关键词：
除了在opencv dnn中使用训练好的model，还可以直接通过classification.exe去查看单张图的训练结果。
但是我在使用opencv dnn的时候，发现里面输出的结果和classification.exe并不一样，一时找不到原因，于是还是考虑将classification.cpp写成库供别的程序调用。
1.配置环境。新建工程切换到release x64下
①项目属性中——配置属性——C/C++——常规：
D:\\caffe\\scripts\\build\\include;
D:\\caffe\\scripts\\build;
C:\\Users\\machenike\\.caffe\\dependencies\\libraries_v140_x64_py27_1.1.0\\libraries\\include\\boost-1_61;
C:\\Users\\machenike\\.caffe\\dependencies\\libraries_v140_x64_py27_1.1.0\\libraries\\include;
C:\\Program Files\\NVIDIA GPU Computing Toolkit\\CUDA\\v8.0\\include;
C:\\Users\\machenike\\.caffe\\dependencies\\libraries_v140_x64_py27_1.1.0\\libraries\\include\\opencv;
D:\\caffe\\include;
C:\\Users\\machenike\\.caffe\\dependencies\\libraries_v140_x64_py27_1.1.0\\libraries\\Include;%(AdditionalIncludeDirectories)
②项目属性中——配置属性——C/C++——预处理器：
WIN32;
_WINDOWS;
NDEBUG;
CAFFE_VERSION=1.0.0;
BOOST_ALL_NO_LIB;
USE_LMDB;
USE_LEVELDB;
USE_CUDNN;
USE_OPENCV;
CMAKE_WINDOWS_BUILD;
GLOG_NO_ABBREVIATED_SEVERITIES;
GOOGLE_GLOG_DLL_DECL=__declspec(dllimport);
GOOGLE_GLOG_DLL_DECL_FOR_UNITTESTS=__declspec(dllimport);
H5_BUILT_AS_DYNAMIC_LIB=1;
CMAKE_INTDIR="Release";
%(PreprocessorDefinitions)③项目属性中——配置属性——链接器——输入——附加依赖项：
D:\\caffe\\scripts\\build\\lib\\Release\\caffe.lib;
D:\\caffe\\scripts\\build\\lib\\Release\\caffeproto.lib;
C:\\Users\\machenike\\.caffe\\dependencies\\libraries_v140_x64_py27_1.1.0\\libraries\\lib\\boost_system-vc140-mt-1_61.lib;
C:\\Users\\machenike\\.caffe\\dependencies\\libraries_v140_x64_py27_1.1.0\\libraries\\lib\\boost_thread-vc140-mt-1_61.lib;
C:\\Users\\machenike\\.caffe\\dependencies\\libraries_v140_x64_py27_1.1.0\\libraries\\lib\\boost_filesystem-vc140-mt-1_61.lib;
C:\\Users\\machenike\\.caffe\\dependencies\\libraries_v140_x64_py27_1.1.0\\libraries\\lib\\boost_chrono-vc140-mt-1_61.lib;
C:\\Users\\machenike\\.caffe\\dependencies\\libraries_v140_x64_py27_1.1.0\\libraries\\lib\\boost_date_time-vc140-mt-1_61.lib;
C:\\Users\\machenike\\.caffe\\dependencies\\libraries_v140_x64_py27_1.1.0\\libraries\\lib\\boost_atomic-vc140-mt-1_61.lib;
C:\\Users\\machenike\\.caffe\\dependencies\\libraries_v140_x64_py27_1.1.0\\libraries\\lib\\glog.lib;
C:\\Users\\machenike\\.caffe\\dependencies\\libraries_v140_x64_py27_1.1.0\\libraries\\Lib\\gflags.lib;
shlwapi.lib;
C:\\Users\\machenike\\.caffe\\dependencies\\libraries_v140_x64_py27_1.1.0\\libraries\\lib\\libprotobuf.lib;
C:\\Users\\machenike\\.caffe\\dependencies\\libraries_v140_x64_py27_1.1.0\\libraries\\lib\\caffehdf5_hl.lib;
C:\\Users\\machenike\\.caffe\\dependencies\\libraries_v140_x64_py27_1.1.0\\libraries\\lib\\caffehdf5.lib;
C:\\Users\\machenike\\.caffe\\dependencies\\libraries_v140_x64_py27_1.1.0\\libraries\\cmake\\..\\lib\\caffezlib.lib;
C:\\Users\\machenike\\.caffe\\dependencies\\libraries_v140_x64_py27_1.1.0\\libraries\\lib\\lmdb.lib;
ntdll.lib;
C:\\Users\\machenike\\.caffe\\dependencies\\libraries_v140_x64_py27_1.1.0\\libraries\\lib\\leveldb.lib;
