本人研一,最近想将用caffe训出的模型,通过MFC做出一个界面,扔进一张图片,点击预测,即可调用预测分类函数完成测试,并且通过MessageBox弹出最终分类的信息。
首先通过查资料总结出两种方法,第一:直接调用编译好的caffe源码;(本次用到的源码是classification.cpp)
第二:将caffe源码生成动态链接库dll,然后在其它工程项目下进行调用。由于caffe的源码依赖 项太多,稍微错一点就编译不通过,故本次操作采用调用dll的方式。
1.win7 vs2013,新建win32控制台程序,如下所示:
2.首先将项目的属性改成release和x64编译模式,添加两个.h文件和一个cpp文件:
(1)我采用的是dllexport方式导出的,采用了条件编译,要将DLL_EXPORTS宏定义加入到预处理器中以及_SCL_SECURE_NO_WARNINGS
Tip:.h文件
#ifndef CAFFE_CLASSIFY_H_
#define CAFFE_CLASSIFY_H_
#define CPU_ONLY 1
#include
#include
#include
#include
#include
#include
#include
#include
#include
#include
//#pragma once
using namespace caffe;
using std::string;
using namespace std;
using boost::shared_ptr;
#ifdef DLL_EXPORTS
#define DLL_EXPORTS_API _declspec(dllexport)
#else
#define DLL_EXPORTS_API _declspec(dllimport)
#endif
/* Pair (label, confidence) representing a prediction. */
typedef std::pair Prediction;
class DLL_EXPORTS_API Classifier {
public:
Classifier(const string& model_file,
const string& trained_file,
const string& mean_file,
const string& label_file);
std::vector Classify(const cv::Mat& img, int N = 5);
~Classifier();
private:
void SetMean(const string& mean_file);
std::vector Predict(const cv::Mat& img);
void WrapInputLayer(std::vector* input_channels);
void Preprocess(const cv::Mat& img,
std::vector* input_channels);
private:
boost::shared_ptr > net_;
cv::Size input_geometry_;
int num_channels_;
cv::Mat mean_;
std::vector labels_;
};
#endif
(2)此文件是关于层的,缺哪个添加哪个。之前按照网上博客抄的,后来运行的时候报错:Unkown Layer 。后来想起来我的网络里面用到了Concat Layer,后来就自己添加了,特别注意:直接extern 就行,不用REGISTER_LAYER_CLASS(Concat);
Tip .h文件,此文件是关于层的,缺哪个添加哪个。之前按照网上博客抄的,后来运行的时候报错:Unkown Layer 。后来想起来我的网络里面用到了Concat Layer,后来就自己添加了,特别注意:直接extern 就行,不用REGISTER_LAYER_CLASS(Concat);
#ifndef LAYER_H
#define LAYER_H
#include "caffe/common.hpp"
#include "caffe/layers/input_layer.hpp"
#include "caffe/layers/inner_product_layer.hpp"
#include "caffe/layers/dropout_layer.hpp"
#include "caffe/layers/conv_layer.hpp"
#include "caffe/layers/relu_layer.hpp"
#include "caffe/layers/pooling_layer.hpp"
#include "caffe/layers/lrn_layer.hpp"
#include "caffe/layers/softmax_layer.hpp"
#include "caffe/layers/concat_layer.hpp"
namespace caffe
{
extern INSTANTIATE_CLASS(InputLayer);
extern INSTANTIATE_CLASS(InnerProductLayer);
extern INSTANTIATE_CLASS(DropoutLayer);
extern INSTANTIATE_CLASS(ConcatLayer);
extern INSTANTIATE_CLASS(ConvolutionLayer);
REGISTER_LAYER_CLASS(Convolution);
extern INSTANTIATE_CLASS(ReLULayer);
REGISTER_LAYER_CLASS(ReLU);
extern INSTANTIATE_CLASS(PoolingLayer);
REGISTER_LAYER_CLASS(Pooling);
extern INSTANTIATE_CLASS(LRNLayer);
REGISTER_LAYER_CLASS(LRN);
extern INSTANTIATE_CLASS(SoftmaxLayer);
REGISTER_LAYER_CLASS(Softmax);
//extern INSTANTIATE_CLASS(ConcatLayer);
//REGISTER_LAYER_CLASS(Concat);
}
#endif
(3)将classification的源文件赋值到cpp中,注意添加头文件;
.cpp文件
#include "Header.h"
#include "SingleDll.h"
Classifier::Classifier(const string& model_file,
const string& trained_file,
const string& mean_file,
const string& label_file) {
#ifdef CPU_ONLY
Caffe::set_mode(Caffe::CPU);
#else
Caffe::set_mode(Caffe::GPU);
#endif
//Caffe::set_mode(Caffe::GPU);
/* Load the network. */
net_.reset(new Net(model_file, TEST));
net_->CopyTrainedLayersFrom(trained_file);
CHECK_EQ(net_->num_inputs(), 1) << "Network should have exactly one input.";
CHECK_EQ(net_->num_outputs(), 1) << "Network should have exactly one output.";
Blob* input_layer = net_->input_blobs()[0];
num_channels_ = input_layer->channels();
CHECK(num_channels_ == 3 || num_channels_ == 1)
<< "Input layer should have 1 or 3 channels.";
