darknet之detection_layer源码分析

• 最关键的函数，以yolov1为例
• yolov1没有anchor，直接使用网络输出计算IOU

void forward_detection_layer(const detection_layer l, network_state state)
{
    // locations是cell的个数，yolov1是49
    int locations = l.side*l.side;
    int i,j;
    memcpy(l.output, state.input, l.outputs*l.batch*sizeof(float));
    //if(l.reorg) reorg(l.output, l.w*l.h, size*l.n, l.batch, 1);
    int b;
    // 如果需要，计算softmax
    if (l.softmax){
        for(b = 0; b < l.batch; ++b){
            int index = b*l.inputs;
            for (i = 0; i < locations; ++i) {
                int offset = i*l.classes;
                softmax(l.output + index + offset, l.classes, 1,
                        l.output + index + offset, 1);
            }
        }
    }
    // 后面的代码都在这个if里
    if(state.train){
        float avg_iou = 0;
        float avg_cat = 0;
        float avg_allcat = 0;
        float avg_obj = 0;
        float avg_anyobj = 0;
        int count = 0;
        *(l.cost) = 0;
        // yolov1 : l.inputs = 7*7*(5*2+20)
        int size = l.inputs * l.batch;
        memset(l.delta, 0, size * sizeof(float));
        for (b = 0; b < l.batch; ++b){
            int index = b*l.inputs;
            // 对每7*7*(5*2+20)个数据，后面的索引都是在一组7*7*(5*2+20)里说
            for (i = 0; i < locations; ++i) {
                int truth_index = (b*locations + i)*(1+l.coords+l.classes);
                // 索引0的值
                int is_obj = state.truth[truth_index];
                // l.n是框的个数
                for (j = 0; j < l.n; ++j) {
                    int p_index = index + locations*l.classes + i*l.n + j;
                    l.delta[p_index] = l.noobject_scale*(0 - l.output[p_index]);
                    *(l.cost) += l.noobject_scale*pow(l.output[p_index], 2);
                    avg_anyobj += l.output[p_index];
                }

                int best_index = -1;
                float best_iou = 0;
                float best_rmse = 20;

                // 如果当前cell没有目标，跳过
                if (!is_obj){
                    continue;
                }

                int class_index = index + i*l.classes;
                // 处理当前cell的20个类别
                for(j = 0; j < l.classes; ++j) {
                    // 类别在索引1到20
                    l.delta[class_index+j] = l.class_scale * (state.truth[truth_index+1+j] - l.output[class_index+j]);
                    *(l.cost) += l.class_scale * pow(state.truth[truth_index+1+j] - l.output[class_index+j], 2);
                    if(state.truth[truth_index + 1 + j]) avg_cat += l.output[class_index+j];
                    avg_allcat += l.output[class_index+j];
                }

                // 取21,22,23,24的x,y,w,h
                box truth = float_to_box(state.truth + truth_index + 1 + l.classes);
                truth.x /= l.side;
                truth.y /= l.side;

                for(j = 0; j < l.n; ++j){
                    // output先存完49组置信度和类别概率，再存98个框
                    int box_index = index + locations*(l.classes + l.n) + (i*l.n + j) * l.coords;
                    box out = float_to_box(l.output + box_index);
                    out.x /= l.side;
                    out.y /= l.side;

                    if (l.sqrt){
                        out.w = out.w*out.w;
                        out.h = out.h*out.h;
                    }

                    float iou  = box_iou(out, truth);
                    //iou = 0;
                    float rmse = box_rmse(out, truth);
                    if(best_iou > 0 || iou > 0){
                        if(iou > best_iou){
                            best_iou = iou;
                            best_index = j;
                        }
                    }else{
                        if(rmse < best_rmse){
                            best_rmse = rmse;
                            best_index = j;
                        }
                    }
                }

                if(l.forced){
                    if(truth.w*truth.h < .1){
                        best_index = 1;
                    }else{
                        best_index = 0;
                    }
                }
                // 迭代次数小于64000可触发随机事件
                if(l.random && *(state.net.seen) < 64000){
                    best_index = rand()%l.n;
                }

                int box_index = index + locations*(l.classes + l.n) + (i*l.n + best_index) * l.coords;
                int tbox_index = truth_index + 1 + l.classes;

                box out = float_to_box(l.output + box_index);
                out.x /= l.side;
                out.y /= l.side;
                if (l.sqrt) {
                    out.w = out.w*out.w;
                    out.h = out.h*out.h;
                }
                float iou  = box_iou(out, truth);

                //printf("%d,", best_index);
                // 置信度的索引，output的组成：49组类别，98个置信度,98个框
                int p_index = index + locations*l.classes + i*l.n + best_index;
                *(l.cost) -= l.noobject_scale * pow(l.output[p_index], 2);
                *(l.cost) += l.object_scale * pow(1-l.output[p_index], 2);
                avg_obj += l.output[p_index];
                l.delta[p_index] = l.object_scale * (1.-l.output[p_index]);

                if(l.rescore){
                    l.delta[p_index] = l.object_scale * (iou - l.output[p_index]);
                }

                l.delta[box_index+0] = l.coord_scale*(state.truth[tbox_index + 0] - l.output[box_index + 0]);
                l.delta[box_index+1] = l.coord_scale*(state.truth[tbox_index + 1] - l.output[box_index + 1]);
                l.delta[box_index+2] = l.coord_scale*(state.truth[tbox_index + 2] - l.output[box_index + 2]);
                l.delta[box_index+3] = l.coord_scale*(state.truth[tbox_index + 3] - l.output[box_index + 3]);
                if(l.sqrt){
                    l.delta[box_index+2] = l.coord_scale*(sqrt(state.truth[tbox_index + 2]) - l.output[box_index + 2]);
                    l.delta[box_index+3] = l.coord_scale*(sqrt(state.truth[tbox_index + 3]) - l.output[box_index + 3]);
                }

                *(l.cost) += pow(1-iou, 2);
                avg_iou += iou;
                ++count;
            }
        }

        // if(0)是什么鬼
        if(0){
            float* costs = (float*)xcalloc(l.batch * locations * l.n, sizeof(float));
            for (b = 0; b < l.batch; ++b) {
                int index = b*l.inputs;
                for (i = 0; i < locations; ++i) {
                    for (j = 0; j < l.n; ++j) {
                        int p_index = index + locations*l.classes + i*l.n + j;
                        costs[b*locations*l.n + i*l.n + j] = l.delta[p_index]*l.delta[p_index];
                    }
                }
            }
            int indexes[100];
            top_k(costs, l.batch*locations*l.n, 100, indexes);
            float cutoff = costs[indexes[99]];
            for (b = 0; b < l.batch; ++b) {
                int index = b*l.inputs;
                for (i = 0; i < locations; ++i) {
                    for (j = 0; j < l.n; ++j) {
                        int p_index = index + locations*l.classes + i*l.n + j;
                        if (l.delta[p_index]*l.delta[p_index] < cutoff) l.delta[p_index] = 0;
                    }
                }
            }
            free(costs);
        }


        *(l.cost) = pow(mag_array(l.delta, l.outputs * l.batch), 2);


        printf("Detection Avg IOU: %f, Pos Cat: %f, All Cat: %f, Pos Obj: %f, Any Obj: %f, count: %d\n", avg_iou/count, avg_cat/count, avg_allcat/(count*l.classes), avg_obj/count, avg_anyobj/(l.batch*locations*l.n), count);
        //if(l.reorg) reorg(l.delta, l.w*l.h, size*l.n, l.batch, 0);
    }
}