使用两个不同LMDB的多标签

时间:2016-05-17 02:06:15

标签: c++ computer-vision caffe multilabel-classification lmdb

我是caffe框架的新手,我想使用caffe来实现多标签的培训。我使用两个LMDB分别保存数据和标签。数据LMDB的尺寸为Nx1xHxW,而标签LMDB的尺寸为Nx1x1x3。标签是浮动数据。

文本文件如下:

5911 3
train/train_data/4224.bmp        13         0        12
train/train_data/3625.bmp        11         3         7
...                              ...

我使用C ++创建LMDB。我的main.cpp:

#include <algorithm>
#include <fstream>  // NOLINT(readability/streams)
#include <string>
#include <utility>
#include <vector>
#include <QImage>

#include "boost/scoped_ptr.hpp"
#include "gflags/gflags.h"
#include "glog/logging.h"

#include "caffe/proto/caffe.pb.h"
#include "caffe/util/db.hpp"
#include "caffe/util/format.hpp"
#include "caffe/util/rng.hpp"

#include <boost/filesystem.hpp>
#include <iomanip>
#include <iostream>  // NOLINT(readability/streams)
#include <string>

#include "google/protobuf/message.h"

#include "caffe/common.hpp"
#include "caffe/proto/caffe.pb.h"
#include "caffe/util/format.hpp"

#ifndef CAFFE_TMP_DIR_RETRIES
#define CAFFE_TMP_DIR_RETRIES 100
#endif

using namespace caffe;  // NOLINT(build/namespaces)
using std::pair;
using boost::scoped_ptr;

const char *dat_lab="/home/mul/caffe-master/examples/2D_3D/new/info/train.data";
string data_db="/home/mul/caffe-master/examples/2D_3D/new/2D_3D_data_leveldb";
string label_db="/home/mul/caffe-master/examples/2D_3D/new/2D_3D_label_leveldb";
string root="/home/mul/caffe-master/examples/2D_3D/new/";
string path;

int main()
{

    //Create data DB
    scoped_ptr<db::DB> dat_db(db::GetDB("leveldb"));
    dat_db->Open(data_db, db::NEW);
    scoped_ptr<db::Transaction> dat_txn(dat_db->NewTransaction());

    //Create label DB
    scoped_ptr<db::DB> lab_db(db::GetDB("leveldb"));
    lab_db->Open(label_db, db::NEW);
    scoped_ptr<db::Transaction> lab_txn(lab_db->NewTransaction());

    //Storing to db
    Datum dat_datum,lab_datum;
    int count=0;

    std::ifstream infile(dat_lab);
    std::string filename;
    const char *dataname;
    int dataNum;
    int labelcount;
    QImage img;
    infile>>dataNum>>labelcount;
    LOG(INFO) << "A total of " << dataNum<< " images.";

    for (int line_id = 0; line_id < dataNum; ++line_id)
    {
        infile>>filename;
        path=root+filename;
        dataname=path.c_str();
        img.load(dataname);

        dat_datum.set_channels(1);
        dat_datum.set_height(img.height());
        dat_datum.set_width(img.width());
        dat_datum.clear_data();
        dat_datum.clear_float_data();

        int datum_channels = dat_datum.channels();
        int datum_height = dat_datum.height();
        int datum_width = dat_datum.width();
        int datum_size = datum_channels * datum_height * datum_width;
        std::string buffer(datum_size, ' ');
        const uchar* ptr = img.bits();
        int img_index = 0;
        for (int h = 0; h < datum_height; ++h)
        {

            for (int w = 0; w < datum_width; ++w)
            {
                for (int c = 0; c < datum_channels; ++c)
                {
                    int datum_index = (c * datum_height + h) * datum_width + w;
                    buffer[datum_index] = static_cast<char>(ptr[img_index++]);
                }
            }
        }
        dat_datum.set_data(buffer);


        lab_datum.set_channels(labelcount);
        lab_datum.set_height(1);
        lab_datum.set_width(1);
        lab_datum.clear_data();
        lab_datum.clear_float_data();
        for(int i=0;i<labelcount;++i)
        {
            float mid;
            infile>>mid;
            lab_datum.add_float_data(mid);
        }

