基于caffe官方网站上面的代码做了一些修改, 去掉了处理leveldb的部分, 对lmdb部分代码做了小小的封装. 开始是想按照http://blog.csdn.net/lingerlanlan/article/details/39400375的方法做, 最终没没能搞定.
//TODO: add code for read image data from lmdb 20160323 19:03
#include <caffe/caffe.hpp>
#define USE_OPENCV
#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;
using std::cout;
using std::endl;
/* Pair (label, confidence) representing a prediction. */
//typedef std::pair<string, float> Prediction;
typedef std::pair<int, 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 = 1);//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_;
std::vector<int> labels_;
};
Classifier::Classifier(const string& model_file, const string& trained_file)
{
#ifdef CPU_ONLY
Caffe::set_mode(Caffe::CPU);
#else
Caffe::set_mode(Caffe::GPU);
#endif
/* Load the network. */
//jin 2016-03-21 18:12:27
//net_.reset(new Net<float>(model_file, TEST));
net_.reset(new Net<float>(model_file));
Caffe::set_phase(Caffe::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));
//
labels_.push_back(0);
labels_.push_back(1);
Blob<float>* output_layer = net_->output_blobs()[0];
CHECK_EQ(labels_.size(), output_layer->channels())
//CHECK_EQ(2, 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::sort(pairs.begin(), pairs.end(), PairCompare);
//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);
// std::cout << pairs[i].second << std::endl;
}
return result;
}
/* Return the top N predictions. */
std::vector<Prediction> Classifier::Classify(const cv::Mat& img, int N) {
std::vector<float> output = Predict(img);
// cout << "output.size=" << output.size() << endl;
//printf("%6.2f %6.2f\n");
//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;
}
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);
//jin:
// net_->Forward();
//const vector<shared_ptr<Layer<float> > > &layers = net_->layers();
//net_->ForwardFromTo(0, layers.size()-1);
net_->ForwardPrefilled();
/* Copy the output layer to a std::vector */
Blob<float>* output_layer = net_->output_blobs()[0]; //TODO 20160322 19:31
//Blob<float> *output_layer = net_->blob_by_name("prob");
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) {
//jin 20160323 16:30
cv::Mat channel(height, width, CV_32FC1, input_data);
//cv::Mat channel(height, width, CV_8UC1, 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);
//jin 20160323 16:32 divide sample_float by 256
sample_float = sample_float * 0.00390625; // 1/256
//jin 20160321 19:11:00
// 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);
cv::split(sample_float, *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(int argc, char** argv) {
if (argc != 4) {
std::cerr << "Usage: " << argv[0]
<< " deploy.prototxt network.caffemodel img.jpg" << std::endl;
//<< " mean.binaryproto labels.txt img.jpg" << std::endl;
return 1;
}
::google::InitGoogleLogging(argv[0]);
string model_file = argv[1];
string trained_file = argv[2];
// string mean_file = argv[3];
// string label_file = argv[4];
Classifier classifier(model_file, trained_file);
string file = argv[3];
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);
// std::cout << "predictions.size() = " << predictions.size() << std::endl;
/* 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;
}
}
#else
int main(int argc, char** argv) {
LOG(FATAL) << "This example requires OpenCV; compile with USE_OPENCV.";
}
#endif // USE_OPENCV