标签：layer pen cond 返回 复制 binary google 文档 getline
python输出activation map与层参数：https://blog.csdn.net/tina_ttl/article/details/51033660
caffe::Net文档：
https://caffe.berkeleyvision.org/doxygen/classcaffe_1_1Net.html#a6f6cf9d40637f7576828d856bb1b1826
caffe::Blob文档：
http://caffe.berkeleyvision.org/doxygen/classcaffe_1_1Blob.html
图像通道分离与合并cv::split() cv::merge()
https://blog.csdn.net/guduruyu/article/details/70837779
caffe官方提供的prediction代码
caffe提供了一个用已经训练好的caffemodel来分类单张图片的库(./build/examples/cpp_classification/classification.bin)，该库的源码为文件./examples/cpp-classification/classification.cpp
#include
#ifdef USE_OPENCV
#include
#include
#include #endif // USE_OPENCV
#include
#include
#include
#include string>
#include
#include
#ifdef USE_OPENCV
using namespace caffe; // NOLINT(build/namespaces)
using std::string;
/* Pair (label, confidence) representing a prediction. */
typedef std::pairstring, float> Prediction;
class Classifier {
public:
Classifier(const string& model_file,
const string& trained_file,
const string& mean_file,
const string& label_file);
std::vector Classify(const cv::Mat& img, int N = 5);
private:
void SetMean(const string& mean_file);
std::vectorfloat> Predict(const cv::Mat& img);
void WrapInputLayer(std::vector<:mat>* input_channels);
void Preprocess(const cv::Mat& img,
std::vector<:mat>* input_channels);
private:
shared_ptrfloat> > net_;
cv::Size input_geometry_;
int num_channels_;
cv::Mat mean_;
std::vectorstring> labels_;
};
/*分类对象构造文件*/
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 Netfloat>(model_file, TEST)); /*复制网络结构*/
net_->CopyTrainedLayersFrom(trained_file); /*加载caffemodel,该函数在net.cpp中实现*/
CHECK_EQ(net_->num_inputs(), 1) "Network should have exactly one input.";
CHECK_EQ(net_->num_outputs(), 1) "Network should have exactly one output.";
Blobfloat>* input_layer = net_->input_blobs()[0];
num_channels_ = input_layer->channels(); /*该网络结构所要求的图片输入通道数*/
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()); /*输入层需要的图片宽高*/
/* Load the binaryproto mean file. */
SetMean(mean_file); /*加载均值文件*/
/* Load labels. */
std::ifstream labels(label_file.c_str()); /*加载标签名称文件*/
CHECK(labels) "Unable to open labels file " label_file;
string line;
while (std::getline(labels, line))
labels_.push_back(string(line));
Blobfloat>* output_layer = net_->output_blobs()[0]; /*检查标签个数与网络的输出结点个数是否一样*/
CHECK_EQ(labels_.size(), output_layer->channels())
"Number of labels is different from the output layer dimension.";
}
static bool PairCompare(const std::pairfloat, int>& lhs,
const std::pairfloat, int>& rhs) {
return lhs.first > rhs.first;
}
/* Return the indices of the top N values of vector v. */
static std::vectorint> Argmax(const std::vectorfloat>& v, int N) {
std::vector<:pair>float, int> > pairs;
for (size_t i = 0; i i)
pairs.push_back(std::make_pair(v[i], i));
std::partial_sort(pairs.begin(), pairs.begin() + N, pairs.end(), PairCompare);
std::vectorint> result;
for (int i = 0; i i)
result.push_back(pairs[i].second);
return result;
}
/* Return the top N predictions. */
std::vector Classifier::Classify(const cv::Mat& img, int N) {
std::vectorfloat> output = Predict(img); /*调用这个函数做分类*/
N = std::minint>(labels_.size(), N);
std::vectorint> maxN = Argmax(output, N);
std::vector predictions;
for (int i = 0; i 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); /*读入均值文件在Io.cpp中实现*/
