detail | 详细描述 | 詳細な説明

环境：
使用的版本是ncnn-20240102-android-vulkan

用profiler定位大致位置在stride 8, 16, 32 抽取特征时，
ex.extract("output", out);
ex.extract("771", out);
ex.extract("791", out);

native部分可以在10分钟左右从200多m增长到800多m

代码详情（借用了nihui大神写的ncnn-android-yolov5）

static int detect_yolov5(const cv::Mat& bgr, std::vector<Object>& objects, ncnn::Net& yolov5, const float& prob_threshold)
{
    const int target_size = 640;
//    const float prob_threshold = 0.25f;
    const float nms_threshold = 0.45f;

    int img_w = bgr.cols;
    int img_h = bgr.rows;

    // letterbox pad to multiple of 32
    int w = img_w;
    int h = img_h;
    float scale = 1.f;
    if (w > h)
    {
        scale = (float)target_size / w;
        w = target_size;
        h = h * scale;
    }
    else
    {
        scale = (float)target_size / h;
        h = target_size;
        w = w * scale;
    }

    ncnn::Mat in = ncnn::Mat::from_pixels_resize(bgr.data, ncnn::Mat::PIXEL_BGR2RGB, img_w, img_h, w, h);

    // pad to target_size rectangle
    // yolov5/utils/datasets.py letterbox
    int wpad = (w + 31) / 32 * 32 - w;
    int hpad = (h + 31) / 32 * 32 - h;
    ncnn::Mat in_pad;
    ncnn::copy_make_border(in, in_pad, hpad / 2, hpad - hpad / 2, wpad / 2, wpad - wpad / 2, ncnn::BORDER_CONSTANT, 114.f);

    const float norm_vals[3] = {1 / 255.f, 1 / 255.f, 1 / 255.f};
    in_pad.substract_mean_normalize(0, norm_vals);

    ncnn::Extractor ex = yolov5.create_extractor();
    ex.set_blob_allocator(&g_blob_pool_allocator);
    ex.set_workspace_allocator(&g_workspace_pool_allocator);

    ex.input("images", in_pad);

    std::vector<Object> proposals;

    // anchor setting from yolov5/models/yolov5s.yaml

    // stride 8
    {
        ncnn::Mat out;
        ex.extract("output", out);

        ncnn::Mat anchors(6);
        anchors[0] = 10.f;
        anchors[1] = 13.f;
        anchors[2] = 16.f;
        anchors[3] = 30.f;
        anchors[4] = 33.f;
        anchors[5] = 23.f;

        std::vector<Object> objects8;
        generate_proposals(anchors, 8, in_pad, out, prob_threshold, objects8);

        proposals.insert(proposals.end(), objects8.begin(), objects8.end());
    }

    // stride 16
    {
        ncnn::Mat out;
        ex.extract("771", out); 

        ncnn::Mat anchors(6);
        anchors[0] = 30.f;
        anchors[1] = 61.f;
        anchors[2] = 62.f;
        anchors[3] = 45.f;
        anchors[4] = 59.f;
        anchors[5] = 119.f;

        std::vector<Object> objects16;
        generate_proposals(anchors, 16, in_pad, out, prob_threshold, objects16);

        proposals.insert(proposals.end(), objects16.begin(), objects16.end());
    }

    // stride 32
    {
        ncnn::Mat out;
        ex.extract("791", out);

        ncnn::Mat anchors(6);
        anchors[0] = 116.f;
        anchors[1] = 90.f;
        anchors[2] = 156.f;
        anchors[3] = 198.f;
        anchors[4] = 373.f;
        anchors[5] = 326.f;

        std::vector<Object> objects32;
        generate_proposals(anchors, 32, in_pad, out, prob_threshold, objects32);

        proposals.insert(proposals.end(), objects32.begin(), objects32.end());
    }

    // sort all proposals by score from highest to lowest
    qsort_descent_inplace(proposals);

    // apply nms with nms_threshold
    std::vector<int> picked;
    nms_sorted_bboxes(proposals, picked, nms_threshold);

    int count = picked.size();

    objects.resize(count);
    for (int i = 0; i < count; i++)
    {
        objects[i] = proposals[picked[i]];

        // adjust offset to original unpadded
        float x0 = (objects[i].rect.x - (wpad / 2)) / scale;
        float y0 = (objects[i].rect.y - (hpad / 2)) / scale;
        float x1 = (objects[i].rect.x + objects[i].rect.width - (wpad / 2)) / scale;
        float y1 = (objects[i].rect.y + objects[i].rect.height - (hpad / 2)) / scale;

        // clip
        x0 = std::max(std::min(x0, (float)(img_w - 1)), 0.f);
        y0 = std::max(std::min(y0, (float)(img_h - 1)), 0.f);
        x1 = std::max(std::min(x1, (float)(img_w - 1)), 0.f);
        y1 = std::max(std::min(y1, (float)(img_h - 1)), 0.f);

        objects[i].rect.x = x0;
        objects[i].rect.y = y0;
        objects[i].rect.width = x1 - x0;
        objects[i].rect.height = y1 - y0;
    }

    return 0;
}
// 模型初始化部分

JNIEXPORT jboolean JNICALL Java_com_tencent_yolov5ncnn_YoloV5Ncnn_Init(JNIEnv* env, jobject thiz, jobject assetManager)
{
    g_blob_pool_allocator.set_size_compare_ratio(0.f);
    g_workspace_pool_allocator.set_size_compare_ratio(0.f);

    ncnn::Option opt;
    opt.lightmode = true;
    opt.num_threads = 4;
    opt.blob_allocator = &g_blob_pool_allocator;
    opt.workspace_allocator = &g_workspace_pool_allocator;
    opt.use_packing_layout = true;

    // use vulkan compute
    if (ncnn::get_gpu_count() != 0)
        opt.use_vulkan_compute = true;

    AAssetManager* mgr = AAssetManager_fromJava(env, assetManager);

    yolov5.opt = opt;

    yolov5.register_custom_layer("YoloV5Focus", YoloV5Focus_layer_creator);
    ....
    return JNI_TRUE;
}