如果您想用C++调用Caffe,这里提供了一个CMAKE配置文件可以编译C++文件。以Caffe的例子imageNet分类来说,python调用的方法如下。这个代码加载模型,然后读取一张图片预测所属类别。[参考]
import numpy as np
import sys, os
caffe_root = '/home/XXX/software/caffe/' #你的Caffe目录
sys.path.insert(0, caffe_root + 'python')
import caffe
thisDir, _ = os.path.split(os.path.abspath(sys.argv[0]))
net_file=thisDir+'/data/deploy.prototxt'
caffe_model=thisDir+'/data/bvlc_reference_caffenet.caffemodel'
mean_file=thisDir+'/data/ilsvrc_2012_mean.npy'
net = caffe.Net(net_file,caffe_model,caffe.TEST)
transformer = caffe.io.Transformer({'data': net.blobs['data'].data.shape})
transformer.set_transpose('data', (2,0,1))
transformer.set_mean('data', np.load(mean_file).mean(1).mean(1))
transformer.set_raw_scale('data', 255)
transformer.set_channel_swap('data', (2,1,0))
im=caffe.io.load_image(thisDir+'/data/cat.jpg')
net.blobs['data'].data[...] = transformer.preprocess('data',im)
out = net.forward()
imagenet_labels_filename =thisDir+'/data/caffe_ilsvrc12/synset_words.txt'
labels = np.loadtxt(imagenet_labels_filename, str, delimiter='\t')
top_k = net.blobs['prob'].data[0].flatten().argsort()[-1:-6:-1]
for i in np.arange(top_k.size):
print top_k[i], labels[top_k[i]]
下面用C++调用。
main.cpp用模型路径等参数创建分类器,然后把读取的图片传给分类器获取类别结果:[参考]
#include <classifier.h>
#ifdef USE_OPENCV
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];
string trained_file = argv[2];
string mean_file = argv[3];
string label_file = argv[4];
Classifier classifier(model_file, trained_file, mean_file, label_file);
string file = argv[5];
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;
}
}
#else
int main(int argc, char** argv) {
LOG(FATAL) << "This example requires OpenCV; compile with USE_OPENCV.";
}
#endif // USE_OPENCV
分类器 classifier.h:
#ifndef _CLASSIFIER_H_
#define _CLASSIFIER_H_
#include <caffe/caffe.hpp>
#ifdef USE_OPENCV
#include <opencv2/core/core.hpp>
#include <opencv2/highgui/highgui.hpp>
#endif // USE_OPENCV
using namespace caffe; // NOLINT(build/namespaces)
/* Pair (label, confidence) representing a prediction. */
typedef std::pair<string, float> Prediction;
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;
}
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_;
};
#endif
classifier.cpp:
#include <classifier.h>
#ifdef USE_OPENCV
#include <opencv2/imgproc/imgproc.hpp>
#endif // USE_OPENCV
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.";
}
/* 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.";
}
配置文件:[参考]
cmake_minimum_required(VERSION 2.8)
project(classifier)
add_definitions("-DUSE_OPENCV")#源码里面有#ifdef USE_OPENCV这样的语句
set(Caffe_Root
/path/caffe#caffe目录,根据实际情况修改
)
set(Caffe_INCLUDE_DIRS
${Caffe_Root}/include
${Caffe_Root}/src
/usr/local/cuda/include
)
set(Caffe_LIBRARIES
caffe
boost_system
glog
)
#add_compile_options(-std=c++11)
find_package(OpenCV REQUIRED)
include_directories(
${Caffe_INCLUDE_DIRS}
${OpenCV_INCLUDE_DIRS}
${CMAKE_CURRENT_SOURCE_DIR}
)
link_directories(
${Caffe_Root}/build/lib
)
add_library(${PROJECT_NAME} #STATIC | SHARED | MODULE
${CMAKE_CURRENT_SOURCE_DIR}/classifier.cpp#把分类器编译成链接库
)
#target_link_libraries(${PROJECT_NAME}
# ${OpenCV_LIBS}
#)
add_executable(run main.cpp)#把main.cpp编译成可执行文件run
target_link_libraries(run
${PROJECT_NAME}
${OpenCV_LIBS}
${Caffe_LIBRARIES}
)
运行方法:
./run \
../data/deploy.prototxt \
../data/bvlc_reference_caffenet.caffemodel \
../data/ilsvrc_2012_mean.binaryproto \
../data/caffe_ilsvrc12/synset_words.txt \
../data/cat.jpg
data数据提取码: 8mcv 。