在mac上安装fast-r-cnn时遇到了一些坑。所以整理下,以便对有需要的人有所帮助。
1. 下载代码
$ cd /Users/aaron/githubRepos/
$ git clone --recursive https://github.com/rbgirshick/py-faster-rcnn.git
2. 下载模型
$ cd /Users/aaron/githubRepos/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
国内下载的有点慢。
3. 编译cython
进入lib目录,修改setup.py,注释掉GPU相关代码,如下:
#def locate_cuda():
# """Locate the CUDA environment on the system
#
# Returns a dict with keys 'home', 'nvcc', 'include', and 'lib64'
# and values giving the absolute path to each directory.
#
# Starts by looking for the CUDAHOME env variable. If not found, everything
# is based on finding 'nvcc' in the PATH.
# """
#
# # first check if the CUDAHOME env variable is in use
# if 'CUDAHOME' in os.environ:
# home = os.environ['CUDAHOME']
# nvcc = pjoin(home, 'bin', 'nvcc')
# else:
# # otherwise, search the PATH for NVCC
# default_path = pjoin(os.sep, 'usr', 'local', 'cuda', 'bin')
# nvcc = find_in_path('nvcc', os.environ['PATH'] + os.pathsep + default_path)
# if nvcc is None:
# raise EnvironmentError('The nvcc binary could not be '
# 'located in your $PATH. Either add it to your path, or set $CUDAHOME')
# home = os.path.dirname(os.path.dirname(nvcc))
#
# cudaconfig = {'home':home, 'nvcc':nvcc,
# 'include': pjoin(home, 'include'),
# 'lib64': pjoin(home, 'lib64')}
# for k, v in cudaconfig.iteritems():
# if not os.path.exists(v):
# raise EnvironmentError('The CUDA %s path could not be located in %s' % (k, v))
#
# return cudaconfig
#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']]
# ),
然后执行:
$ make
4. 安装自带的caffe(不是通用的)
进入caffe-fast-rcnn目录,大部分跟前面caffe安装记录一样,参考之前的Makefile.config文件进行修改(可以直接拷贝过来)。
然后进行编译过程,也和安装通用的caffe是一样的。记得执行make pycaffe语句:
5. 运行示例程序
为了让程序能正常运行,我们需要修改:tools/demo.py和lib/fast_rcnn/test.py文件。
将程序中原本的import caffe改为:
sys.path.insert(0, '/Users/aaron/githubRepos/py-faster-rcnn/caffe-fast-rcnn/python')
import caffe
然后执行命令:
./tools/demo.py --cpu
结果:

6. 常见错误
1) No module named easydict
Traceback (most recent call last):
File "./tools/demo.py", line 17, in
from fast_rcnn.config import cfg
File "/Users/aaron/githubRepos/py-faster-rcnn/tools/../lib/fast_rcnn/config.py", line 23, in
from easydict import EasyDict as edict
ImportError: No module named easydict
这是缺少Python库easydict,所以使用命令pip install easydict进行安装即可。
2) No module named cv2
Traceback (most recent call last):
File "./tools/demo.py", line 18, in
from fast_rcnn.test import im_detect
File "/Users/aaron/githubRepos/py-faster-rcnn/tools/../lib/fast_rcnn/test.py", line 15, in
import cv2
ImportError: No module named cv2
这是因为没有安装opencv2,使用如下命令安装即可:
brew tap homebrew/science
brew info opencv
brew install opencv
cd /usr/local/Cellar/opencv/2.4.13_3/
cd /Library/Python/2.7/site-packages/
ln -s /usr/local/Cellar/opencv/2.4.13_3/lib/python2.7/site-packages/cv.py cv.py
ln -s /usr/local/Cellar/opencv/2.4.13_3/lib/python2.7/site-packages/cv2.so cv2.so
3) No module named gpu_nms
Traceback (most recent call last):
File "tools/demo.py", line 19, in
from fast_rcnn.nms_wrapper import nms
File "/Users/aaron/githubRepos/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
vim lib/fast_rcnn/nms_wrapper.py
修改如下:
def nms (dets, thresh, force_cpu =True):
评论