faster_rcnn c++版本的 caffe 封装(1)
2016-06-18 12:13
711 查看
转载请注明出处,楼燚(yì)航的blog,http://www.cnblogs.com/louyihang-loves-baiyan/
由于需要把FasterRCNN做的工程化,因此这里需要对Caffe进行封装。其实封装听起来感觉很高深的样子,其实就是将自己在caffe上再调用的接口做成一个动态库,同时将Caffe的库连着Caffe的那些库依赖一起做成自己工程的库依赖就可以了。如果你只是直接使用Caffe的话,那么到时候直接链接到caffe下面build目录中的libcaffe.so或者libcaffe.a就可以了。如果有对Caffe有C++代码的改动,操作也是一样的,但是如果用了Python 模块比如使用了Python Layer,那么在使用中,还需要为Caffe指定其Python模块的位置。好了,首先在这里我参照http://blog.csdn.net/xyy19920105/article/details/50440957,感谢他的分享,让我们很受用。首先写成一个C++版本。一开始的版本是这样的,当时只有一个cpp文件。
#include <stdio.h> // for snprintf #include <string> #include <vector> #include <math.h> #include <fstream> #include <boost/python.hpp> #include "caffe/caffe.hpp" #include "gpu_nms.hpp" #include <opencv2/core/core.hpp> #include <opencv2/highgui/highgui.hpp> #include <opencv2/imgproc/imgproc.hpp> using namespace caffe; using namespace std; #define max(a, b) (((a)>(b)) ? (a) :(b)) #define min(a, b) (((a)<(b)) ? (a) :(b)) const int class_num=2; /* * === Class ====================================================================== * Name: Detector * Description: FasterRCNN CXX Detector * ===================================================================================== */ class Detector { public: Detector(const string& model_file, const string& weights_file); void Detection(const string& im_name); void bbox_transform_inv(const int num, const float* box_deltas, const float* pred_cls, float* boxes, float* pred, int img_height, int img_width); void vis_detections(cv::Mat image, int* keep, int num_out, float* sorted_pred_cls, float CONF_THRESH); void boxes_sort(int num, const float* pred, float* sorted_pred); private: shared_ptr<Net<float> > net_; Detector(){} }; /* * === FUNCTION ====================================================================== * Name: Detector * Description: Load the model file and weights file * ===================================================================================== */ //load modelfile and weights Detector::Detector(const string& model_file, const string& weights_file) { net_ = shared_ptr<Net<float> >(new Net<float>(model_file, caffe::TEST)); net_->CopyTrainedLayersFrom(weights_file); } //Using for box sort struct Info { float score; const float* head; }; bool compare(const Info& Info1, const Info& Info2) { return Info1.score > Info2.score; } /* * === FUNCTION ====================================================================== * Name: Detect * Description: Perform detection operation * Warning the max input size should less than 1000*600 * ===================================================================================== */ //perform detection operation //input image max size 1000*600 void Detector::Detection(const string& im_name) { float CONF_THRESH = 0.8; float NMS_THRESH = 0.3; const int max_input_side=1000; const int min_input_side=600; cv::Mat cv_img = cv::imread(im_name); cv::Mat cv_new(cv_img.rows, cv_img.cols, CV_32FC3, cv::Scalar(0,0,0)); if(cv_img.empty()) { std::cout<<"Can not get the image file !"