caffe MobileNet-yolov3 deploy.prototxt 以及调用代码

最新推荐文章于 2022-10-10 19:24:45 发布

原创

最新推荐文章于 2022-10-10 19:24:45 发布 · 517 阅读

0 ·

CC 4.0 BY-SA版权

文章标签：

#MobileNetyolov3

本文介绍了如何从test.prototxt修改得到deploy.prototxt，主要涉及修改输入层和删除detection层。同时提供了使用mobilenet_yolov3_deploy.prototx和caffemodel的调用代码。

deploy.prototxt 可经test.prototxt修改得到:
1.修改输入层

layer {
  name: "data"
  type: "Input"
  top: "data"
  input_param {
    shape {
      dim: 1
      dim: 3
      dim: 416
      dim: 416
    }
  }
}

2.删掉最后的detection层

layer {
  name: "detection_eval"
  type: "DetectionEvaluate"
  bottom: "detection_out"
  bottom: "label"
  top: "detection_eval"

  detection_evaluate_param {
    num_classes: 2
    background_label_id: 0
    overlap_threshold: 0.5
    evaluate_difficult_gt: false
  }
}

如图:

##########################################

以下为mobilenet_yolov3_deploy.prototx mobilenet_yolov3_deploy.caffemodel 调用代码

// This is a demo code for using a SSD model to do detection.
// The code is modified from examples/cpp_classification/classification.cpp.
// Usage:
//    ssd_detect [FLAGS] model_file weights_file list_file
//
// where model_file is the .prototxt file defining the network architecture, and
// weights_file is the .caffemodel file containing the network parameters, and
// list_file contains a list of image files with the format as follows:
//    folder/img1.JPEG
//    folder/img2.JPEG
// list_file can also contain a list of video files with the format as follows:
//    folder/video1.mp4
//    folder/video2.mp4
//
#define USE_OPENCV
#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 <iomanip>
#include <iosfwd>
#include <memory>
#include <string>
#include <utility>
#include <vector>

#ifdef USE_OPENCV

using namespace caffe;  // NOLINT(build/namespaces)
using namespace cv;
using namespace std;

class Detector {
public:
    Detector(const string& model_file,
             const string& weights_file,
             const string& mean_file,
             const string& mean_value);

    std::vector<vector<float> > Detect(const cv::Mat& img);

private:
    void SetMean(const string& mean_file, const string& mean_value);

    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_;
};

Detector::Detector(const string& model_file,
                   const string& weights_file,
                   const string& mean_file,
                   const string& mean_value) {
#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(weights_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

最低0.47元/天解锁文章