C:\\Users\\machenike\\.caffe\\dependencies\\libraries_v140_x64_py27_1.1.0\\libraries\\cmake\\..\\lib\\boost_date_time-vc140-mt-1_61.lib;
C:\\Users\\machenike\\.caffe\\dependencies\\libraries_v140_x64_py27_1.1.0\\libraries\\cmake\\..\\lib\\boost_filesystem-vc140-mt-1_61.lib;
C:\\Users\\machenike\\.caffe\\dependencies\\libraries_v140_x64_py27_1.1.0\\libraries\\cmake\\..\\lib\\boost_system-vc140-mt-1_61.lib;
C:\\Users\\machenike\\.caffe\\dependencies\\libraries_v140_x64_py27_1.1.0\\libraries\\lib\\snappy_static.lib;
C:\\Users\\machenike\\.caffe\\dependencies\\libraries_v140_x64_py27_1.1.0\\libraries\\lib\\caffezlib.lib;
C:\\Program Files\\NVIDIA GPU Computing Toolkit\\CUDA\\v8.0\\lib\\x64\\cudart.lib;
C:\\Program Files\\NVIDIA GPU Computing Toolkit\\CUDA\\v8.0\\lib\\x64\\curand.lib;
C:\\Program Files\\NVIDIA GPU Computing Toolkit\\CUDA\\v8.0\\lib\\x64\\cublas.lib;
C:\\Program Files\\NVIDIA GPU Computing Toolkit\\CUDA\\v8.0\\lib\\x64\\cublas_device.lib;
C:\\Program Files\\NVIDIA GPU Computing Toolkit\\CUDA\\v8.0\\lib\\x64\\cudnn.lib;
C:\\Users\\machenike\\.caffe\\dependencies\\libraries_v140_x64_py27_1.1.0\\libraries\\x64\\vc14\\lib\\opencv_highgui310.lib;
C:\\Users\\machenike\\.caffe\\dependencies\\libraries_v140_x64_py27_1.1.0\\libraries\\x64\\vc14\\lib\\opencv_imgcodecs310.lib;
C:\\Users\\machenike\\.caffe\\dependencies\\libraries_v140_x64_py27_1.1.0\\libraries\\x64\\vc14\\lib\\opencv_imgproc310.lib;
C:\\Users\\machenike\\.caffe\\dependencies\\libraries_v140_x64_py27_1.1.0\\libraries\\x64\\vc14\\lib\\opencv_core310.lib;
C:\\Users\\machenike\\.caffe\\dependencies\\libraries_v140_x64_py27_1.1.0\\libraries\\lib\\libopenblas.dll.a;
kernel32.lib;
user32.lib;
gdi32.lib;
winspool.lib;
shell32.lib;
ole32.lib;
oleaut32.lib;
uuid.lib;
comdlg32.lib;
advapi32.lib
④项目属性中——配置属性——链接器——输入——忽略特定默认库：
%(IgnoreSpecificDefaultLibraries)⑤复制D:\\caffe\\scripts\\build\\tools\\Release所有的dll到工程Release下
以上①②③④其实都可以在D:\\caffe\\scripts\\build\\Caffe.sln中找到
⑥复制classification需要的5个文件，分别是deploy.prototxt network.caffemodel mean.binaryproto labels.txt img.jpg到工程下（你的不一定是这个文件名）
2.复制源码。
从Caffe.sln中可以找到classification.cpp的源码，全选复制修改输入，修改后如下
#include <caffe/caffe.hpp>
#include <opencv2/core/core.hpp>
#include <opencv2/highgui/highgui.hpp>
#include <opencv2/imgproc/imgproc.hpp>
#include <algorithm>
#include <iosfwd>
#include <memory>
#include <string>
#include <utility>
#include <vector>
using namespace caffe; // NOLINT(build/namespaces)
using std::string;
/* Pair (label, confidence) representing a prediction. */
typedef std::pair<string, float> Prediction;
class Classifier
public:
Classifier(const string& model_file,
const string& trained_file,
const string& mean_file,
const string& label_file);
std::vector<Prediction> Classify(const cv::Mat& img, int N = 5);
private:
void SetMean(const string& mean_file);
std::vector<float> Predict(const cv::Mat& img);
void WrapInputLayer(std::vector<cv::Mat>* input_channels);
