caffe

caffe

关注
发信
关注(28)粉丝(399)

c++ - 如何在ssd-caffe中加载图像而不是LMDB

当我阅读ssd-caffe代码时有一些问题，我确实需要您的帮助。

  • 本机caffe仅支持分类，数据读取层通常用于读取LMDB数据库和读取图像以训练
  • 为了支持多个标签和输入注释框的输入，我决定使用ssd-caffe，它向本地caffe添加了AnnotatedDataLayer层。这个新添加的层可以支持多个标签和注释框，但是有其局限性。原因是它读取的数据类型仍然是lmdb。
  • 现在，我们需要随机读取数据集的数据，但是根据查询结果，lmdb是B +树结构，只能通过迭代器顺序读取，因此我们想更改lmdb以直接读取图像。但是，本机咖啡的直接阅读图片不支持多标签和注释框。如何修改caffe的image_data_layers以支持注释框的输入(我可以遵循AnnotatedDataLayer的方法来解决此问题)吗？

    • 注意:
  • 修改的ssd-caffe源代码:https://github.com/eric612/MobileNet-YOLO
  • 新添加的注释框的文件路径:/MobileNet-YOLO/src/caffe/layers/annotated_data_layer.cpp
  • 用于直接读取图片的本机caffe文件路径:/MobileNet-YOLO/src/caffe/layers/image_data_layer.cpp

    • 最佳答案

    数据层提供了异步读取硬盘上随机数据的可能性(它使用2个线程:一个线程读取数据，另一个线程将数据传送到神经网络)。您的顶部Blob由数据和标签组成。不幸的是，标签是一维的。为了解决此问题，可以以特殊顺序组织lmdb数据库。然后，当我们读取数据时，在将其传递到神经网络之前，我们先对其进行转换以使其适应我们的问题。在下面的示例中，我将进行演示:首先，我将编写一个LMDB数据库，其中包含10个不同的图像(它是同一张图像，但我们假定它们是不同的)，10个随机边界框和10个维度为3的随机标签。

    注意:要重现以下代码，您必须安装caffe。如果只编译了caffe文件夹，则在 root_caffe / examples / new_folder 中创建该文件夹，将代码放入其中，然后进行编译 make 。

    #include <caffe/caffe.hpp>
#include "caffe/proto/caffe.pb.h"
#include "caffe/util/db.hpp"
#include "boost/scoped_ptr.hpp"
#include <opencv2/imgcodecs.hpp>
#include <iostream>
#include <stdlib.h>


using namespace caffe;
using boost::scoped_ptr;


std::vector<float> generate_random_boxes(const int max_num_bbx){

        std::vector<float> bbx(4*max_num_bbx);

    for(int i = 0; i < max_num_bbx; i++){

       float scale = 500*static_cast <float> (rand()) / static_cast <float> (RAND_MAX);
       float x1 = static_cast <float> (rand()) / static_cast <float> (RAND_MAX);
       float y1 = static_cast <float> (rand()) / static_cast <float> (RAND_MAX);
       float x2 = x1 + static_cast <float> (rand()) / static_cast <float> (RAND_MAX);
       float y2 = x1 + static_cast <float> (rand()) / static_cast <float> (RAND_MAX);
       bbx[i*4] = scale*x1;
       bbx[i*4 + 1] = scale*y1;
       bbx[i*4 + 2] = scale*x2;
       bbx[i*4 + 3] = scale*y2;

    }

    return bbx;
}

std::vector<float> generate_random_labels(const int dim_label, const int max_num_bbx){

        std::vector<float> labels(dim_label*max_num_bbx);

    for(int i = 0; i < max_num_bbx; i++){
       for(int j = 0; j < dim_label; j++){

          labels[dim_label*i + j] = static_cast <float> (rand()) / static_cast <float> (RAND_MAX);

