ubuntu14.04安装CPU版caffe以及py-faster-rcnn
2017-03-03 16:04
471 查看
本文转自博主,地址如下,仅为学习收藏用,在此谢过博主
http://blog.csdn.net/zyb19931130/article/details/53842791
第一部分:ubuntu16.04+caffe安装。。。。。我的是ubuntu14.04, 64位,问题不大
General dependencies:
[python]
view plain
copy
sudo apt-get install libprotobuf-dev libleveldb-dev libsnappy-dev libopencv-dev libhdf5-serial-dev protobuf-compiler
sudo apt-get install --no-install-recommends libboost-all-dev
BLAS: install ATLAS by
[python]
view plain
copy
sudo apt-get install libatlas-base-dev
or install OpenBLAS or MKL for better CPU performance.
要使用Python调用caffe, 还需要python-dev包依赖:
[python]
view plain
copy
sudo apt-get install python-dev
如果是ubuntu14.04 ,还需要安装如下依赖:
[python]
view plain
copy
sudo apt-get install libgflags-dev libgoogle-glog-dev liblmdb-dev
安装图像包依赖OpenCV开源库:
(1)从github上下载安装脚本:https://github.com/jayrambhia/Install-OpenCV
(2)进行Ubuntu/2.4目录,对所有脚本增加可执行权限
[python]
view plain
copy
sudo chmod +x *.sh
(3)安装依赖项
[python]
view plain
copy
sudo ./dependencies.sh
(4)安装opencv 2.4.9
[python]
view plain
copy
sudo sh ./opencv2_4_10.sh
从caffe项目主页把caffe项目clone下来:
[python]
view plain
copy
git clone --recursive https://github.com/BVLC/caffe.git
然后:
[python]
view plain
copy
cd caffe
cp Makefile.config.example Makefile.config
由于是仅CPU安装,修改Makefile相关配置:
[plain]
view plain
copy
去掉注释CPU_ONLY :=1
注释掉CUDA有关的行:
#CUDA_DIR := /usr/local/cuda
#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
去掉注释WITH_PYTHON_LAYER := 1
INCLUDE_DIRS := $(PYTHON_INCLUDE) /usr/local/include /usr/include/hdf5/serial
LIBRARY_DIRS := $(PYTHON_LIB) /usr/local/lib /usr/lib /usr/lib/i386-linux-gnu/hdf5/serial /usr/lib/x86_64-linux-gnu /usr/lib/x86_64-linux-gnu/hdf5/serial
#TEST_GPUID := 0
文件修改完成后,开始编译:
[python]
view plain
copy
make all
make test
make runtest
make pycaffe
若编译没有错误,则编译成功。完成后:
[python]
view plain
copy
$cd caffe/python
$python
>>>import caffe
若没有错误则表示安装成功,否则make clean,重新编译。
第二部分:py-faster-rcnn的CPU安装
下载项目,里面包含的caffe--rcnn与第一部分的caffe并不相同。
[python]
view plain
copy
git clone --recursive https://github.com/rbgirshick/py-faster-rcnn.git
安装cython和easydict:
[python]
view plain
copy
sudo pip install cython
sudo pip install easydict
编译cython:到/py-faster-rcnn/lib/目录下修改setup.py文件,然后
[python]
view plain
copy
#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caffe:到/py-faster-rcnn/caffe-fast-rcnn/目录下,修改Makefile.config文件(和第一部分中的修改一样)和CMakeLists.txt文件(OFF改成ON),修改如下
[python]
view plain
copy
caffe_option(CPU_ONLY "Build Caffe without CUDA support" ON) # TODO: rename to USE_CUDA
[plain]
view plain
copy
cd ~/py-faster-rcnn/caffe-fast-rcnn
make -j8&& make pycaffe
测试demo:
首先下载训练好的数据集:
[plain]
view plain
copy
cd ~/py-faster-rcnn
./data/scripts/fetch_faster_rcnn_models.sh
然后修改一些文件:
A:修改/py-faster-rcnn/lib/fast_rcnn/config.py文件(True改成False)
# Use GPU implementation of non-maximum suppression
__C.USE_GPU_NMS = False
B:将/py-faster-rcnn/tools/test_net.py和 /py-faster-rcnn/tools/train_net.py的caffe.set_mode_gpu()修改为caffe.set_mode_cpu().
