#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;

}

}

深度学习caffe测试代码c++的更多相关文章

  1. 人工智能深度学习Caffe框架介绍,优秀的深度学习架构

    人工智能深度学习Caffe框架介绍,优秀的深度学习架构 在深度学习领域,Caffe框架是人们无法绕过的一座山.这不仅是因为它无论在结构.性能上,还是在代码质量上,都称得上一款十分出色的开源框架.更重要 ...

  2. win7 配置微软的深度学习caffe

    win7 配置微软的深度学习caffe   官方下载: https://github.com/Microsoft/caffe 然后 直接修改caffe目录下的windows目录下的项目的props文件 ...

  3. 【机器学习PAI实践十】深度学习Caffe框架实现图像分类的模型训练

    背景 我们在之前的文章中介绍过如何通过PAI内置的TensorFlow框架实验基于Cifar10的图像分类,文章链接:https://yq.aliyun.com/articles/72841.使用Te ...

  4. 10K+,深度学习论文、代码最全汇总!

    我们大部分人是如何查询和搜集深度学习相关论文的?绝大多数情况是根据关键字在谷歌.百度搜索.想寻找相关论文的复现代码又会去 GitHub 上搜索关键词.浪费了很多时间不说,论文.代码通常也不够完整.怎么 ...

  5. 学习《精通数据科学从线性回归到深度学习》PDF+代码分析

    数据科学内容广泛,涉及到统计分析.机器学习以及计算机科学三方面的知识和技能.学习数据科学,推荐学习<精通数据科学从线性回归到深度学习>. 针对技术书籍,最好的阅读方法是对照每一章的示例代码 ...

  6. 对比学习:《深度学习之Pytorch》《PyTorch深度学习实战》+代码

    PyTorch是一个基于Python的深度学习平台,该平台简单易用上手快,从计算机视觉.自然语言处理再到强化学习,PyTorch的功能强大,支持PyTorch的工具包有用于自然语言处理的Allen N ...

  7. 对比《动手学深度学习》 PDF代码+《神经网络与深度学习 》PDF

    随着AlphaGo与李世石大战的落幕,人工智能成为话题焦点.AlphaGo背后的工作原理"深度学习"也跳入大众的视野.什么是深度学习,什么是神经网络,为何一段程序在精密的围棋大赛中 ...

  8. 学习《深度学习与计算机视觉算法原理框架应用》《大数据架构详解从数据获取到深度学习》PDF代码

    <深度学习与计算机视觉 算法原理.框架应用>全书共13章,分为2篇,第1篇基础知识,第2篇实例精讲.用通俗易懂的文字表达公式背后的原理,实例部分提供了一些工具,很实用. <大数据架构 ...

  9. 深度学习-Caffe编译测试的小总结

    1. 搭建的环境和代码:win7 64bit + vs2013+CUDA7.5 http://blog.csdn.net/thesby/article/details/50880802 2. 编译,制 ...

随机推荐

  1. lua --- 点号 和 冒号

    冒号的作用:1.定义函数时,给函数添加隐藏的第一个参数 self2.调用函数时,默认把当前调用者作为第一个参数传递进去 如 a:b(c) 可以理解为 a.b(a, c) 以下是用点号的定义和调用函数的 ...

  2. jenkins之从0到1利用Git和Ant插件打war包并自动部署到tomcat(第二话):安装插件,配置JDK、Git、Ant

    jenkins之所以这么强大,离不开丰富的插件库. 要确保jenkins上安装好Git plugin.GitHub plugin.AntPlugin插件,一般在启动jenkins时默认安装的插件中就包 ...

  3. Synergy软件的基本配置/使用(详细教程)

    1.Synergy软件的简介 Synergy是一款可让多台电脑共享一个鼠标与键盘的软件,用户可借助Synergy操作一个鼠标与键盘控制多个电脑…… 2.Synergy软件的配置过程 下载链接:计算机相 ...

  4. 在mk/rte.app.mk 256行加echo $(O_TO_EXE_DO)查看GCC参数

    在mk/rte.app.mk 256行加echo $(O_TO_EXE_DO)查看GCC参数,如:

  5. 完整的Django入门指南学习笔记3

    前言 在本节课中,我们将深入理解两个基本概念: URLs 和 Forms.在这个过程中,我们还将学习其它很多概念,如创建可重用模板和安装第三方库.同时我们还将编写大量单元测试. 如果你是从这个系列教程 ...

  6. [Fiddler] ReadResponse() failed: The server did not return a complete response for this request. Server returned 0 bytes.

    待解决 [Fiddler] ReadResponse() failed: The server did not return a complete response for this request. ...

  7. 485. Max Consecutive Ones最大连续1的个数

    网址:https://leetcode.com/problems/max-consecutive-ones/ 很简单的一题 class Solution { public: int findMaxCo ...

  8. 2017-6-6&6-8/大型网站架构总结

    一.WikiPedia(维基百科) WikiPedia是非盈利网站,因此尽可能地使用免费的软件和廉价的服务器.截止到2012年,这个只有区区数百台服务器和十余个技术人员开发.维护的网站,成为流量全球排 ...

  9. 2017-4-13/MySQL

    1. mysql一般的连接方式都有哪些,各自优缺点. MySQL:过程式风格,最常用. MySQLi:MySQL的增强扩展,提供了过程化和面向对象两种风格的API,增加了预编译和参数绑定等新特性, 但 ...

  10. A Bug's Life(向量偏移)

    A Bug's Life Time Limit : 15000/5000ms (Java/Other)   Memory Limit : 32768/32768K (Java/Other) Total ...