void Preprocess(const cv::Mat& img,
std::vector<cv::Mat>* input_channels);
private:
shared_ptr<Net<float> > net_;
cv::Size input_geometry_;
int num_channels_;
cv::Mat mean_;
std::vector<string> labels_;
;
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
/* Load the network. */
net_.reset(new Net<float>(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<float>* 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<float>* 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<float, int>& lhs,
const std::pair<float, int>& rhs)
return lhs.first > rhs.first;
/* Return the indices of the top N values of vector v. */
static std::vector<int> Argmax(const std::vector<float>& v, int N)
std::vector<std::pair<float, int> > pairs;
for (size_t i = 0; i < v.size(); ++i)
pairs.push_back(std::make_pair(v[i], static_cast<int>(i)));
std::partial_sort(pairs.begin(), pairs.begin() + N, pairs.end(), PairCompare);
std::vector<int> result;
for (int i = 0; i < N; ++i)
result.push_back(pairs[i].second);
return result;
/* Return the top N predictions. */
std::vector<Prediction> Classifier::Classify(const cv::Mat& img, int N)
std::vector<float> output = Predict(img);
N = std::min<int>(labels_.size(), N);
std::vector<int> maxN = Argmax(output, N);
std::vector<Prediction> 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<float> */
Blob<float> 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<cv::Mat> 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<float> Classifier::Predict(const cv::Mat& img)
Blob<float>* 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<cv::Mat> input_channels;
WrapInputLayer(&input_channels);
Preprocess(img, &input_channels);
net_->Forward();
/* Copy the output layer to a std::vector */
Blob<float>* output_layer = net_->output_blobs()[0];
const float* begin = output_layer->cpu_data();
const float* end = begin + output_layer->channels();
return std::vector<float>(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<cv::Mat>* input_channels)
Blob<float>* 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<cv::Mat>* 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<float*>(input_channels->at(0).data)
== net_->input_blobs()[0]->cpu_data())
<< "Input channels are not wrapping the input layer of the network.";
int main()
::google::InitGoogleLogging("init");
string model_file = "bvlc_googlenet_iter_5000.prototxt";
string trained_file = "bvlc_googlenet_iter_5000.caffemodel";
string mean_file = "imagenet_mean.binaryproto";
string label_file = "synset_words.txt";
Classifier classifier(model_file, trained_file, mean_file, label_file);
string file = "test/(1).png";
std::cout << "---------- Prediction for "
<< file << " ----------" << std::endl;
cv::Mat img = cv::imread(file, -1);
CHECK(!img.empty()) << "Unable to decode image " << file;
std::vector<Prediction> predictions = classifier.Classify(img);
/* Print the top N predictions. */
for (size_t i = 0; i < predictions.size(); ++i)