C:修改/py-faster-rcnn/lib/fast_rcnn/nms_wrapper.py文件(注释该引用,并将False改成True)
#from nms.gpu_nms import gpu_nms
def nms(dets, thresh, force_cpu=True):
最后,运行demo:
[plain]
view plain
copy
cd ~/py-faster-rcnn
./tools/demo.py --cpu
此时可能出现报错,nms_cpu.........not found,好吧,打开nms文件夹,看看里面的那个.py文件名字是不是和刚刚nms_wrapper.py中的import 的名字一致,不一致的对应在nms_wrapper.py修改时一并修改了OK
参考:
(1)http://caffe.berkeleyvision.org/install_apt.html
(2)https://github.com/BVLC/caffe
(3)https://github.com/rbgirshick/py-faster-rcnn
http://blog.csdn.net/zyb19931130/article/details/53842791
第一部分:ubuntu16.04+caffe安装。。。。。我的是ubuntu14.04, 64位,问题不大
General dependencies:
[python]
view plain
copy
sudo apt-get install libprotobuf-dev libleveldb-dev libsnappy-dev libopencv-dev libhdf5-serial-dev protobuf-compiler
sudo apt-get install --no-install-recommends libboost-all-dev
BLAS: install ATLAS by
[python]
view plain
copy
sudo apt-get install libatlas-base-dev
or install OpenBLAS or MKL for better CPU performance.
要使用Python调用caffe, 还需要python-dev包依赖:
[python]
view plain
copy
sudo apt-get install python-dev
如果是ubuntu14.04 ,还需要安装如下依赖:
[python]
view plain
copy
sudo apt-get install libgflags-dev libgoogle-glog-dev liblmdb-dev
安装图像包依赖OpenCV开源库:
(1)从github上下载安装脚本:https://github.com/jayrambhia/Install-OpenCV
(2)进行Ubuntu/2.4目录,对所有脚本增加可执行权限
[python]
view plain
copy
sudo chmod +x *.sh
(3)安装依赖项
[python]
view plain
copy
sudo ./dependencies.sh
(4)安装opencv 2.4.9
[python]
view plain
copy
sudo sh ./opencv2_4_10.sh
从caffe项目主页把caffe项目clone下来:
[python]
view plain
copy
git clone --recursive https://github.com/BVLC/caffe.git
然后:
[python]
view plain
copy
cd caffe
cp Makefile.config.example Makefile.config
由于是仅CPU安装,修改Makefile相关配置:
[plain]
view plain
copy
去掉注释CPU_ONLY :=1
注释掉CUDA有关的行:
#CUDA_DIR := /usr/local/cuda
#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
去掉注释WITH_PYTHON_LAYER := 1
INCLUDE_DIRS := $(PYTHON_INCLUDE) /usr/local/include /usr/include/hdf5/serial
LIBRARY_DIRS := $(PYTHON_LIB) /usr/local/lib /usr/lib /usr/lib/i386-linux-gnu/hdf5/serial /usr/lib/x86_64-linux-gnu /usr/lib/x86_64-linux-gnu/hdf5/serial
#TEST_GPUID := 0
文件修改完成后,开始编译:
[python]
view plain
copy
make all
make test
make runtest
make pycaffe
若编译没有错误,则编译成功。完成后:
[python]
view plain
copy
$cd caffe/python
$python
>>>import caffe
若没有错误则表示安装成功,否则make clean,重新编译。
第二部分:py-faster-rcnn的CPU安装
下载项目,里面包含的caffe--rcnn与第一部分的caffe并不相同。
[python]
view plain
copy
