加载caffemodel做图像分类(windows+vs2013)

要根据已有caffemodel等文件进行图像分类,需要阅读classification.cpp文件,然后在此cpp文件基础上修改相应代码即可。

打开E:\study_materials\Caffe\caffe-master\caffe-master\windows根目录下的Caffe.sln,然后找到如图所示的cpp文件


解读此cpp文件,可参考网址:

http://m.blog.csdn.net/wanggao_1990/article/details/78118062

主要的调用函数

  Classifier classifier(model_file, trained_file, mean_file, label_file);
  //输入的待测图片
  string file = argv[5];
  cv::Mat img = cv::imread(file, -1);

  std::vector<Prediction> predictions = classifier.Classify(img);

实例运行1:用以训练好的模型进行图像分类

http://blog.csdn.net/shakevincent/article/details/52995253

http://blog.csdn.net/sinat_30071459/article/details/50974695

model下载地址:链接:http://pan.baidu.com/s/1hs3CF9y 密码:j7m4

该代码逐张读取文件夹下的图像并将分类结果显示在图像左上角,按任意键(除Esc键)进入下一张,按Esc键结束程序。

结果显示在左上角,有英文和中文两种标签可选,如果显示中文,需要使用Freetype库。

运行过程:
(前提:按 http://blog.csdn.net/Angela_qin/article/details/79429377 所述,配置好了相应属性)

vs2013上新建一个 Win32控制台应用程序空项目

1. 添加classification.cpp,内容如下:(基本是在源码基础上修改了一下)
#include <caffe/caffe.hpp>
#include <opencv2/core/core.hpp>
#include <opencv2/highgui/highgui.hpp>
#include <opencv2/imgproc/imgproc.hpp>
#include <algorithm>
#include <iosfwd>
#include <memory>
#include <string>
#include <utility>
#include <vector>

#include <iostream>  
#include <string>  
#include <sstream>  
#include "io.h"

#include "stdio.h"
#include "stdlib.h" 
#include "time.h" 
#include"caffe_layers_registry.hpp"

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);
	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.";
}
//获取路径path下的文件,并保存在files容器中  
void getFiles(string path, vector<string>& files)
{
	//文件句柄  
	long   hFile = 0;
	//文件信息  
	struct _finddata_t fileinfo;
	string p;
	if ((hFile = _findfirst(p.assign(path).append("\\*").c_str(), &fileinfo)) != -1)
	{
		do
		{
			if ((fileinfo.attrib &  _A_SUBDIR))
			{
				if (strcmp(fileinfo.name, ".") != 0 && strcmp(fileinfo.name, "..") != 0)
					getFiles(p.assign(path).append("\\").append(fileinfo.name), files);
			}
			else
			{
				files.push_back(p.assign(path).append("\\").append(fileinfo.name));
			}
		} while (_findnext(hFile, &fileinfo) == 0);
		_findclose(hFile);
	}
}

int main(int argc, char** argv) {
	string model_file("E:\\study_materials\\Caffe\\caffe-master\\caffe-master\\examples\\vehicle_type_recognition1\\model\\deploy.prototxt");
	string trained_file("E:\\study_materials\\Caffe\\caffe-master\\caffe-master\\examples\\vehicle_type_recognition1\\model\\type.caffemodel");
	string mean_file("E:\\study_materials\\Caffe\\caffe-master\\caffe-master\\examples\\vehicle_type_recognition1\\model\\type_mean.binaryproto");
	string label_file("E:\\study_materials\\Caffe\\caffe-master\\caffe-master\\examples\\vehicle_type_recognition1\\model\\labels.txt");
	string picture_path("E:\\study_materials\\Caffe\\caffe-master\\caffe-master\\examples\\vehicle_type_recognition1\\model\\type");