Prediction p = predictions[i];
std::cout << std::fixed << std::setprecision(4) << p.second << " - \\""
<< p.first << "\\"" << std::endl;
4.写成动态链接库供别的程序调用。
因为我分4类，一般都是直接返回相似度最大的那类，但是我还是想看以下别的类的信息，所以把每一类的相似度都返回。
于是修改上面源码为：
#include <caffe/caffe.hpp>
#include <opencv2/core/core.hpp>
#include <opencv2/highgui/highgui.hpp>
#include <opencv2/imgproc/imgproc.hpp>
#include <algorithm>
#include <iosfwd>
#include <memory>
#include <string>
#include <utility>
#include <vector>
using namespace caffe; // NOLINT(build/namespaces)
using std::string;
/* Pair (label, confidence) representing a prediction. */
typedef std::pair<string, float> Prediction;
class Classifier
public:
Classifier();
Classifier(const string& model_file,
const string& trained_file,
const string& mean_file,
const string& label_file);
void ClassifierInit(const string& model_file,
const string& trained_file,
const string& mean_file,
const string& label_file);
std::vector<Prediction> Classify(const cv::Mat& img, int N = 5);
private:
void SetMean(const string& mean_file);
std::vector<float> Predict(const cv::Mat& img);
void WrapInputLayer(std::vector<cv::Mat>* input_channels);
void Preprocess(const cv::Mat& img,
std::vector<cv::Mat>* input_channels);
private:
shared_ptr<Net<float> > net_;
cv::Size input_geometry_;
int num_channels_;
cv::Mat mean_;
std::vector<string> labels_;
;
Classifier::Classifier()
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
/* Load the network. */
net_.reset(new Net<float>(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<float>* 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<float>* output_layer = net_->output_blobs()[0];
CHECK_EQ(labels_.size(), output_layer->channels())
<< "Number of labels is different from the output layer dimension.";
void Classifier::ClassifierInit(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
/* Load the network. */
net_.reset(new Net<float>(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<float>* 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<float>* 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<float, int>& lhs,
const std::pair<float, int>& rhs)
return lhs.first > rhs.first;
/* Return the indices of the top N values of vector v. */
static std::vector<int> Argmax(const std::vector<float>& v, int N)
std::vector<std::pair<float, int> > pairs;
for (size_t i = 0; i < v.size(); ++i)
pairs.push_back(std::make_pair(v[i], static_cast<int>(i)));
std::partial_sort(pairs.begin(), pairs.begin() + N, pairs.end(), PairCompare);
std::vector<int> result;
for (int i = 0; i < N; ++i)
result.push_back(pairs[i].second);
return result;
/* Return the top N predictions. */
std::vector<Prediction> Classifier::Classify(const cv::Mat& img, int N)
std::vector<float> output = Predict(img);
N = std::min<int>(labels_.size(), N);
std::vector<int> maxN = Argmax(output, N);
std::vector<Prediction> 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<float> */
