所有的操作是基於caffe的根目錄/caffe-master/來操作的:
在caffe框架中用訓練好的模型分類單張圖片需要用到classification.bin,本博客主要提供其源碼文件classification.cpp的註釋。
1、caffe提供了一個用已經訓練好的caffemodel來分類單張圖片的庫(./build/examples/cpp_classification/classification.bin),該庫的源碼爲文件./examples/cpp-classification/classification.cpp。
2、利用該庫的分類單張圖片的具體方法::
./build/examples/cpp_classification/classification.bin \
網絡結構文件:xx/xx/deploy.prototxt \
訓練的模型文件:xx/xx/xx.caffemodel \
訓練的圖像的均值文件:xx/xx/xx.binaryproto \
類別名稱標籤文件:xx/xx/synset_words.txt \
待測試圖像:xx/xx/xx.jpg
具體可見這位大牛的博客:http://www.cnblogs.com/denny402/p/5111018.html
下面記錄下我在看classification.cpp代碼時一些註釋,如有錯誤望指教:::
#include <caffe/caffe.hpp>
#ifdef USE_OPENCV
#include <opencv2/core/core.hpp>
#include <opencv2/highgui/highgui.hpp>
#include <opencv2/imgproc/imgproc.hpp>
#endif // USE_OPENCV
#include <algorithm>
#include <iosfwd>
#include <memory>
#include <string>
#include <utility>
#include <vector>
#ifdef USE_OPENCV
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_;
};
/*分類對象構造文件*/
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)); /*複製網絡結構*/
net_->CopyTrainedLayersFrom(trained_file); /*加載caffemodel,該函數在net.cpp中實現*/
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(); /*該網絡結構所要求的圖片輸入通道數*/
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()); /*輸入層需要的圖片寬高*/
/* Load the binaryproto mean file. */
SetMean(mean_file); /*加載均值文件*/
/* Load labels. */
std::ifstream labels(label_file.c_str()); /*加載標籤名稱文件*/
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]; /*檢查標籤個數與網絡的輸出結點個數是否一樣*/
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], 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); /*調用這個函數做分類*/
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); /*讀入均值文件在Io.cpp中實現*/
/* Convert from BlobProto to Blob<float> */
Blob<float> mean_blob;
mean_blob.FromProto(blob_proto); /*將讀入的均值文件轉成Blob對象*//*Blob類在Blob.hpp中定義*/
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();
} /*將均值圖像的每個通道圖像拷貝到channel中*/
/* Merge the separate channels into a single image. */
cv::Mat mean;
cv::merge(channels, mean); /*合併每個通道圖像*/
/* 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);
}
/*測試函數*/
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);/*沒太看懂,應該是一些縮放*/
/* Forward dimension change to all layers. */
net_->Reshape();
std::vector<cv::Mat> input_channels;
WrapInputLayer(&input_channels);/*對輸入層數據進行包裝*/
Preprocess(img, &input_channels); /*把傳入的測試圖像寫入到輸入層*/
net_->Forward(); /*網絡前向傳播:計算出該測試圖像屬於哪個每個類別的概率也就是最終的輸出層*/
/* Copy the output layer to a std::vector */
Blob<float>* output_layer = net_->output_blobs()[0]; /*將輸出層拷貝到向量*/
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;/*將輸入的圖像轉換成輸入層需要的圖像格式*/
cv::Mat sample_resized;
if (sample.size() != input_geometry_)
cv::resize(sample, sample_resized, input_geometry_); /*如果大小不一致則需要縮放*/
else
sample_resized = sample;
cv::Mat sample_float;
if (num_channels_ == 3)
sample_resized.convertTo(sample_float, CV_32FC3); /*將數據轉化成浮點型*/
else
sample_resized.convertTo(sample_float, CV_32FC1);
cv::Mat sample_normalized;
cv::subtract(sample_float, mean_, sample_normalized); /*應該是當前圖像減去均值圖像*/
/* 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); /*把測試的圖像通過之前的定義的wraper寫入到輸入層*/
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(int argc, char** argv) {
if (argc != 6) {
std::cerr << "Usage: " << argv[0]
<< " deploy.prototxt network.caffemodel"
<< " mean.binaryproto labels.txt img.jpg" << std::endl;
return 1;
}
::google::InitGoogleLogging(argv[0]);
string model_file = argv[1]; /*標識網絡結構的deploy.prototxt文件*/
string trained_file = argv[2]; /*訓練出來的模型文件caffemodel*/
string mean_file = argv[3]; /*均值.binaryproto文件*/
string label_file = argv[4]; /*標籤文件:標識類別的名稱*/
Classifier classifier(model_file, trained_file, mean_file, label_file); /*創建對象並初始化網絡、模型、均值、標籤各類對象*/
string file = argv[5]; /*傳入的待測試圖片*/
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); /*具體測試傳入的圖片並返回測試的結果:類別ID與概率值的Prediction類型數組*/
/* Print the top N predictions. *//*將測試的結果打印*/
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;
}
}
#else
int main(int argc, char** argv) {
LOG(FATAL) << "This example requires OpenCV; compile with USE_OPENCV.";
}
#endif // USE_OPENCV
感謝:::::http://blog.csdn.net/csyanbin/article/details/50877359