input_geometry_ = cv::Size(input_layer->width(), input_layer->height());
/* Load the binaryproto mean file. */
SetMean(mean_file);
/* Load labels. */
std::ifstream labels(label_file.c_str());
CHECK(labels) << "Unable to open labels file " << label_file;
string line;
while (std::getline(labels, line))
labels_.push_back(string(line));
Blob* output_layer = net_->output_blobs()[0];
CHECK_EQ(labels_.size(), output_layer->channels())
<< "Number of labels is different from the output layer dimension.";
}
static bool PairCompare(const std::pair& lhs,
const std::pair& rhs) {
return lhs.first > rhs.first;
}
/* Return the indices of the top N values of vector v. */
static std::vector Argmax(const std::vector& v, int N) {
std::vector > pairs;
for (size_t i = 0; i < v.size(); ++i)
pairs.push_back(std::make_pair(v[i], static_cast(i)));
std::partial_sort(pairs.begin(), pairs.begin() + N, pairs.end(), PairCompare);
std::vector result;
for (int i = 0; i < N; ++i)
result.push_back(pairs[i].second);
return result;
}
/* Return the top N predictions. */
std::vector Classifier::Classify(const cv::Mat& img, int N) {
std::vector output = Predict(img);
N = std::min(labels_.size(), N);
std::vector maxN = Argmax(output, N);
std::vector predictions;
for (int i = 0; i < N; ++i) {
int idx = maxN[i];
predictions.push_back(std::make_pair(labels_[idx], output[idx]));
}
return predictions;
}
/* Load the mean file in binaryproto format. */
void Classifier::SetMean(const string& mean_file) {
BlobProto blob_proto;
ReadProtoFromBinaryFileOrDie(mean_file.c_str(), &blob_proto);
/* Convert from BlobProto to Blob */
Blob mean_blob;
mean_blob.FromProto(blob_proto);
CHECK_EQ(mean_blob.channels(), num_channels_)
<< "Number of channels of mean file doesn't match input layer.";
/* The format of the mean file is planar 32-bit float BGR or grayscale. */
std::vector channels;
float* data = mean_blob.mutable_cpu_data();
for (int i = 0; i < num_channels_; ++i) {
/* Extract an individual channel. */
cv::Mat channel(mean_blob.height(), mean_blob.width(), CV_32FC1, data);
channels.push_back(channel);
data += mean_blob.height() * mean_blob.width();
}
/* Merge the separate channels into a single image. */
cv::Mat mean;
cv::merge(channels, mean);
/* Compute the global mean pixel value and create a mean image
* filled with this value. */
cv::Scalar channel_mean = cv::mean(mean);
mean_ = cv::Mat(input_geometry_, mean.type(), channel_mean);
}
std::vector Classifier::Predict(const cv::Mat& img) {
Blob* input_layer = net_->input_blobs()[0];
input_layer->Reshape(1, num_channels_,
input_geometry_.height, input_geometry_.width);
/* Forward dimension change to all layers. */
net_->Reshape();
std::vector input_channels;
WrapInputLayer(&input_channels);
Preprocess(img, &input_channels);
net_->Forward();
/* Copy the output layer to a std::vector */
Blob* output_layer = net_->output_blobs()[0];
const float* begin = output_layer->cpu_data();
const float* end = begin + output_layer->channels();
return std::vector(begin, end);
}
/* Wrap the input layer of the network in separate cv::Mat objects
* (one per channel). This way we save one memcpy operation and we
* don't need to rely on cudaMemcpy2D. The last preprocessing
* operation will write the separate channels directly to the input
* layer. */
void Classifier::WrapInputLayer(std::vector* input_channels) {
Blob* input_layer = net_->input_blobs()[0];
int width = input_layer->width();
int height = input_layer->height();
float* input_data = input_layer->mutable_cpu_data();
for (int i = 0; i < input_layer->channels(); ++i) {