	Classifier classifier(model_file, trained_file, mean_file, label_file);
	vector<string> files;
	getFiles(picture_path, files);


	for (int i = 0; i < files.size(); i++)
	{
		clock_t start, finish;
		double   duration;
		start = clock();
		cv::Mat img = cv::imread(files[i], -1);
		cv::Mat img2;

		std::vector<Prediction> predictions = classifier.Classify(img);
		//Prediction p = predictions[i];

		IplImage* show;
		CvSize sz;
		sz.width = img.cols;
		sz.height = img.rows;
		float scal = 0;
		scal = sz.width > sz.height ? (300.0 / (float)sz.height) : (300.0 / (float)sz.width);
		sz.width *= scal;
		sz.height *= scal;
		resize(img, img2, sz, 0, 0, CV_INTER_LINEAR);
		show = cvCreateImage(sz, IPL_DEPTH_8U, 3);
		cvCopy(&(IplImage)img2, show);
		CvFont font;
		cvInitFont(&font, CV_FONT_HERSHEY_COMPLEX, 0.5, 0.5, 0, 1, 8);  //初始化字体  
		//cvPutText(show, text.c_str(), cvPoint(10, 30), &font, cvScalar(0, 0, 255, NULL));
		string name_text;
		name_text = files[i].substr(files[i].find_last_of("\\") + 1);
		name_text = "Test picture ID::" + name_text;
		cvPutText(show, name_text.c_str(), cvPoint(10, 130), &font, cvScalar(0, 0, 255, NULL));
		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;
			string text = p.first;
			char buff[20];
			_gcvt(p.second, 4, buff);
			text = text + ":" + buff;

			/***************************输出英文标签*****************************************/

			//CvFont font;
			//cvInitFont(&font, CV_FONT_HERSHEY_COMPLEX, 0.5, 0.5, 0, 1, 8);  //初始化字体  
			//cvPutText(show, text.c_str(), cvPoint(10, 30), &font, cvScalar(0, 0, 255, NULL));
			//string name_text;
			cvPutText(show, text.c_str(), cvPoint(10, 30 + i * 20), &font, cvScalar(0, 0, 255, NULL));

			/**********************************************************************************/

			cvNamedWindow("结果");
			cvShowImage("结果", show);
			cvWaitKey(1);

		}
		finish = clock();
		duration = (double)(finish - start) / CLOCKS_PER_SEC;
		printf("Time to do is ::");
		printf("%f seconds\n", duration);
		int c = cvWaitKey();
		cvDestroyWindow("结果");
		cvReleaseImage(&show);
		std::cout << "///" << std::endl;
		if (c == 27)
		{
			return 0;
		}
	}
	return 0;
}
2.  添加caffe_layers_registry.hpp,内容如下:(必须要对各层进行注册,否则会报错,所以必须要这个头文件)
#include <caffe/common.hpp>
#include "caffe/layers/input_layer.hpp"  
#include "caffe/layers/inner_product_layer.hpp"  
#include "caffe/layers/dropout_layer.hpp"  
#include "caffe/layers/conv_layer.hpp"  
#include "caffe/layers/relu_layer.hpp"  
#include "caffe/layers/prelu_layer.hpp"  

#include "caffe/layers/pooling_layer.hpp"  
#include "caffe/layers/lrn_layer.hpp"  
#include "caffe/layers/softmax_layer.hpp"  
#include "caffe/layers/flatten_layer.hpp"
#include "caffe/layers/concat_layer.hpp"
#include "caffe/layers/reshape_layer.hpp"
#include "caffe/layers/softmax_layer.hpp"
#include "caffe/layers/rpn_layer.hpp"
#include "caffe/layers/roi_pooling_layer.hpp"
#include "caffe/layers/frcnn_proposal_layer.hpp""

namespace caffe
{
	namespace Frcnn{
		extern INSTANTIATE_CLASS(FrcnnProposalLayer);
		REGISTER_LAYER_CLASS(FrcnnProposal);
	}
	extern INSTANTIATE_CLASS(InputLayer);
	REGISTER_LAYER_CLASS(Input);

	extern INSTANTIATE_CLASS(SplitLayer);
	REGISTER_LAYER_CLASS(Split);