           }
    }

    return labels;
}


int main(){

  const std::string root_path = "/path/for/test/";
  const std::string path_lmdb = root_path + "lmdb";
  std::string rm_lmdb = std::string("rm -rf ") + path_lmdb.c_str();
  system(rm_lmdb.c_str());
  scoped_ptr<db::DB> db(db::GetDB("lmdb"));
  db->Open(path_lmdb, db::NEW);
  scoped_ptr<db::Transaction> txn(db->NewTransaction());


  int n = 10;
  int max_num_bbx = 7;
  int dim_label = 3;
  cv::Mat aux_img = cv::imread(root_path + "image.jpg");
  int rows = aux_img.rows;
  int cols = aux_img.cols;

  std::vector<cv::Mat> vec_img(n);
  std::vector< std::vector<float> > vec_bbx(n);
  std::vector< std::vector<float> > vec_label(n);

  for(int i = 0; i < n; i++){

     vec_img[i] = aux_img.clone();
     vec_bbx[i] = generate_random_boxes(max_num_bbx);
     vec_label[i] = generate_random_labels(dim_label, max_num_bbx);

  }

  for(int i = 0; i< n; i++){

     int sz = 3*rows*cols + 4*max_num_bbx + dim_label*max_num_bbx;

     Datum datum;
     datum.set_label(0); //no used
     datum.set_channels(1);
     datum.set_height(1);
     datum.set_width(sz);

     google::protobuf::RepeatedField<float>* datumFloatData = datum.mutable_float_data();

     //store images
     cv::Mat img = vec_img[i];
     for(int d = 0; d < 3; d++){ //BGR
        for(int r = 0; r < rows; r++){
           for(int c = 0; c < cols; c++){

              cv::Vec3b pixel = img.at<cv::Vec3b>(r, c);
              datumFloatData->Add(float(pixel[d]));

           }
        }
     }


    //store bounding-boxes
    std::vector<float>& bbx = vec_bbx[i];
    for(int j = 0; j < 4*max_num_bbx; j++)
       datumFloatData->Add(bbx[j]);

    //store labels
    std::vector<float>& label = vec_label[i];
    for(int j = 0; j < dim_label*max_num_bbx; j++)
       datumFloatData->Add(label[j]);


    //store lmdb
    std::string key_str = caffe::format_int(i);
    std::string out;
    CHECK(datum.SerializeToString(&out));
    txn->Put(key_str, out);
    txn->Commit();
    txn.reset(db->NewTransaction());
    std::cout<<"save data: "<<i<<std::endl;


  }

 return 0;

}

    然后在文件夹“/ path / for / test” 中，我们将有一个名为 lmdb 的文件夹，其中包含我们的数据库。现在，我们必须读取数据并按所需顺序对其进行组织。为此，我将使用 Slice 层，该层允许将输入的底部数据划分为多个顶部。因此，由图像批处理，边界框和标签组成的输入数据将被分为5个顶部Blob:img_b，img_g，img_r，bbx，标签。
    #include <caffe/caffe.hpp>

#include <opencv2/imgcodecs.hpp>
#include <opencv2/core.hpp>
#include <opencv2/imgcodecs.hpp>
#include <opencv2/highgui.hpp>
#include <opencv2/imgproc/imgproc.hpp>
#include "boost/scoped_ptr.hpp"
#include <iostream>
#include <stdio.h>
#include <stdlib.h>

using namespace caffe;
using boost::scoped_ptr;

int main(){


  const std::string root_path = "/path/for/test/";
  const std::string path_lmdb = root_path + "lmdb";


  //parameters used to store lmdb data base
  int n = 10;
  int max_num_bbx = 7;
  int dim_label = 3;
  cv::Mat aux_img = cv::imread(root_path + "image.jpg");
  int rows = aux_img.rows;
  int cols = aux_img.cols;


  //here we build the network input

  NetParameter net_param;

  LayerParameter* db_layer_param = net_param.add_layer();
  db_layer_param->set_name("data");
  db_layer_param->set_type("Data");
  DataParameter* db_data_param = db_layer_param->mutable_data_param();

  db_data_param->set_batch_size(2);
  db_data_param->set_prefetch(3);


  db_data_param->set_source(path_lmdb);
  db_data_param->set_backend(DataParameter_DB_LMDB);


  db_layer_param->add_top("data");

