目录
重要提醒：请仔细阅读GitHub上关于Caffe-SSD网络的配置安装教程！！
https://github.com/weiliu89/caffe/tree/ssd#installation
一. 安装前准备工作：
1. 更新Linux系统软件
:~$ sudo apt-get update #更新软件列表 安装必要的依赖库
2. 安装GitHub依赖包，可以使用git指令从GitHub下载
:~$ sudo apt-get install git cmake build-essential
3. 安装Caffe依赖包
:~$ 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
:~$ sudo apt-get install libatlas-base-dev liblapack-dev libopenblas-dev
:~$ sudo apt-get install python-dev python-opencv (可能要源码编译OpenCV，参考链接https://mp.csdn.net/postedit/88639372)
:~$ sudo apt-get install libgflags-dev libgoogle-glog-dev liblmdb-dev
二. Installation
1. Get the code. We will call the directory that you cloned Caffe into $CAFFE_ROOT(即/home/usrname)
:~$ git clone https://github.com/weiliu89/caffe.git
:~$ cd caffe
:~/caffe$ git checkout ssd
2. Modify Makefile.config according to your Caffe installation.
:~/caffe$ cp Makefile.config.example Makefile.config
3. 打开并修改Makefile.config (a lot of kengs)
:~/caffe$ vim Makefile.config
# -------------------------------------------------------------- #
- 去掉 CPU_ONLY :=1的注释
- OPENCV_VERSION := 3
- 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
- # TEST_GPUID := 0
- 去掉WITH_PYTHON_LAYER := 1的注释
- INCLUDE_DIRS := $(PYTHON_INCLUDE) /usr/local/include /usr/include/hdf5/serial
- LIBRARY_DIRS:= $(PYTHON_LIB) /usr/local/lib /usr/lib /usr/lib/aarch64-linux-gnu /usr/lib/aarch64-linux-gnu/hdf5/serial
# -------------------------------------------------------------- #
4. 打开并修改Makefile
:~/caffe$ vim Makefile
# -------------------------------------------------------------- #
ifeq ($(USE_OPENCV), 1)
LIBRARIES += opencv_core opencv_highgui opencv_imgproc opencv_videoio
# -------------------------------------------------------------- #
5. 编译安装Caffe
:~/caffe$ make all -j8
:~/caffe$ make test -j8
:~/caffe$ make runtest -j8 # (Optional)
:~/caffe$ make pycaffe
6. 编译python-caffe接口 (不需要这一步就可以在MNIST数据集上测试Caffe)
参考链接：https://blog.csdn.net/u010193446/article/details/53259294，其第五步.
https://www.cnblogs.com/venus024/p/5664103.html
提醒：因为我当时用pip下载其他Python依赖库时出现了问题，比如镜像源无法使用或者没有权限。因此我使用以下命令逐个
安装CAFFE_ROOT/caffe/python路径下的requirements.txt中的库.
pip install -i https://pypi.tuna.tsinghua.edu.cn/simple pkg-**
7. 将Caffe的Python库路径添加到PYTHONPATH环境变量中
vim ~/.bashrc
export CAFFE_ROOT=/data0/zzw/caffe
export PYTHONPATH=$CAFFE_ROOT/python:$PYTHONPATH
source ~/.bashrc
8. 测试Caffe是否安装成功
:~/caffe$ python
>>> import caffe # it works that means your Caffe is successfully installed
>>>
2019.03.19 各种bug导致未编译成功，应该是Ubuntu18.04的版本和以上编译方法不匹配问题！！！
2019.03.20 历时三天，终于编译安装成功.
Caffe中的Makefile.config的解释，参考链接：https://blog.csdn.net/JiaJunLee/article/details/52068230
Makefile.config修改后的源码如下：
## 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 := 0
# 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 through *_61 lines for compatibility.
# For CUDA < 8.0, comment the *_60 and *_61 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_52,code=sm_52 \
# -gencode arch=compute_60,code=sm_60 \
# -gencode arch=compute_61,code=sm_61 \
# -gencode arch=compute_61,code=compute_61
# BLAS choice:
# atlas for ATLAS (default)
# mkl for MKL
# open for OpenBlas
BLAS := open
# 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.
PYTHON_INCLUDE := /usr/include/python2.7 \
/usr/lib/python2.7/site-packages/numpy/core/include/
#/System/Library/Frameworks/Python.framework/Versions/2.7/Extras/lib/python/numpy
# 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)
WITH_PYTHON_LAYER := 1
# Whatever else you find you need goes here.
INCLUDE_DIRS := $(PYTHON_INCLUDE) /usr/local/include /usr/include/hdf5/serial
LIBRARY_DIRS := $(PYTHON_LIB) /usr/local/lib /usr/lib /usr/lib/aarch64-linux-gnu /usr/lib /usr/lib/aarch64-linux-gnu/hdf5/serial (注意：aarch64-linux-gpu可替换为x86_64-linux-gnu)
# 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
# NCCL acceleration switch (uncomment to build with NCCL)
# https://github.com/NVIDIA/nccl (last tested version: v1.2.3-1+cuda8.0)
# USE_NCCL := 1
# 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
# N.B. both build and distribute dirs are cleared on `make clean`
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 ?= @
参考链接：
https://zhuanlan.zhihu.com/p/48603525
https://blog.csdn.net/Y_AOZHEN/article/details/84137377
https://blog.csdn.net/u010193446/article/details/53259294
https://www.itread01.com/content/1547169842.html
https://blog.csdn.net/weixin_38125866/article/details/81951548
https://blog.csdn.net/DonatelloBZero/article/details/51304162