<<endl; return ; } int max_side = max(cv_img.rows, cv_img.cols); int min_side = min(cv_img.rows, cv_img.cols); float max_side_scale = float(max_side) / float(max_input_side); float min_side_scale = float(min_side) /float( min_input_side); float max_scale=max(max_side_scale, min_side_scale); float img_scale = 1; if(max_scale > 1) { img_scale = float(1) / max_scale; } int height = int(cv_img.rows * img_scale); int width = int(cv_img.cols * img_scale); int num_out; cv::Mat cv_resized; std::cout<<"imagename "<<im_name<<endl; float im_info[3]; float data_buf[height*width*3]; float *boxes = NULL; float *pred = NULL; float *pred_per_class = NULL; float *sorted_pred_cls = NULL; int *keep = NULL; const float* bbox_delt; const float* rois; const float* pred_cls; int num; for (int h = 0; h < cv_img.rows; ++h ) { for (int w = 0; w < cv_img.cols; ++w) { cv_new.at<cv::Vec3f>(cv::Point(w, h))[0] = float(cv_img.at<cv::Vec3b>(cv::Point(w, h))[0])-float(102.9801); cv_new.at<cv::Vec3f>(cv::Point(w, h))[1] = float(cv_img.at<cv::Vec3b>(cv::Point(w, h))[1])-float(115.9465); cv_new.at<cv::Vec3f>(cv::Point(w, h))[2] = float(cv_img.at<cv::Vec3b>(cv::Point(w, h))[2])-float(122.7717); } } cv::resize(cv_new, cv_resized, cv::Size(width, height)); im_info[0] = cv_resized.rows; im_info[1] = cv_resized.cols; im_info[2] = img_scale; for (int h = 0; h < height; ++h ) { for (int w = 0; w < width; ++w) { data_buf[(0*height+h)*width+w] = float(cv_resized.at<cv::Vec3f>(cv::Point(w, h))[0]); data_buf[(1*height+h)*width+w] = float(cv_resized.at<cv::Vec3f>(cv::Point(w, h))[1]); data_buf[(2*height+h)*width+w] = float(cv_resized.at<cv::Vec3f>(cv::Point(w, h))[2]); } } net_->blob_by_name("data")->Reshape(1, 3, height, width); net_->blob_by_name("data")->set_cpu_data(data_buf); net_->blob_by_name("im_info")->set_cpu_data(im_info); net_->ForwardFrom(0); bbox_delt = net_->blob_by_name("bbox_pred")->cpu_data(); num = net_->blob_by_name("rois")->num(); rois = net_->blob_by_name("rois")->cpu_data(); pred_cls = net_->blob_by_name("cls_prob")->cpu_data(); boxes = new float[num*4]; pred = new float[num*5*class_num]; pred_per_class = new float[num*5]; sorted_pred_cls = new float[num*5]; keep = new int[num]; for (int n = 0; n < num; n++) { for (int c = 0; c < 4; c++) { boxes[n*4+c] = rois[n*5+c+1] / img_scale; } } bbox_transform_inv(num, bbox_delt, pred_cls, boxes, pred, cv_img.rows, cv_img.cols); for (int i = 1; i < class_num; i ++) { for (int j = 0; j< num; j++) { for (int k=0; k<5; k++) pred_per_class[j*5+k] = pred[(i*num+j)*5+k]; } boxes_sort(num, pred_per_class, sorted_pred_cls); _nms(keep, &num_out, sorted_pred_cls, num, 5, NMS_THRESH, 0); vis_detections(cv_img, keep, num_out, sorted_pred_cls, CONF_THRESH); } cv::imwrite("vis.jpg",cv_img); delete []boxes; delete []pred; delete []pred_per_class; delete []keep; delete []sorted_pred_cls; } /* * === FUNCTION ====================================================================== * Name: vis_detections * Description: Visuallize the detection result * ===================================================================================== */ void Detector::vis_detections(cv::Mat image, int* keep, int num_out, float* sorted_pred_cls, float CONF_THRESH) { int i=0; while(sorted_pred_cls[keep[i]*5+4]>CONF_THRESH && i < num_out) { if(i>=num_out) return; cv::rectangle(image,cv::Point(sorted_pred_cls[keep[i]*5+0], sorted_pred_cls[keep[i]*5+1]),cv::Point(sorted_pred_cls[keep[i]*5+2], sorted_pred_cls[keep[i]*5+3]),cv::Scalar(255,0,0)); i++; } } /* * === FUNCTION ====================================================================== * Name: boxes_sort * Description: Sort the bounding box according score * ===================================================================================== */ void Detector::boxes_sort(const int num, const float* pred, float* sorted_pred) { vector<Info> my; Info tmp; for (int i = 0; i< num; i++) { tmp.score = pred[i*5 + 4]; tmp.head = pred + i*5; my.push_back(tmp); } std::sort(my.begin(), my.end(), compare); for (int i=0; i<num; i++) { for (int j=0; j<5; j++) sorted_pred[i*5+j] = my[i].head[j]; } } /* * === FUNCTION ====================================================================== * Name: bbox_transform_inv * Description: Compute bounding box regression value * ===================================================================================== */ void Detector::bbox_transform_inv(int num, const float* box_deltas, const float* pred_cls, float* boxes, float* pred, int img_height, int img_width) { float width, height, ctr_x, ctr_y, dx, dy, dw, dh, pred_ctr_x, pred_ctr_y, pred_w, pred_h; for(int i=0; i< num; i++) { width = boxes[i*4+2] - boxes[i*4+0] + 1.0; height = boxes[i*4+3] - boxes[i*4+1] + 1.0; ctr_x = boxes[i*4+0] + 0.5 * width; ctr_y = boxes[i*4+1] + 0.5 * height; for (int j=0; j< class_num; j++) { dx = box_deltas[(i*class_num+j)*4+0]; dy = box_deltas[(i*class_num+j)*4+1]; dw = box_deltas[(i*class_num+j)*4+2]; dh = box_deltas[(i*class_num+j)*4+3]; pred_ctr_x = ctr_x + width*dx; pred_ctr_y = ctr_y + height*dy; pred_w = width * exp(dw); pred_h = height * exp(dh); pred[(j*num+i)*5+0] = max(min(pred_ctr_x - 0.5* pred_w, img_width -1), 0); pred[(j*num+i)*5+1] = max(min(pred_ctr_y - 0.5* pred_h, img_height -1), 0); pred[(j*num+i)*5+2] = max(min(pred_ctr_x + 0.5* pred_w, img_width -1), 0); pred[(j*num+i)*5+3] = max(min(pred_ctr_y + 0.5* pred_h, img_height -1), 0); pred[(j*num+i)*5+4] = pred_cls[i*class_num+j]; } } } int main() { string model_file = "/home/lyh1/workspace/py-faster-rcnn/models/pascal_voc/VGG_CNN_M_1024/faster_rcnn_alt_opt/faster_rcnn_test.pt"; string weights_file = "/home/lyh1/workspace/py-faster-rcnn/output/default/yuanzhang_car/vgg_cnn_m_1024_fast_rcnn_stage2_iter_40000.caffemodel"; int GPUID=0; Caffe::SetDevice(GPUID); Caffe::set_mode(Caffe::GPU); Detector det = Detector(model_file, weights_file); det.Detection("/home/lyh1/workspace/py-faster-rcnn/data/demo/car.jpg"); return 0; }
这个文件对应的CMakeLists.txt,其中对编译部分加了相应的注释。此处需要添加
$PYTHONPATH,原因是因为我们在使用中是C++接口调用的Caffe,但是在Caffe运行中调用了Python,因此需要告诉Caffe我们自己的Python模块的路径,比如这里去模型的定义文件中看,里面用了py-faster-rcnn根目录下的lib中的rpn文件夹下的proposal模块,因此需要在