  LayerParameter* slice_layer_param = net_param.add_layer();
  slice_layer_param->set_name("slice");
  slice_layer_param->set_type("Slice");
  slice_layer_param->mutable_slice_param()->set_axis(3);//starting B
  slice_layer_param->mutable_slice_param()->add_slice_point(rows*cols);//starting G
  slice_layer_param->mutable_slice_param()->add_slice_point(2*rows*cols);//starting R
  slice_layer_param->mutable_slice_param()->add_slice_point(3*rows*cols);//starting bbx
  slice_layer_param->mutable_slice_param()->add_slice_point(3*rows*cols + 4*max_num_bbx);//starting labels


  slice_layer_param->add_bottom("data");

  slice_layer_param->add_top("img_b");
  slice_layer_param->add_top("img_g");
  slice_layer_param->add_top("img_r");
  slice_layer_param->add_top("bbx");
  slice_layer_param->add_top("labels");


  //NOTE: you must add the additional layers of your model
  /*
  .
  .
  .
  .
  */



  //here we store and load the model
  //NOTE:In this example is not necessary to store the model in prototxt file
  const std::string net_file = root_path + "model.prototxt";
  Net<float> net(net_param);
  WriteProtoToTextFile(net_param,net_file);




  //here we make forward in order to read our data
  net.Forward();



  /*Note that in this example we read 2 images, but then we will only show the first*/

  //read first image
  boost::shared_ptr< Blob< float > > img_b = net.blob_by_name("img_b");
  boost::shared_ptr< Blob< float > > img_g = net.blob_by_name("img_g");
  boost::shared_ptr< Blob< float > > img_r = net.blob_by_name("img_r");

  cv::Mat img(rows,cols,CV_8UC3);

  for(int r = 0; r < rows; r++){
      for(int c = 0; c < cols; c++){

      img.at<cv::Vec3b>(r,c)[0] = (uchar) img_b->cpu_data()[r*cols + c];
      img.at<cv::Vec3b>(r,c)[1] = (uchar) img_g->cpu_data()[r*cols + c];
      img.at<cv::Vec3b>(r,c)[2] = (uchar) img_r->cpu_data()[r*cols + c];
      }
  }



  //read bounding boxes
  boost::shared_ptr< Blob< float > > bbx = net.blob_by_name("bbx");

  for(int i = 0; i < max_num_bbx; i++){

     float x1 = bbx->cpu_data()[4*i];
     float y1 = bbx->cpu_data()[4*i + 1];
     float x2 = bbx->cpu_data()[4*i + 2];
     float y2 = bbx->cpu_data()[4*i + 3];

     cv::Point pt1(y1, x1);
     cv::Point pt2(y2, x2);
     cv::rectangle(img, pt1, pt2, cv::Scalar(0, 255, 0));

  }


 //read labels
 boost::shared_ptr< Blob< float > > labels = net.blob_by_name("labels");

 std::cout<<"labels: "<<std::endl;
 for(int i = 0; i < max_num_bbx; i++){
    for(int j = 0; j < dim_label; j++){

     std::cout<<labels->cpu_data()[i*dim_label + j]<<" ";

    }
    std::cout<<std::endl;
 }


 cv::imshow("img", img);
 cv::waitKey(0);

 return 0;

}

    生成的输出如下:

    c&#43;&#43; - 如何在ssd-caffe中加载图像而不是LMDB-LMLPHP

    数据和 Slice层使用WriteProtoToTextFile(net_param，net_file)生成的原型(prototype)文件如下:
    layer {
  name: "data"
  type: "Data"
  top: "data"
  data_param {
    source: "/path/for/test/lmdb"
    batch_size: 2
    backend: LMDB
    prefetch: 3
  }
}
layer {
  name: "slice"
  type: "Slice"
  bottom: "data"
  top: "img_b"
  top: "img_g"
  top: "img_r"
  top: "bbx"
  top: "labels"
  slice_param {
    slice_point: 344000
    slice_point: 688000
    slice_point: 1032000
    slice_point: 1032028
    axis: 3
  }
}

    在 Slice图层之后，您可能需要添加其他 Reshape图层以使数据适应后续图层。

    关于c++ - 如何在ssd-caffe中加载图像而不是LMDB，我们在Stack Overflow上找到一个类似的问题：https://stackoverflow.com/questions/62307905/

    10-12 23:31
    Powered by LMLPHP ©2024 caffe 0.033271