (most recent call last):
File "./tools/demo.py", line 18, in
from fast_rcnn.test import im_detect
File "/root/zhanxiang/work/py-faster-rcnn/tools/../lib/fast_rcnn/test.py", line 15, in
import cv2
ImportError: No module named cv2
缺少Python库cv2，这个是openCV里面的。那就来装openCV python库
yum install opencv-python.x86_64
[root@localhost py-faster-rcnn]# python tools/demo.py --cpu
Traceback (most recent call last):
File "tools/demo.py", line 21, in
import matplotlib.pyplot as plt
File "/usr/lib64/python2.7/site-packages/matplotlib/pyplot.py", line 26, in
from matplotlib.figure import Figure, figaspect
File "/usr/lib64/python2.7/site-packages/matplotlib/figure.py", line 36, in
from matplotlib.axes import Axes, SubplotBase, subplot_class_factory
File "/usr/lib64/python2.7/site-packages/matplotlib/axes/__init__.py", line 4, in
from ._subplots import *
File "/usr/lib64/python2.7/site-packages/matplotlib/axes/_subplots.py", line 10, in
from matplotlib.axes._axes import Axes
File "/usr/lib64/python2.7/site-packages/matplotlib/axes/_axes.py", line 14, in
from matplotlib import unpack_labeled_data
ImportError: cannot import name unpack_labeled_data
看起来跟matplotlib库有关，pip install的版本太旧，直接下载源码安装。
[root@localhost work]# git clone git://github.com/matplotlib/matplotlib.git
[root@localhost work]# cd matplotlib/
安装依赖包
[root@localhost matplotlib]# yum-builddep python-matplotlib
安装
[root@localhost matplotlib]# python setup.py install
[root@localhost py-faster-rcnn]# python tools/demo.py --cpu
Traceback (most recent call last):
File "tools/demo.py", line 19, in
from fast_rcnn.nms_wrapper import nms
File "/root/zhanxiang/work/py-faster-rcnn/tools/../lib/fast_rcnn/nms_wrapper.py", line 9, in
from nms.gpu_nms import gpu_nms
ImportError: No module named gpu_nms
修改nms_wrapper.py，改force_cpu =True
[root@localhost py-faster-rcnn]# vi lib/fast_rcnn/nms_wrapper.py
def nms (dets, thresh, force_cpu =True):
- 大功告成
[root@localhost py-faster-rcnn]# python tools/demo.py --cpu
就能看到结果了
更多资源：http://www.cnblogs.com/justinzhang/p/5386837.html
