Caffe经典模型--faster-rcnn目标检测实战案例(一)
这篇文章主要记录py-faster-rcnn的编译及测试,是实战案例的前期准备。想动手训练自己的数据集可以参考下一篇文章Caffe经典模型--faster-rcnn目标检测实战案例(二)(训练kitti数据集)
在编译py-faster-rcnn之前,首先要确保机器上已经安装后caffe,如果还没有安装好caffe,可以参考Centos下的Caffe编译安装简易手册
下面正式开始py-faster-rcnn的编译和安装
第一步:下载源码
在命令行执行下载源代码:git clone --recursive https://github.com/rbgirshick/py-faster-rcnn.git
注意:确保要有--recursive ,这个会确保将faster-rcnn下的caffe-fast-rcnn一同下载
如果没有下载到caffe-faster-rcnn,则需要手动去下载,执行命令:git submodule update --init --recursive
如果,没有git命令,则使用命令:yum -y install git 安装git
第二步:编译lib目录
1、编译lib目录(带GPU时)
先确定当前GPU的计算能力,修改py-faster-rcnn/lib/setup.py文件(按照如下方式修改):
执行编译命令:
$>cd py-faster-rcnn/lib
$>make
2、编译lib目录(无GPU时)
(a)首先按照如下方式修改py-faster-rcnn/lib/setup.py文件(取消使用GPU的配置)
将文件中58行的CUDA=locate_cuda()注释掉
将125行开始的含有nms.gpu_nms的Extension部分也注释掉(也就是将如下内容全部注释)
(b)在/py-faster-rcnn/lib/fast_rcnn/config.py文件中取消GPU的配置
在该文件的第205行的__C.USE_GPU_NMS = True中的True改为False,如下所示:
(c)在py-faster-rcnn/lib/fast_rcnn/nms_wrapper.py文件中取消GPU的配置
将该文件的第9行的from nms.gpu_nms import gpu_nms注释掉,如下所示:
注意:如果没有GPU,直接编译将会报错,显示没有CUDA的相关信息
第三步:编译FasterRCNN
1、配置caffe-fast-rcnn的Makefile.config
将caffe-fast-rcnn目录下的Makefile.config.example 复制一份到Makefile.config,然后编辑Makefile.config
修改的地方有如下几处:
a)取消 WITH_PYTHON_LAYER := 1 这一行的注释.
b)如果有GPU的话,将 USE_CUDNN := 1 这一行的注释也取消
如下是我的Makefile.config文件的内容:
[code]## 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 through *_61 lines for compatibility. # For CUDA < 8.0, comment the *_60 and *_61 lines for compatibility. # For CUDA >= 9.0, comment the *_20 and *_21 lines for compatibility. CUDA_ARCH := -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 BLAS_INCLUDE := /usr/include/openblas # 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 python3.6m #PYTHON_INCLUDE := /usr/include/python3.6m \ # /usr/local/lib64/python3.6/site-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 LIBRARY_DIRS := $(PYTHON_LIB) /usr/local/lib /usr/lib # 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 ?= @
2、编译fast-rcnn
在caffe-fast-rcnn目录下执行如下命令:
$>make all -j8 && make pycaffe
第四步:下载预训练的模型探测器
1、下载模型压缩包
在py-faster-rcnn/data目录下执行如下命令去下载模型的压缩包
$>./scripts/fetch_faster_rcnn_models.sh
下载完后会在py-faster-rcnn/data目录下得到faster_rcnn_models.tgz这个压缩文件
2、解压模型压缩包的到模型文件
执行如下命令解压faster_rcnn_models.tgz文件:
$>tar -zxvf faster_rcnn_models.tgz
解压后得到VGG16_faster_rcnn_final.caffemodel和ZF_faster_rcnn_final.caffemodel两个模型文件
这两个模型是使用VOC2007数据集训练后得到的
第五步:运行图片探测---执行Demo
在执行demo之前首先将探测的图片放到py-faster-rcnn/data/demo目录下
在py-faster-rcnn目录下执行如下命令:(默认使用GPU,如果是cpu,需要在后面添加 --cpu )
$>./tool/demo.py
- 大话目标检测经典模型(RCNN、Fast RCNN、Faster RCNN)
- caffe框架下目标检测——faster-rcnn实战篇问题集锦
- 大话目标检测经典模型(RCNN、Fast RCNN、Faster RCNN)
- caffe框架下目标检测——faster-rcnn实战篇问题集锦
- DL开源框架Caffe | 目标检测Faster-rcnn问题全解析
- 深度学习Caffe实战笔记(21)Windows平台 Faster-RCNN 训练好的模型测试数据
- Caffe学习系列——6使用Faster-RCNN进行目标检测
- Caffe使用step by step:faster-rcnn目标检测matlab代码
- caffe框架下目标检测——faster-rcnn实战篇操作
- DL开源框架Caffe | 目标检测Faster-rcnn训练自己数据问题整理
- 利用py-faster-rcnn训练目标检测模型
- [目标检测]windows下实现c++版faster-rcnn
- 目标检测之RCNN,fast RCNN,faster RCNN
- 使用Faster-Rcnn进行目标检测(实践篇)
- 逐字理解目标检测simple-faster-rcnn-pytorch-master代码(一)
- 逐字理解目标检测simple-faster-rcnn-pytorch-master代码(二)
- 使用Faster-Rcnn进行目标检测的原理
- caffe框架下目标检测——faster-rcnn实战篇操作
- 深度学习目标检测模型全面综述:Faster R-CNN、R-FCN和SSD
- 目标检测——从RCNN到Faster RCNN 串烧