        // sequential
        string key_str = caffe::format_int(line_id, 8);

        // Put in db
        string out;
        CHECK(dat_datum.SerializeToString(&out));
        dat_txn->Put(key_str, out);
        CHECK(lab_datum.SerializeToString(&out));
        lab_txn->Put(key_str, out);

        if (++count % 1000 == 0)
        {
            // Commit db
            dat_txn->Commit();
            dat_txn.reset(dat_db->NewTransaction());
            lab_txn->Commit();
            lab_txn.reset(lab_db->NewTransaction());
            LOG(INFO) << "Processed " << count << " files.";
        }
    }
    // write the last batch
    if (count % 1000 != 0)
    {
        dat_txn->Commit();
        lab_txn->Commit();
        LOG(INFO) << "Processed " << count << " files.";
    }
    return 0;
}

可以成功创建两个LMDB。但是当我使用caffe用两个LMDB实现训练时,结果总是错误的。损失层是EUCLIDEAN_LOSS并且损失不能下降。我不知道可以创建两个LMDB的代码是错误的。谁能帮我 ?谢谢。

1 个答案:

答案 0 :(得分:2)

总的来说,上面的代码还可以,但你应该注意到:

  1. 您的.cpp是创建LEVELDB而不是LMDB,当然这不是导致您的问题的原因,两种类型都可以。
  2. 您的代码生成的&#34;标签 LMDB&#34; 维度 Nx3x1x1 Nx1x1x3( NumberxChannelxWidthxHeight )。
  3. 在使用minibatch SGD的学习任务中,据我所知,将数据洗牌以获得更优化的模型非常有用。我不确定你是否注意到了这一点。但至少你的cpp并没有改变你的&#34; train.data&#34;。
  4. 最重要的是,导致您的问题的原因最有可能是在您网络中的数据层中读取您的数据并标记lmdb / leveldb文件,因为您已将标签分配给浮动数据的数据和caffe中的DataLayer实际上不会读取浮点数据(仅当您使用自定义数据层时)。所以请同时上传定义网络的原型文件。因此,我们可以找出问题到底是什么。
  5. 最后,我添加了一个&#34; MultiTaskData&#34;图层MultiTaskDataLayer可以从基准面读取多标签以进行多任务培训,您可以进行简单的修改以将其添加到您的caffe中并使用如下:

        name: "AgeNet"
        layer {
            name: "Age"
            type: "MultiTaskData"
            top: "data"
            top: "age_label"
            top: "gender_label"
            data_param { 
                source: "age_gender_classification_0_60p_train_leveldb"   
                batch_size: 60 
                task_num: 2
                label_dimension: 1
                label_dimension: 1
            }
            transform_param {
                scale: 0.00390625
                crop_size: 60
                mirror: true
            }
            include:{ phase: TRAIN }
        }
        layer { 
            name: "cls_age" 
            type: "InnerProduct"
            bottom: "data"  
            top: "cls_age" 
            param {
                lr_mult: 1
                decay_mult: 1
            }
            param {
                lr_mult: 2
                decay_mult: 0
            }
            inner_product_param {
                num_output: 7
                weight_filler {
                type: "xavier"
                }    
            bias_filler {      
                type: "constant"
                }  
            }
        }
        layer {  
            name: "age_loss"  
            type: "SoftmaxWithLoss"  
            bottom: "cls_age" 
            bottom: "age_label"
            top: "age_loss"
            include:{ phase: TRAIN }
        }
        layer { 
            name: "cls_gender" 
            type: "InnerProduct"
            bottom: "data"  
            top: "cls_gender" 
            param {
                lr_mult: 1
                decay_mult: 1
            }
            param {
                lr_mult: 2
                decay_mult: 0
            }
            inner_product_param {
                num_output: 2
                weight_filler {
                    type: "xavier"
                }    
                bias_filler {      
                    type: "constant"
                }  
            }
        }
        layer {  
            name: "gender_loss"  
            type: "SoftmaxWithLoss"  
            bottom: "cls_gender" 
            bottom: "gender_label"
            top: "gender_loss"
            include:{ phase: TRAIN }
        }