接口可以完全按照官网的分类cpp文件调用学习。
classification.cpp
#include <caffe/caffe.hpp>
#include <opencv2/core/core.hpp>
#include <opencv2/highgui/highgui.hpp>
#include <opencv2/imgproc/imgproc.hpp>
#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], 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);
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_->ForwardPrefilled();
/* 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_BGR2GRAY);
else if (img.channels() == 4 && num_channels_ == 1)
cv::cvtColor(img, sample, CV_BGRA2GRAY);
else if (img.channels() == 4 && num_channels_ == 3)
cv::cvtColor(img, sample, CV_BGRA2BGR);
else if (img.channels() == 1 && num_channels_ == 3)
cv::cvtColor(img, sample, CV_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(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;
}
}海康的星空下的巫师一个脚本：
/************************初始化网络**************************/
#include "caffe/caffe.hpp"
#include <string>
#include <vector>
using namespace caffe;
char *proto = "H:\\Models\\Caffe\\deploy.prototxt"; /* 加载CaffeNet的配置 */
Phase phase = TEST; /* or TRAIN */
Caffe::set_mode(Caffe::CPU);
// Caffe::set_mode(Caffe::GPU);
// Caffe::SetDevice(0);
//! Note: 后文所有提到的net，都是这个net
boost::shared_ptr< Net<float> > net(new caffe::Net<float>(proto, phase));
/************************加载已训练好的模型**************************/
char *model = "H:\\Models\\Caffe\\bvlc_reference_caffenet.caffemodel";
net->CopyTrainedLayersFrom(model);
/*******************读取模型中的每层的结构配置参数*************************/
char *model = "H:\\Models\\Caffe\\bvlc_reference_caffenet.caffemodel";
NetParameter param;
ReadNetParamsFromBinaryFileOrDie(model, ¶m);
int num_layers = param.layer_size();
for (int i = 0; i < num_layers; ++i)
{
// 结构配置参数:name，type，kernel size，pad，stride等
LOG(ERROR) << "Layer " << i << ":" << param.layer(i).name() << "\t" << param.layer(i).type();
if (param.layer(i).type() == "Convolution")
{
ConvolutionParameter conv_param = param.layer(i).convolution_param();
LOG(ERROR) << "\t\tkernel size: " << conv_param.kernel_size()
<< ", pad: " << conv_param.pad()
<< ", stride: " << conv_param.stride();
}
}
/************************读取图像均值**************************/
char *mean_file = "H:\\Models\\Caffe\\imagenet_mean.binaryproto";
Blob<float> image_mean;
BlobProto blob_proto;
const float *mean_ptr;
unsigned int num_pixel;
bool succeed = ReadProtoFromBinaryFile(mean_file, &blob_proto);
if (succeed)
{
image_mean.FromProto(blob_proto);
num_pixel = image_mean.count(); /* NCHW=1x3x256x256=196608 */
mean_ptr = (const float *) image_mean.cpu_data();
}
/************************根据指定数据，前向传播网络**************************/
//! Note: data_ptr指向已经处理好（去均值的，符合网络输入图像的长宽和Batch Size）的数据
void caffe_forward(boost::shared_ptr< Net<float> > & net, float *data_ptr)
{
Blob<float>* input_blobs = net->input_blobs()[0];
switch (Caffe::mode())
{
case Caffe::CPU:
memcpy(input_blobs->mutable_cpu_data(), data_ptr,
sizeof(float) * input_blobs->count());
break;
case Caffe::GPU:
cudaMemcpy(input_blobs->mutable_gpu_data(), data_ptr,
sizeof(float) * input_blobs->count(), cudaMemcpyHostToDevice);
break;
default:
LOG(FATAL) << "Unknown Caffe mode.";
}
net->ForwardPrefilled();
}
/*********************根据Feature层的名字获取其在网络中的Index******************/
