运行faster-rcnn、配置opencv中遇到的问题

1、

编译caffe和pycaffe

*** [.build_release/src/caffe/layer_factory.o] 错误 1

cudnn版本有问题。在makefile里关了cudnn

2、

ImportError: No module named packages

$wget https://bootstrap.pypa.io/get-pip.py$sudo python get-pip.py

3、

The directory '/home/ubuntu/.cache/pip/http' or its parent directory is not owned by the current user and the cache has been disabled. Please check the permissions and owner of that directory. If executing pip with sudo, you may want sudo's -H flag.

The directory '/home/ubuntu/.cache/pip' or its parent directory is not owned by the current user and caching wheels has been disabled. check the permissions and owner of that directory. If executing pip with sudo, you may want sudo's -H flag.

去掉sudo

4、

Command "python setup.py egg_info" failed with error code 1 in /tmp/pip-buil

sudo python -m pip install --upgrade --force pip sudo pip install setuptools== 33.1 . 1

5、

ImportError: No module named cv2

安装opencv

6、

error: ‘NppiGraphcutState’ has not been declared

typedef NppStatus (*init_func_t)(NppiSize oSize, NppiGraphcutState** ppState, Npp8u* pDeviceMem);

graphcuts.cpp文件中许多变量没有声明，opencv3.0还不支持cuda8.0,

方法一、换2.4.13

方法二、

opencv-3.0.0/ modules/cudalegacy/src/graphcuts.cpp 中

45行

# if !defined (HAVE_CUDA) || defined (CUDA_DISABLER)

改为

# if !defined (HAVE_CUDA) || defined (CUDA_DISABLER) || (CUDART_VERSION >= 8000)

7、

ImportError: No module named cv2

方法一、

$ sudo cp /home/data1/package/opencv-3.0.0/build/lib/cv2.so /usr/local/lib/python2.7/site-packages/

>>> import sys

>>> sys.path.append('/usr/local/lib/python2.7/site-packages/')

>>> import cv2

方法二、

>>> import sys

>>> sys . path

查看当前os.sys.path

把cv2.so拷到pythonpath

8、

Error using Caffe: "This tool requires OpenCV; compile with USE_OPENCV."

makefile里设置错误

之前装opencv的时候取消了USE_OPENCV := 0 的注释

#USE_OPENCV := 0

$cd caffe

$make

$make pycaffe

$make matcaffe