git clone --recursive https://github.com/rbgirshick/py-faster-rcnn.git
安装cython和easydict:
[python]
view plain
copy
sudo pip install cython
sudo pip install easydict
编译cython:到/py-faster-rcnn/lib/目录下修改setup.py文件,然后
make,修改如下:
[python]
view plain
copy
#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caffe:到/py-faster-rcnn/caffe-fast-rcnn/目录下,修改Makefile.config文件(和第一部分中的修改一样)和CMakeLists.txt文件(OFF改成ON),修改如下
[python]
view plain
copy
caffe_option(CPU_ONLY "Build Caffe without CUDA support" ON) # TODO: rename to USE_CUDA
[plain]
view plain
copy
cd ~/py-faster-rcnn/caffe-fast-rcnn
make -j8&& make pycaffe
测试demo:
首先下载训练好的数据集:
[plain]
view plain
copy
cd ~/py-faster-rcnn
./data/scripts/fetch_faster_rcnn_models.sh
然后修改一些文件:
A:修改/py-faster-rcnn/lib/fast_rcnn/config.py文件(True改成False)
# Use GPU implementation of non-maximum suppression
__C.USE_GPU_NMS = False
B:将/py-faster-rcnn/tools/test_net.py和 /py-faster-rcnn/tools/train_net.py的caffe.set_mode_gpu()修改为caffe.set_mode_cpu().
C:修改/py-faster-rcnn/lib/fast_rcnn/nms_wrapper.py文件(注释该引用,并将False改成True)
#from nms.gpu_nms import gpu_nms
def nms(dets, thresh, force_cpu=True):
最后,运行demo:
[plain]
view plain
copy
cd ~/py-faster-rcnn
./tools/demo.py --cpu
此时可能出现报错,nms_cpu.........not found,好吧,打开nms文件夹,看看里面的那个.py文件名字是不是和刚刚nms_wrapper.py中的import 的名字一致,不一致的对应在nms_wrapper.py修改时一并修改了OK
参考:
(1)http://caffe.berkeleyvision.org/install_apt.html
(2)https://github.com/BVLC/caffe
(3)https://github.com/rbgirshick/py-faster-rcnn
相关文章推荐
- ubuntu14.04在cpu上配置caffe以及py-faster-rcnn环境(可在odroid上实现)
- Ubuntu16.04+caffe的安装和Py-faster-rcnn在CPU电脑的安装-2
- ubuntu安装faster r-cnn(caffe,python,only cpu)
- ubuntu下基于docker安装caffe以及faster rcnn
- ubuntu16.04+caffe安装和 py-faster-rcnn的CPU安装
- ubuntu14.04、CPU的py-faster-rcnn安装步骤
- ubuntu14.04+CPU环境下搭建caffe,python接口以及运行fast-rcnn实例
- 在Ubuntu 14.04上使用anaconda pyenv来安装caffe cpu only
- 【Caffe】Caffe,CUDA,cuDNN安装指南,以及各种问题的解决方法(Ubuntu14.04)
- 【Caffe安装】Ubuntu14.04上Caffe配置安装(Only CPU)
- 【Caffe】【场景分类】Places365安装、docker运行,以及调用本地caffe运行(Ubuntu14.04)
- py-faster-rcnn + opencv3.0.0 + ubuntu16.04配置(CPU模式)
- ubuntu14.04 安装caffe步骤 CPU版本
- Ubuntu14.04 安装Caffe(仅CPU)
- Ubuntu 14.04 安装Caffe(CPU) 且支持 PYTHON接口
- Ubuntu14.04 安装Caffe(仅CPU)
- Ubuntu 14.04+cuda 7.0+cudnn 7.0+caffe安装配置+faster-rcnn安装
- 32bit/64bit-Ubuntu14.04+anaconda+CPU版本的Caffe安装教程
- py-faster-rcnn + cpu安装及训练自己的数据集
- Ubuntu下深度环境的搭建opencv2.4.9+caffe+py-faster-rcnn+tensorflow的搭建