vs2013中可视化caffe某层的feature map

记录下自己的实验

#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>
#include <io.h>
#include <string>
#include <boost/algorithm/string.hpp>
#include <fstream>

#include "caffe/util/bbox_util.hpp"

#ifdef USE_OPENCV
using namespace caffe;  // NOLINT(build/namespaces)
using std::string;
using namespace boost;
using namespace std;
using namespace cv;
/* 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 int &input_mean_value1,
		const int &input_mean_value2,
		const int &input_mean_value3);

	std::vector<Prediction> Classify(const cv::Mat& img, int N = 5);
	cv::Mat visualize_featuremap(const cv::Mat& img, string layer_name);
	cv::Mat visualize_priorbox(const cv::Mat& img, vector<string> layer_names);

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:
	boost::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 int& input_mean_value1,
	const int& input_mean_value2,
	const int& input_mean_value3) {
#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. */
	//如果不指定均值文件，则默认使用均值代替
	/*transform_param{
	#mean_value : 104
	#mean_value : 117
	#mean_value : 123
	}*/
	if (mean_file != "")
	{
		SetMean(mean_file);
	}
	else
	{
		cv::Scalar channel_mean = cv::Scalar(input_mean_value1, input_mean_value2, input_mean_value3);
		std::cout << "mean_values:" << channel_mean << endl;
		mean_ = cv::Mat(input_geometry_, CV_32FC3, channel_mean);//????????????????????????????????????
		cv::Mat _mean;
		mean_.convertTo(_mean, CV_8UC3);
	}
}

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], static_cast<int>(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);

	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);
	std::cout << "mean_values:" << channel_mean << endl;
	mean_ = cv::Mat(input_geometry_, mean.type(), channel_mean);
	cv::Mat _mean;
	mean_.convertTo(_mean, CV_8UC3);
}

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);
	clock_t start_t = clock();
	net_->Forward();
	clock_t end_t = clock();
	float duration = float(end_t - start_t) / CLOCKS_PER_SEC;
	std::cout << "forward cost time " << duration << std::endl;

	/* 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.";
}

//可视化特征图
cv::Mat Classifier::visualize_featuremap(const cv::Mat& img, string layer_name)
{
	Blob<float>* input_layer = net_->input_blobs()[0];
	input_layer->Reshape(1, num_channels_, input_geometry_.height, input_geometry_.width);

	net_->Reshape();

	std::vector<cv::Mat> input_channels;
	WrapInputLayer(&input_channels);

	Preprocess(img, &input_channels);

	net_->Forward();


	std::cout << "网络中的Blobs名称为：\n";
	vector<boost::shared_ptr<Blob<float>>> blobs = net_->blobs();
	vector<string> blob_names = net_->blob_names();
	std::cout << blobs.size() << " " << blob_names.size() << std::endl;
	for (int i = 0; i<blobs.size(); i++){
		std::cout << blob_names[i] << " " << blobs[i]->shape_string() << std::endl;
	}
	std::cout << std::endl;



	assert(net_->has_blob(layer_name));
	cout << "提取的层名：" << layer_name << endl;
	boost::shared_ptr<Blob<float> >  conv1Blob = net_->blob_by_name(layer_name);
	std::cout << "测试图片的特征响应图的形状信息为：" << conv1Blob->shape_string() << std::endl;

	float maxValue = -10000000, minValue = 10000000;
	const float* tmpValue = conv1Blob->cpu_data();
	for (int i = 0; i<conv1Blob->count(); i++){
		maxValue = std::max(maxValue, tmpValue[i]);
		minValue = std::min(minValue, tmpValue[i]);
	}

	int width = conv1Blob->shape(3);  //响应图的高度	
	int height = conv1Blob->shape(2);  //响应图的宽度	
	int channel = conv1Blob->shape(1);  //通道数
	int num = conv1Blob->shape(0);      //个数	
	int imgHeight = (int)(1 + sqrt(channel))*height;
	int imgWidth = (int)(1 + sqrt(channel))*width;
	cv::Mat img(imgHeight, imgWidth, CV_8UC1, cv::Scalar(0));

	int kk = 0;
	for (int x = 0; x<imgHeight; x += height){
		for (int y = 0; y<imgWidth; y += width){
			if (kk >= channel)
				continue;
			cv::Mat roi = img(cv::Rect(y, x, width, height));
			for (int i = 0; i<height; i++){
				for (int j = 0; j<width; j++){
					float value = conv1Blob->data_at(0, kk, i, j);
					roi.at<uchar>(i, j) = (value - minValue) / (maxValue - minValue) * 255;
				}
			}
			kk++;
		}
	}
	return img;

}


int main(int argc, char** argv) {
	if (argc != 6) {
		std::cerr << "Usage: " << argv[0]
			<< " deploy.prototxt network.caffemodel"
			<< " mean.binaryproto testimg" << std::endl;
		return 1;
	}

	//::google::InitGoogleLogging(argv[0]);

	string model_file = argv[1];
	string trained_file = argv[2];
	string mean_file = argv[3];
	Classifier classifier(model_file, trained_file, mean_file, 104, 117, 123);

	string layer_str = argv[4];
	string file = argv[5];


	stringstream ss(layer_str);
	vector<string> layers;
	string item;
	while (getline(ss, item, ',')) {
		string ly = item.c_str();
		layers.push_back(ly);
	}


	cv::Mat img = cv::imread(file, -1);
	CHECK(!img.empty()) << "Unable to decode image " << file;


	string layer = layers[0];
    cv::Mat feature_map = classifier.visualize_featuremap(img, layer);
	imshow("feature_map", feature_map);
	//string save_path = "feature_out/"+layer + ".png";
	//imwrite(save_path, feature_map);
	//cout << "保存在" << save_path << endl;
	cv::waitKey(0);

}
#else
int main(int argc, char** argv) {
	LOG(FATAL) << "This example requires OpenCV; compile with USE_OPENCV.";
}
#endif  // USE_OPENCV

opencv显示出的featuremap如下：