	extern INSTANTIATE_CLASS(ConvolutionLayer);
	REGISTER_LAYER_CLASS(Convolution);

	extern INSTANTIATE_CLASS(InnerProductLayer);
	REGISTER_LAYER_CLASS(InnerProduct);

	extern INSTANTIATE_CLASS(DropoutLayer);
	REGISTER_LAYER_CLASS(Dropout);

	extern INSTANTIATE_CLASS(ReLULayer);
	REGISTER_LAYER_CLASS(ReLU);

	extern INSTANTIATE_CLASS(PReLULayer);
	REGISTER_LAYER_CLASS(PReLU);

	extern INSTANTIATE_CLASS(PoolingLayer);
	REGISTER_LAYER_CLASS(Pooling);

	extern INSTANTIATE_CLASS(LRNLayer);
	REGISTER_LAYER_CLASS(LRN);

	extern INSTANTIATE_CLASS(SoftmaxLayer);
	REGISTER_LAYER_CLASS(Softmax);

	extern INSTANTIATE_CLASS(RPNLayer);
	REGISTER_LAYER_CLASS(RPN);

	extern INSTANTIATE_CLASS(ROIPoolingLayer);
	REGISTER_LAYER_CLASS(ROIPooling);

	extern INSTANTIATE_CLASS(FlattenLayer);
	REGISTER_LAYER_CLASS(Flatten);

	extern INSTANTIATE_CLASS(ConcatLayer);
	REGISTER_LAYER_CLASS(Concat);

	extern INSTANTIATE_CLASS(ReshapeLayer);
	REGISTER_LAYER_CLASS(Reshape);


}

编译运行,结果如下图所示:


实例运行2:用自己训练的模型进行图像分类

Trick:Classifier classifier(model_file, trained_file, mean_file, label_file);
主要是修改这四个参数即可实现对不同模型的分类

参考资料

https://www.cnblogs.com/k7k8k91/p/7806232.html

根据我的博文“用已有模型进行微调finetune”,在“..\mydata1”根目录下新建文件deploy.prototxt

1. model_file: :生成deploy.prototxt(train_val.prototxt修改而得)
1)头部:

打开根目录下的train_val.prototxt文件,删除训练用的输入数据层,即前两个layer内容(训练阶段和测试阶段),如下图所示。



并添加:

layer {
  name: "data"
  type: "Input"
  top: "data"
  input_param { shape: { dim: 1 dim: 3 dim: 224 dim: 224 } }

}

2)中间层内容保持不变
3)尾部

删除最后两个layer(Accuracy 和 SoftmaxWithLoss),如下图所示。

并添加:

layer {
  name: "prob"
  type: "Softmax"
  bottom: "fc8"
  top: "prob"
}

二、label_file:生成labels.txt,内容如下图所示。

三、trained_file, mean_file

分别是 caffenet_train_iter_1000.caffemodel 和 modelre_train_mean.binaryproto


四、存放需要测试的图片

..\mydata1根目录下新建文件夹type,存放需要测试的图片


四个参数修改并新建了文件夹type之后,就可以成功运行了!!!

  • 2
    点赞
  • 1
    收藏
    觉得还不错? 一键收藏
  • 1
    评论

“相关推荐”对你有帮助么?

  • 非常没帮助
  • 没帮助
  • 一般
  • 有帮助
  • 非常有帮助
提交
评论 1
添加红包

请填写红包祝福语或标题

红包个数最小为10个

红包金额最低5元

当前余额3.43前往充值 >
需支付:10.00
成就一亿技术人!
领取后你会自动成为博主和红包主的粉丝 规则
hope_wisdom
发出的红包
实付
使用余额支付
点击重新获取
扫码支付
钱包余额 0

抵扣说明:

1.余额是钱包充值的虚拟货币,按照1:1的比例进行支付金额的抵扣。
2.余额无法直接购买下载,可以购买VIP、付费专栏及课程。

余额充值