//! Note: Net的Blob是指，每个层的输出数据，即Feature Maps
// char *query_blob_name = "conv1";
unsigned int get_blob_index(boost::shared_ptr< Net<float> > & net, char *query_blob_name)
{
std::string str_query(query_blob_name);
vector< string > const & blob_names = net->blob_names();
for( unsigned int i = 0; i != blob_names.size(); ++i )
{
if( str_query == blob_names[i] )
{
return i;
}
}
LOG(FATAL) << "Unknown blob name: " << str_query;
}
/*********************读取网络指定Feature层数据*****************/
//! Note: 根据CaffeNet的deploy.prototxt文件，该Net共有15个Blob，从data一直到prob
char *query_blob_name = "conv1"; /* data, conv1, pool1, norm1, fc6, prob, etc */
unsigned int blob_id = get_blob_index(net, query_blob_name);
boost::shared_ptr<Blob<float> > blob = net->blobs()[blob_id];
unsigned int num_data = blob->count(); /* NCHW=10x96x55x55 */
const float *blob_ptr = (const float *) blob->cpu_data();
/*********************根据文件列表，获取特征，并存为二进制文件*****************/
/*
主要包括三个步骤
生成文件列表，格式与训练用的类似，每行一个图像 包括文件全路径、空格、标签（没有的话，可以置0）
根据train_val或者deploy的prototxt，改写生成feat.prototxt 主要是将输入层改为image_data层，最后加上prob和argmax（为了输出概率和Top1/5预测标签）
根据指定参数，运行程序后会生成若干个二进制文件，可以用MATLAB读取数据，进行分析
根据Layer的名字获取其在网络中的Index
*/
//! Note: Layer包括神经网络所有层，比如，CaffeNet共有23层
// char *query_layer_name = "conv1";
unsigned int get_layer_index(boost::shared_ptr< Net<float> > & net, char *query_layer_name)
{
std::string str_query(query_layer_name);
vector< string > const & layer_names = net->layer_names();
for( unsigned int i = 0; i != layer_names.size(); ++i )
{
if( str_query == layer_names[i] )
{
return i;
}
}
LOG(FATAL) << "Unknown layer name: " << str_query;
}
/*********************读取指定Layer的权重数据*****************/
//! Note: 不同于Net的Blob是Feature Maps，Layer的Blob是指Conv和FC等层的Weight和Bias
char *query_layer_name = "conv1";
const float *weight_ptr, *bias_ptr;
unsigned int layer_id = get_layer_index(net, query_layer_name);
boost::shared_ptr<Layer<float> > layer = net->layers()[layer_id];
std::vector<boost::shared_ptr<Blob<float> >> blobs = layer->blobs();
if (blobs.size() > 0)
{
weight_ptr = (const float *) blobs[0]->cpu_data();
bias_ptr = (const float *) blobs[1]->cpu_data();
}
//! Note: 训练模式下，读取指定Layer的梯度数据，与此相似，唯一的区别是将cpu_data改为cpu_diff
/*********************修改某层的Weight数据*****************/
const float* data_ptr; /* 指向待写入数据的指针， 源数据指针*/
float* weight_ptr = NULL; /* 指向网络中某层权重的指针，目标数据指针*/
unsigned int data_size; /* 待写入的数据量 */
char *layer_name = "conv1"; /* 需要修改的Layer名字 */
unsigned int layer_id = get_layer_index(net, query_layer_name);
boost::shared_ptr<Blob<float> > blob = net->layers()[layer_id]->blobs()[0];
CHECK(data_size == blob->count());
switch (Caffe::mode())
{
case Caffe::CPU:
weight_ptr = blob->mutable_cpu_data();
break;
case Caffe::GPU:
weight_ptr = blob->mutable_gpu_data();
break;
default:
LOG(FATAL) << "Unknown Caffe mode";
}
caffe_copy(blob->count(), data_ptr, weight_ptr);
//! Note: 训练模式下，手动修改指定Layer的梯度数据，与此相似
// mutable_cpu_data改为mutable_cpu_diff，mutable_gpu_data改为mutable_gpu_diff
/*********************保存新的模型*****************/
char* weights_file = "bvlc_reference_caffenet_new.caffemodel";
NetParameter net_param;
net->ToProto(&net_param, false);
WriteProtoToBinaryFile(net_param, weights_file);
扫一扫
被折叠的 条评论
为什么被折叠?
到【灌水乐园】发言