Blob<float> 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<cv::Mat> 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<float> Classifier::Predict(const cv::Mat& img)
Blob<float>* 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<cv::Mat> input_channels;
WrapInputLayer(&input_channels);
Preprocess(img, &input_channels);
net_->Forward();
/* Copy the output layer to a std::vector */
Blob<float>* output_layer = net_->output_blobs()[0];
const float* begin = output_layer->cpu_data();
const float* end = begin + output_layer->channels();
return std::vector<float>(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<cv::Mat>* input_channels)
Blob<float>* 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<cv::Mat>* 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<float*>(input_channels->at(0).data)
== net_->input_blobs()[0]->cpu_data())
<< "Input channels are not wrapping the input layer of the network.";
Classifier classifier;
_declspec(dllexport) void initNet(string model_file, string trained_file, string mean_file, string label_file)
::google::InitGoogleLogging("init");
classifier.ClassifierInit(model_file, trained_file, mean_file, label_file);
//************************************
// Method: RegPic
// FullName: RegPic
// Access: public
// Returns: void
// Qualifier:
// Parameter: int rows
// Parameter: int cols
// Parameter: unsigned __int8 * data 8位单通道，灰度图
// Parameter: float a[4] 4类相似度，也可以修改位返回最大相似度的序号，但是损失了其他信息
//************************************
_declspec(dllexport) void RegPic(int rows, int cols, unsigned __int8 *data, float classPro[4])
cv::Mat image(rows, cols, CV_8UC1, &data[0]);//单通道灰度图
if (image.empty())
std::cout << "image read error" << std::endl;
return;
cv::Mat img;
cvtColor(image, img, CV_GRAY2BGR);
std::vector<Prediction> predictions = classifier.Classify(img);
/* Print the top N predictions. */
for (size_t i = 0; i < predictions.size(); ++i)
Prediction p = predictions[i];
std::cout << std::fixed << std::setprecision(4) << p.second << " - \\""
<< p.first << "\\"" << std::endl;
int classnum = p.first[0] - 48;//类别序号
classPro[classnum] = p.second;
测试源码：
#include <opencv2/opencv.hpp>
#include <iostream>
using namespace std;
using namespace cv;
_declspec(dllexport) void RegPic(int rows, int cols, unsigned __int8 *data, float classPro[4]);
_declspec(dllexport) void initNet(string model_file, string trained_file, string mean_file, string label_file);
void main()
string model_file = "bvlc_googlenet_iter_5000.prototxt";
string trained_file = "bvlc_googlenet_iter_5000.caffemodel";
string mean_file = "imagenet_mean.binaryproto";
string label_file = "synset_words.txt";
initNet(model_file, trained_file, mean_file, label_file);//初始化网络，只需要运行一次
for (int i = 0; i < 100; i++)
stringstream ss;
ss << "test/(";
ss << i;
ss << ").png";
Mat img = imread(ss.str(), 0);
if (img.empty())
continue;
float classPro[4];
//0为合格品， 1为X花， 2为XX花， 3为XXX花
cout << "图片：" << i << endl;
