darknet获取某一层的输出

关注

原创最新推荐文章于 2026-04-13 16:17:31 发布 186 阅读 AI 写同款· GEO 优化 ›

yolov3--进行darknet_53输出以后从特征获取预测结果对darknet_53输出的特征层中取预测结果这是上一篇文章，darknet_53的主干网络：https://blog.youkuaiyun.com/weixin_44403602/article/details/116241877 接着上文，在完成darknet_53以后呢，会得到三个输出out,out2,out3，这是主干网络提取的特征，需要对这些特征进行预测处理。主要流程图就是下方所示啦： import torch import torch.nn as nn from collections import O 阅读详情

#include <iostream>
#include <fstream>
#include <string>
#include <opencv2/opencv.hpp>
#include "darknet.h"

image mat_to_image(cv::Mat mat)
{
    int w = mat.cols;
    int h = mat.rows;
    int c = mat.channels();
    image im = make_image(w, h, c);
    unsigned char *data = (unsigned char *)mat.data;
    int step = mat.step;
    for (int y = 0; y < h; ++y)
    {
        for (int k = 0; k < c; ++k)
        {
            for (int x = 0; x < w; ++x)
            {
                im.data[k * w * h + y * w + x] = data[y * step + x * c + k] / 255.0f;
            }
        }
    }
    return im;
}

int main(int argc, char **argv)
{
	char weight_file[255] = "../2.weights";
    char cfg_file[255] = "../yolov3-tiny.cfg";
    network *net = load_network_custom(cfg_file, weight_file, 0, 1);
    
    std::string name = "../6.jpg";
    cv::Mat img = cv::imread(name);
    cv::cvtColor(img, img, cv::COLOR_BGR2RGB);
    if(img.data == NULL) return 0;
    image im = mat_to_image(img);
    image sized = resize_image(im, (*net).w, (*net).h);
    float *X = sized.data;
    network_predict(*net, X);
    // 
    layer l = (*net).layers[0];
    cuda_pull_array(l.output_gpu, l.output, l.outputs*l.batch);
    //std::cout << l.outputs*l.batch << std::endl;
    std::ofstream ofs("../output.txt");
    for(int i = 0; i < 16; ++i) {
    	ofs << l.output[i] << std::endl;
    }
    ofs.close();
    
    return 0;
}