cv::Mat channel(height, width, CV_32FC1, input_data);
input_channels->push_back(channel);
input_data += width * height;
}
}
void Classifier::Preprocess(const cv::Mat& img,
std::vector* input_channels) {
/* Convert the input image to the input image format of the network. */
cv::Mat sample;
if (img.channels() == 3 && num_channels_ == 1)
cv::cvtColor(img, sample, cv::COLOR_BGR2GRAY);
else if (img.channels() == 4 && num_channels_ == 1)
cv::cvtColor(img, sample, cv::COLOR_BGRA2GRAY);
else if (img.channels() == 4 && num_channels_ == 3)
cv::cvtColor(img, sample, cv::COLOR_BGRA2BGR);
else if (img.channels() == 1 && num_channels_ == 3)
cv::cvtColor(img, sample, cv::COLOR_GRAY2BGR);
else
sample = img;
cv::Mat sample_resized;
if (sample.size() != input_geometry_)
cv::resize(sample, sample_resized, input_geometry_);
else
sample_resized = sample;
cv::Mat sample_float;
if (num_channels_ == 3)
sample_resized.convertTo(sample_float, CV_32FC3);
else
sample_resized.convertTo(sample_float, CV_32FC1);
cv::Mat sample_normalized;
cv::subtract(sample_float, mean_, sample_normalized);
/* This operation will write the separate BGR planes directly to the
* input layer of the network because it is wrapped by the cv::Mat
* objects in input_channels. */
cv::split(sample_normalized, *input_channels);
CHECK(reinterpret_cast(input_channels->at(0).data)
== net_->input_blobs()[0]->cpu_data())
<< "Input channels are not wrapping the input layer of the network.";
}
Classifier::~Classifier()
{}
3.打开属性管理器,添加caffe相关依赖项。添加完可能会报各种can not open XXX.lib的错误。莫着急,这都是由于粗心路径不对造成的,要注意细节。
包含目录:
D:\caffe\NugetPackages\gflags.2.1.2.1\build\native\include
D:\caffe\NugetPackages\glog.0.3.3.0\build\native\include
D:\caffe\NugetPackages\protobuf-v120.2.6.1\build\native\include
D:\caffe\NugetPackages\OpenCV.2.4.10\build\native\include
D:\caffe\NugetPackages\OpenBLAS.0.2.14.1\lib\native\include
D:\caffe\NugetPackages\boost.1.59.0.0\lib\native\include
还要加上caffe编译完生成的include路径,最好将其复制到该项目下
eg.D:\caffe-class\include
库目录:
E:\caffe\NugetPackages\OpenCV.2.4.10\build\native\lib\x64\v120\Release
E:\caffe\NugetPackages\gflags.2.1.2.1\build\native\x64\v120\dynamic\Lib
E:\caffe\NugetPackages\glog.0.3.3.0\build\native\lib\x64\v120\Release \dynamic
E:\caffe\NugetPackages\OpenBLAS.0.2.14.1\lib\native\lib\x64
E:\caffe\NugetPackages\protobuf-v120.2.6.1\build\native\lib\x64\v120\Release
E:\caffe\NugetPackages\LevelDB-vc120.1.2.0.0\build\native\lib\x64\v120\Release
E:\caffe\NugetPackages\hdf5-v120-complete.1.8.15.2\lib\native\lib\x64
E:\caffe\NugetPackages\boost_date_time-vc120.1.59.0.0\lib\native\address-model-64\lib
E:\caffe\NugetPackages\boost_filesystem-vc120.1.59.0.0\lib\native\address-model-64\lib
E:\caffe\NugetPackages\boost_system-vc120.1.59.0.0\lib\native\address-model-64\lib
E:\caffe\NugetPackages\boost_thread-vc120.1.59.0.0\lib\native\address-model-64\lib
E:\caffe\NugetPackages\boost_chrono-vc120.1.59.0.0\lib\native\address-model-64\lib
注意还需添加caffe编译生成的release文件
Tip:上述库目录中少了lmdb ,自己别忘了
添加依赖项
libglog.lib
libcaffe.lib
gflags.lib
gflags_nothreads.lib
hdf5.lib
hdf5_hl.lib
libprotobuf.lib
libopenblas.dll.a
Shlwapi.lib
LevelDb.lib
lmdb.lib
opencv_core2410.lib
opencv_highgui2410.lib
opencv_imgproc2410.lib
opencv_video2410.lib
opencv_objdetect2410.lib
注意:由于我是cpu条件下编译的(加了宏定义CPU_ONLY),若您是GPU 则要添加相应的cudn的路径,以及
cublas.lib
cuda.lib
curand.lib
cudart.lib
cudnn.lib 这些依赖项!!
4.编译生成,会发现生成dll lib等文件,但是没有ink,不知道为啥,那不重要。
最后第一篇生成dll文件就讲解到这里,生成完后可以测试一下能不能用。我也是先测试能用,才新建MFC工程进行调用的。
下次就为大家讲解MFC下调用,具体实现MFC调用caffemodel实现过程。
若需要help,QQ 1443563995.如有错误,多多指教!