yolo_layer.c

...

box get_yolo_box(float *x, float *biases, int n, int index, int i, int j, int lw, int lh, int w, int h, int stride)

/*

输入参数解析：(*x 预测数据),(*biases 存放anchor数据),

(i、j 对应在feature map上的坐标),

(n 表示anchor数组的mask,为了让三个yolo_layer能取到自己对应的三组anchor, 小尺寸feature map对应大size anchor，比较好理解小尺寸特征图负责检查大尺寸目标),

(index,当前bbox对应的数据的起始下标),

(lw lh,特征图的w h),

(w h, 网络输入的w h),

(同一个bbox数据之间的stride lw*lh)

*/

{

    box b; // 网络为了每一个bbox都给出了4个坐标预测值: tx ty tw ty

    /*

    其中tx 和 ty是相对于当前feature map坐标的偏移

    除以lw&&lh 是计算出bbox坐标在图像中的比例

    */

    b.x = (i + x[index + 0*stride]) / lw;

    b.y = (j + x[index + 1*stride]) / lh;

    /*

    e^tw * biases[2*n] 表示学习到的w回归值和对应prior bbox(anchor) w的乘积得到

    bbox在网络输入size基础上的w size, 除以 net_w得到相对于网络输入图像的比例

    h的计算同理, 这部分的内容涉及到yolov3论文中的图二

    */

    b.w = exp(x[index + 2*stride]) * biases[2*n]   / w;

    b.h = exp(x[index + 3*stride]) * biases[2*n+1] / h;

    return b;

    /*补充一下，这里算出的x,y,w,h都是相对于net input size的比例*/

}
此不分为转载：

https://blog.csdn.net/wwwhp/article/details/84718089

...

int get_yolo_detections(layer l, int w, int h, int netw, int neth, float thresh, int *map, int relative, detection *dets)

{

    int i,j,n;

    float *predictions = l.output;

    if (l.batch == 2) avg_flipped_yolo(l);

    int count = 0;

    for (i = 0; i < l.w*l.h; ++i){

        int row = i / l.w;

        int col = i % l.w;

    //printf("get_yolo_detections:i =%d,row = i / l.w=%d, col = i % l.w;\n",i, row, col);

        for(n = 0; n < l.n; ++n){

            int obj_index  = entry_index(l, 0, n*l.w*l.h + i, 4);

            float objectness = predictions[obj_index];//objectness：有框的

        //printf("objectness:%f\n",objectness);

            if(objectness <= thresh) continue;

        printf("obj_index = %d,objectness:%f, thresh:%f\n",obj_index,objectness,thresh);

            int box_index  = entry_index(l, 0, n*l.w*l.h + i, 0);

            dets[count].bbox = get_yolo_box(predictions, l.biases, l.mask[n], box_index, col, row, l.w, l.h, netw, neth, l.w*l.h);//模型推理出偏移量

            dets[count].objectness = objectness;

            dets[count].classes = l.classes;

            for(j = 0; j < l.classes; ++j){

                int class_index = entry_index(l, 0, n*l.w*l.h + i, 4 + 1 + j);

                float prob = objectness*predictions[class_index];//predictions[class_index]：框中物体是class的概率，prob：置信度

        printf("get_yolo_detections1:prob=objectness*predictions[class_index] = %f * predictions[%d] = %f * %f = %f;\n",objectness,class_index,objectness,predictions[class_index],prob);

                dets[count].prob[j] = (prob > thresh) ? prob : 0;

        printf("get_yolo_detections2:[dets[count].prob[j] = (prob > thresh) ? prob : 0] = [ %f = (%f > %f) ? %f : 0];\n",dets[count].prob[j],prob,thresh,prob);

            }

            ++count;

        }

    }

    correct_yolo_boxes(dets, count, w, h, netw, neth, relative);

    return count;

}

...