RegPic(img.rows, img.cols, img.data, classPro);//识别判断，返回a数组，4个数分别代表四类的相似度最大1最小0
caffe初步实践---------使用训练好的模型完成语义分割任务
caffe刚刚安装配置结束，乘热打铁！（一）环境准备前面我有两篇文章写到caffe的搭建，第一篇cpuonly，第二篇是在服务器上搭建的，其中第二篇因为硬件环境更佳我们的步骤稍显复杂。其实，第二篇也仅仅是caffe的初步搭建完成... 查看详情
怎样用自己的数据集对caffe训练好的model进行fineture
参考技术A建议使用已有model进行finetune，新手从头开始做经常会不收敛。进一步的话可以在现有的比较好的网络结构上进行修改，使之符合自己的需求。最难的就是从零开始设计训练网络模型。题主可以体验一下从零开始设计训... 查看详情
caffe2----下载现成的模型并使用
...型可在ModelZoo下载，下载的命令很简单，接下来以下载和使用squeezenet为例，进行简单说明。 1.浏览可下载的模型已有模型都放在github上，地址：https://github.com/caffe2/caffe2/wiki/Model-Zoo，当前有caffe和caffe2两种版本的选择。 2.... 查看详情
使用caffe的cifar10网络模型训练自己的图片数据
由于我涉及一个车牌识别系统的项目，计划使用深度学习库caffe对车牌字符进行识别。刚开始接触caffe，打算先将示例中的每个网络模型都拿出来用用，当然这样暴力的使用是不会有好结果的--|||，所以这里只是记录一下示例... 查看详情
5：使用caffe对自己的图像数据进行训练并测试
使用caffe对自己的图像数据进行训练并测试之前实践的一些步骤诸如数据集的准备、数据集的转换等过程都是为了训练我们所需要的模型进行铺垫，我们学习caffe的核心目的是使用caffe对我们自己的数据集进行训练，得到... 查看详情
caffe训练好的网络对图像分类
...：彩色or灰度图片 做minist下手写识别分类，不能直接使用，需去除均值图像，同时将输入图像像素归一化到0-1直接即可。 #include<caffe/caffe 查看详情
如何使用opencvdnn模块调用caffe预训练模型？(代码片段)
QStringmodelPrototxt="D:\\Qt\\qmake\\CaffeModelTest\\caffe\\lenet.prototxt";QStringmodelBin="D:\\Qt\\qmake\\CaffeModelTest\\caffe\\snapshot_iter_10000.caffemodel";QStringimageFile= 查看详情
如何将更多图像输入到 caffe 模型中？
...图像以提高其准确性？【问题讨论】：【参考方案1】：使用更多图像进行再训练以提高准确性尝 查看详情
如何将经过训练的 caffe 模型以 h5 格式加载到 c++ caffe 网络？
...何在C++中将hdf5格式的caffe模型加载到caffenet吗？我有一个使用hd 查看详情
caffe的学习和使用·一」--使用caffe训练自己的数据
学习知识的一种方式是先会用然后再问为什么。在安装完成caffe，根据caffe的提示下载完mnist训练测试数据，并且运行lenet训练模型之后，摆在眼前的问题就是我怎么用caffe训练自己的数据啊，mnist的数据通过脚本就可以下载创建成... 查看详情
如何使用tf训练好的模型
参考技术A 1、将mnist.tflite模型放在assets文件夹下。 2、更新build.gradle以包含tflite依赖项。 3、为用户创建自定义视图。 4、创建一个进行数字分类的分类器。 5、从自定义视图输入图像。 6、图像预处理。 ... 查看详情
下载模型
...odelzoo里面有许多已有的模型，不仅有模型的prototxt，还有训练好的参数，可以下载来做finetuninghttps://github.com/BVLC/caffe/wiki/Model-Zoo 下载的方式有以下几种:1.直接去这个网址下载：http://dl.caffe.berkeleyvision.org/2.直接在modelzoo（https:... 查看详情
如何调用caffe已经训练好的net
参考技术A关于准确率一直是0.5：我不了解你是怎么训练的，但是对于二分类问题最后准确率是0.5，有可能是因为最终结果都分到同一类上面去了，这个你需要调用caffe看看网络最终的输出来判断对于二分类问题，一般训练的时候... 查看详情
是否可以在python中提取训练好的机器学习模型的公式？
...】：2018-11-0607:32:43【问题描述】：在我的项目中，我应该使用分类器根据6个输入值预测8个类之一。我必须在仅运行C++代码的设备上比较所有监督学习分类器。所以我使用python来教授/拟合机器学 查看详情
如何实现java上传图片并用python训练好的模型来测试呢
参考技术ATensorflow可以使用训练好的模型对新的数据进行测试，有两种方法：第一种方法是调用模型和训练在同一个py文件中，中情况比较简单；第二种是训练过程和调用模型过程分别在两个py文件中。 查看详情
如何利用bing算法训练自己的模型
...ts=examples/mnist/lenet_iter_10000.caffemodel-gpu=0 如果没有GPU则使用 ./build/tools/caffe.bintest-model=examples/mnist/lenet_train_test.prototxt-weights=examples/mnist/lenet_iter_10000.caffemodel 从上面的指令，对应上图。 1、先是test表明是要评价一个... 查看详情
如何使用 tensorflow 微调训练好的模型和保存的模型？
】如何使用tensorflow微调训练好的模型和保存的模型？【英文标题】：Howtofinetuneatrainedmodelandsavedmodelwithtensorflow?【发布时间】：2021-10-0614:20:08【问题描述】：我有一个大数据集，我想通过这个数据集训练efficientnetb0，但是googlecolab... 查看详情
如何用tensorflow训练模型成pb文件和和如何加载已经训练好的模型文件
参考技术A基本使用使用TensorFlow,你必须明白TensorFlow:使用图(graph)来表示计算任务.在被称之为会话(Session)的上下文(context)中执行图.使用tensor表示数据.通过变量(Variable)维护状态.使用feed和fetch可以为任意的操作(arb... 查看详情