/* Convert from BlobProto to Blob*/
Blobfloat> mean_blob;
mean_blob.FromProto(blob_proto); /*将读入的均值文件转成Blob对象*//*Blob类在Blob.hpp中定义*/
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<:mat> channels;
float* data = mean_blob.mutable_cpu_data();
for (int i = 0; i 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();
} /*将均值图像的每个通道图像拷贝到channel中*/
/* Merge the separate channels into a single image. */
cv::Mat mean;
cv::merge(channels, mean); /*合并每个通道图像*/
/* 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);
}
/*测试函数*/
std::vectorfloat> Classifier::Predict(const cv::Mat& img) {
Blobfloat>* input_layer = net_->input_blobs()[0];
input_layer->Reshape(1, num_channels_,
input_geometry_.height, input_geometry_.width);/*没太看懂，应该是一些缩放*/
/* Forward dimension change to all layers. */
net_->Reshape();
std::vector<:mat> input_channels;
WrapInputLayer(&input_channels);/*对输入层数据进行包装*/
Preprocess(img, &input_channels); /*把传入的测试图像写入到输入层*/
net_->Forward(); /*网络前向传播：计算出该测试图像属于哪个每个类别的概率也就是最终的输出层*/
/* Copy the output layer to a std::vector */
Blobfloat>* output_layer = net_->output_blobs()[0]; /*将输出层拷贝到向量*/
const float* begin = output_layer->cpu_data();
const float* end = begin + output_layer->channels();
return std::vectorfloat>(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<:mat>* input_channels) {
Blobfloat>* 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 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<: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;/*将输入的图像转换成输入层需要的图像格式*/
cv::Mat sample_resized;
if (sample.size() != input_geometry_)
cv::resize(sample, sample_resized, input_geometry_); /*如果大小不一致则需要缩放*/
else
sample_resized = sample;
cv::Mat sample_float;
if (num_channels_ == 3)
sample_resized.convertTo(sample_float, CV_32FC3); /*将数据转化成浮点型*/
else
sample_resized.convertTo(sample_float, CV_32FC1);
cv::Mat sample_normalized;
cv::subtract(sample_float, mean_, sample_normalized); /*应该是当前图像减去均值图像*/
/* 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); /*把测试的图像通过之前的定义的wraper写入到输入层*/
CHECK(reinterpret_castfloat*>(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: " 0]
" deploy.prototxt network.caffemodel"
" mean.binaryproto labels.txt img.jpg" std::endl;
return 1;
}
::google::InitGoogleLogging(argv[0]);
string model_file = argv[1]; /*标识网络结构的deploy.prototxt文件*/
string trained_file = argv[2]; /*训练出来的模型文件caffemodel*/
string mean_file = argv[3]; /*均值.binaryproto文件*/
string label_file = argv[4]; /*标签文件:标识类别的名称*/
Classifier classifier(model_file, trained_file, mean_file, label_file); /*创建对象并初始化网络、模型、均值、标签各类对象*/
string file = argv[5]; /*传入的待测试图片*/
std::cout "---------- Prediction for "
" ----------" std::endl;
cv::Mat img = cv::imread(file, -1);
CHECK(!img.empty()) "Unable to decode image " file;
std::vector predictions = classifier.Classify(img); /*具体测试传入的图片并返回测试的结果：类别ID与概率值的Prediction类型数组*/
/* Print the top N predictions. *//*将测试的结果打印*/
for (size_t i = 0; i i) {
Prediction p = predictions[i];
std::cout fixed 4) " - \""
"\"" std::endl;
}
}
#else
int main(int argc, char** argv) {
LOG(FATAL) "This example requires OpenCV; compile with USE_OPENCV.";
}
#endif // USE_OPENCV
输出activation map代码
输出层参数代码
c++ caffe 输出 activation map 、 层参数
标签：layer pen cond 返回 复制 binary google 文档 getline
原文地址：https://www.cnblogs.com/zealousness/p/9638056.html