$PYTHONPATH中加入这个模块路径
...\py-faster-rcnn\lib以及Caffe的Python接口路径
...\py-faster-rcnn\caffe-fast-rcnn\python,下面是我在
~.bashrc中添加
$PYTHONPATH,可供参考。添加之后
执行source ~/.bashrc,对bash立即生效,提醒一下
.bashrc是在你启动一个bash的时候会被立即执行的。要么你直接在当前bash中直接source,否则需要再打开一个新的
bash。还有一点,顺带提一下,加入到
$PYTHONPATH之后,如果你系统中有多个
caffe,那么你得想一下怎么防止冲突,当时我就给自己埋了个坑,别的
caffe调用
PYTHON接口时,就直接调到这个加入到
$PYTHONPATH中的这个caffe了,所以各种报错,如果可以话可以考虑用Docker来处理这种东西。
如图添加
还是接下来讲一下这个CMakeList.txt。我也是第一次用,之前用
Autotools,真是各种麻烦,对Linux下的手动编译都有一些阴影。用Cmake真的是比较傻瓜式的,能把东西梳理的比较清晰。
#This part is used for compile faster_rcnn_demo.cpp #这里是版本要求,根据自己项目而定,我用了默认的 cmake_minimum_required (VERSION 2.8) #我们的工程的名字 project (faster_rcnn_demo) #添加我们要生成的可执行文件的名字,以及相应的源码文件 add_executable(faster_rcnn_demo faster_rcnn_demo.cpp) #这里添加这个faster_rcnn_demo.cpp所依赖的头文件路径 #首先是Caffe目录的include #其次是用了gpu_nms.cu,所以也要添加相应的头文件gpu_nms.hpp在py-faster-rcnn根目录下的lib/nms中 #下面就是几个Caffe的依赖项,包括Python #值得注意的是boost/python。hpp的头文件路径也要加入 #还有opencv的路径,cuda路径,线性代数库路径相应的都要添加 include_directories ( "${PROJECT_SOURCE_DIR}/../caffe-fast-rcnn/include" "${PROJECT_SOURCE_DIR}/../lib/nms" /share/apps/local/include /usr/local/include /opt/python/include/python2.7 /share/apps/opt/intel/mkl/include /usr/local/cuda/include ) #在这里值得说一下,target_link_libraries 语句中 生成的目标是可执行文件 后面紧跟的得是动态库的完整路径,否则会出错 #我一开始用的是Link_directoreis然后在后面直接加入了动态库的路径,结果他一直报错,提示找不到库,ORZ真是跪了, #所以要么在这里直接加入完整路径或者同通过另一条语句find_library(),这种方式也比较好,直接去指定路径查找,返回相应的绝对路径也可避免直接添加地址的问题 #gpu_nms.so 在py-faster-rcnn根目录下的lib\nms中,直接make就会生成这个so文件 target_link_libraries(faster_rcnn_demo /home/lyh1/workspace/py-faster-rcnn/caffe-fast-rcnn/build/lib/libcaffe.so /home/lyh1/workspace/py-faster-rcnn/lib/nms/gpu_nms.so /share/apps/local/lib/libopencv_highgui.so /share/apps/local/lib/libopencv_core.so /share/apps/local/lib/libopencv_imgproc.so /share/apps/local/lib/libopencv_imgcodecs.so /share/apps/local/lib/libglog.so /share/apps/local/lib/libboost_system.so /share/apps/local/lib/libboost_python.so /share/apps/local/lib/libglog.so /opt/rh/python27/root/usr/lib64/libpython2.7.so )
编译的时候比较坑爹,还会到这个问题
但是我用find命令查找了一下整个caffe的工程目录下居然没有这个caffe.pb.h 后来Google一下之后才知道需要手动生成,解决办法如下用protoc命令手动生成,并放到include文件夹下
protoc src/caffe/proto/caffe.proto --cpp_out=. mkdir include/caffe/proto mv src/caffe/proto/caffe.pb.h include/caffe/proto
最后
cmake .然后
make编译成功,运行正常。
接下来就是这么打包成动态库了,具体操作在下一个博文中
相关文章推荐
- faster-rcnn配置和训练小结
- faster-rcnn 之 shell脚本开始训练:./experiments/scripts/faster_rcnn_alt_opt.sh 0 ZF pascal_voc
- faster-rcnn 之训练脚本解析:./tools/train_faster_rcnn_alt_opt.py
- faster-rcnn 之 RPN网络的结构解析
- faster-rcnn 之 基于roidb get_minibatch(数据准备操作)
- py-faster-rcnn + ZF 实现自己的数据训练与检测(一)
- cuda8.0 + cudnn5.1 Faster-RCNN
- 物体检测系列之faster-rcnn原理介绍
- faster-rcnn训练自己的数据集以及遇到的一些问题
- faster-rcnn原理及相应概念解释
- 使用gpu(gtx1080) cudnn 5.1下编译faster rcnn
- Faster-rcnn voc数据集制作
- faster-rcnn训练自己的数据时报错too many indices
- caffe安装好MATLAB接口配置(和faster-rcnn里的MATLAB是一样的操作)--4
- Ubuntu16.04+MATLAB2014a+faster-rcnn的CPU安装-3
- Ubuntu16.04+caffe的安装和Py-faster-rcnn在CPU电脑的安装-2
- PASCAL VOC数据集分析
- R-CNN,SSP-Net,fast-RCNN,faster-RCNN论文读后笔记
- MATLAB版Faster-RCNN代码解析