【Caffe】Windows下调用生成的classification.exe单张图片分类错误问题

第一次更新：2017.10.25

本人环境：

1.Caffe工程已经编译好

2.Matlab接口可用

问题概述：

    在用Caffe自带的程序对图片进行分类时，Matlab接口下识别率与训练时test的准确率一致，但使用VS接口，即直接调用工程生成的Classification.exe时出错。对于同一张图片，Matlab和VS的分类结果不一致。

Classification 调用语句如下所示：

F:\caffe-master\Build\x64\Release\classification.exe F:\caffe-master\data\ORL_Alex\deploy.prototxt F:\caffe-master\data\ORL_Alex\ORL_alexnet__iter_20000.caffemodel F:\caffe-master\data\ORL_Alex\ORL_mean.binaryproto F:\caffe-master\data\ORL_Alex\label.txt F:\caffe-master\data\ORL_Alex\28p010.bmp

pause

分析原因：

    在Matlab接口例程中，对于图像的预处理步骤有：1.转换通道  2.减去均值   3.变换大小  4.Crop ，即对其进行位移变换和旋转变换，生成十张图片，输入网络进行前向计算。

    而在VS代码中，可以看到，缺少了 1、4两个步骤。

    减去均值的问题：减均值对网络的影响并不是非常大，将我们自己的均值文件改为caffe自带的均值文件，或是不减去均值文件，而是减去固定值，都没有特别大的影响，除非均值文件通道反了会有一丢丢影响

解决方法：

    我们需要在caffe的vs工程中，找到classification.CPP，对于下面函数进行修改。

void Classifier::Preprocess(const cv::Mat& img,std::vector<cv::Mat>* input_channels)

    具体是，在里面加入如下代码：

  cv::cvtColor(sample_normalized, sample_normalized, cv::COLOR_BGR2RGB);

    至于crop步骤，可以在工程外进行编写。

第二次更新：2018.3.9

贴上代码：

classification.cpp

#include <caffe/caffe.hpp>
//#define USE_OPENCV
//#include"head.h"


#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;

/* 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], 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);
	channel_mean[0] = 104.0070;
	channel_mean[1] = 116.6688;
	channel_mean[2] = 122.6789;
	mean_ = cv::Mat(input_geometry_, mean.type(), channel_mean);
	cv::imshow("mean", mean_ / 255);

	//mean_ = 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 if (img.channels() == 3 && num_channels_ == 3)
	//	  cv::cvtColor(img, sample, cv::COLOR_BGR2RGB);
	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::imshow("1", sample_float / 255);
	cv::subtract(sample_float, mean_, sample_normalized);

	cv::cvtColor(sample_normalized, sample_normalized, cv::COLOR_BGR2RGB);
	//sample_normalized = sample_normalized.t();

	//cv::imshow("2", sample_normalized / 255);

	//cv::waitKey(0);

	/* 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;
	}
	cv::waitKey(0);
}
#else
int main(int argc, char** argv) {
	LOG(FATAL) << "This example requires OpenCV; compile with USE_OPENCV.";
}
#endif  // USE_OPENCV

第三次更新 2018.3.12

参考该博客：http://blog.csdn.net/HelloHaibo/article/details/77761880

可以直接利用opencv3.4，调用caffe进行分类，然而依旧出现了分类错误的问题，解决方法依旧是，在加载图片之后，加上这么一句变换RGB通道的代码：

cv::cvtColor(img, img, cv::COLOR_BGR2RGB);

第四次更新 2018.4.2【总结】

①分到每一类的概率相等

解决办法：检查train_val.prototxt和deploy.prototxt中网络每一层对应的名称是否相同

（如果不相同，会出现该层在进行分类任务时的输出全为0，推测原因是发现层的名称不一样，所以在copy weight的时候没有copy过去，导致该层参数全部为0）

②分到每一类的概率不一样，且matlab的demo结果和调用VS中classification.exe的分类效果不一样（matlab分类正确）

原因：vs中预处理步骤和matlab的不一样

参考：http://blog.csdn.net/auntielee/article/details/78341806

③分到同一类

解决办法：检查训练时使用的lmdb文件，在生成的时候标签是否从0开始，以及分类时使用的label，是否从0开始