yolov4.cpp

// Tencent is pleased to support the open source community by making ncnn available.
//
// Copyright (C) 2020 THL A29 Limited, a Tencent company. All rights reserved.
//
// Licensed under the BSD 3-Clause License (the "License"); you may not use this file except
// in compliance with the License. You may obtain a copy of the License at
//
// https://opensource.org/licenses/BSD-3-Clause
//
// Unless required by applicable law or agreed to in writing, software distributed
// under the License is distributed on an "AS IS" BASIS, WITHOUT WARRANTIES OR
// CONDITIONS OF ANY KIND, either express or implied. See the License for the
// specific language governing permissions and limitations under the License.

#pragma warning(disable:4996)
#include "net.h"

#include <opencv2/core/core.hpp>
#include <opencv2/highgui/highgui.hpp>
#include <opencv2/imgproc/imgproc.hpp>

#if CV_MAJOR_VERSION >= 3
#include <opencv2/videoio/videoio.hpp>
#endif

#include <vector>

#include <stdio.h>

#define NCNN_PROFILING
#define YOLOV4_TINY //Using yolov4_tiny, if undef, using original yolov4

#ifdef NCNN_PROFILING
#include "benchmark.h"
#endif

struct Object
{
    cv::Rect_<float> rect;
    int label;
    float prob;
};

static int init_yolov4(ncnn::Net* yolov4, int* target_size)
{
    /* --> Set the params you need for the ncnn inference <-- */

    yolov4->opt.num_threads = 8; //You need to compile with libgomp for multi thread support

    yolov4->opt.use_vulkan_compute = true; //You need to compile with libvulkan for gpu support

    yolov4->opt.use_winograd_convolution = true;
    yolov4->opt.use_sgemm_convolution = true;
    yolov4->opt.use_int8_inference = true;
    //yolov4->opt.use_fp16_packed = true;
    //yolov4->opt.use_fp16_storage = true;
    //yolov4->opt.use_fp16_arithmetic = true;
    yolov4->opt.use_packing_layout = true;
    yolov4->opt.use_shader_pack8 = false;
    yolov4->opt.use_image_storage = false;

    /* --> End of setting params <-- */
    int ret = 0;

    // original pretrained model from https://github.com/AlexeyAB/darknet
    // the ncnn model https://drive.google.com/drive/folders/1YzILvh0SKQPS_lrb33dmGNq7aVTKPWS0?usp=sharing
    // the ncnn model https://github.com/nihui/ncnn-assets/tree/master/models
#ifdef YOLOV4_TINY
    const char* yolov4_param = "E:/ncnn/yolov4/yolov4-tiny-opt-int8.param";
    const char* yolov4_model = "E:/ncnn/yolov4/yolov4-tiny-opt-int8.bin";
    *target_size = 416;
#else
    const char* yolov4_param = "yolov4-opt.param";
    const char* yolov4_model = "yolov4-opt.bin";
    *target_size = 608;
#endif

    ret = yolov4->load_param(yolov4_param);
    if (ret != 0)
    {
        return ret;
    }

    ret = yolov4->load_model(yolov4_model);
    if (ret != 0)
    {
        return ret;
    }

    return 0;
}

static int detect_yolov4(const cv::Mat& bgr, std::vector<Object>& objects, int target_size, ncnn::Net* yolov4)
{
    int img_w = bgr.cols;
    int img_h = bgr.rows;

    ncnn::Mat in = ncnn::Mat::from_pixels_resize(bgr.data, ncnn::Mat::PIXEL_BGR2RGB, bgr.cols, bgr.rows, target_size, target_size);

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

    ncnn::Extractor ex = yolov4->create_extractor();

    ex.input("data", in);

    ncnn::Mat out;
    ex.extract("output", out);

    objects.clear();
    for (int i = 0; i < out.h; i++)
    {
        const float* values = out.row(i);

        Object object;
        object.label = values[0];
        object.prob = values[1];
        object.rect.x = values[2] * img_w;
        object.rect.y = values[3] * img_h;
        object.rect.width = values[4] * img_w - object.rect.x;
        object.rect.height = values[5] * img_h - object.rect.y;

        objects.push_back(object);
    }

    return 0;
}

static int draw_objects(const cv::Mat& bgr, const std::vector<Object>& objects, int is_streaming)
{
    static const char* class_names[] = { "background", "person", "bicycle",
                                        "car", "motorbike", "aeroplane", "bus", "train", "truck",
                                        "boat", "traffic light", "fire hydrant", "stop sign",
                                        "parking meter", "bench", "bird", "cat", "dog", "horse",
                                        "sheep", "cow", "elephant", "bear", "zebra", "giraffe",
                                        "backpack", "umbrella", "handbag", "tie", "suitcase",
                                        "frisbee", "skis", "snowboard", "sports ball", "kite",
                                        "baseball bat", "baseball glove", "skateboard", "surfboard",
                                        "tennis racket", "bottle", "wine glass", "cup", "fork",
                                        "knife", "spoon", "bowl", "banana", "apple", "sandwich",
                                        "orange", "broccoli", "carrot", "hot dog", "pizza", "donut",
                                        "cake", "chair", "sofa", "pottedplant", "bed", "diningtable",
                                        "toilet", "tvmonitor", "laptop", "mouse", "remote", "keyboard",
                                        "cell phone", "microwave", "oven", "toaster", "sink",
                                        "refrigerator", "book", "clock", "vase", "scissors",
                                        "teddy bear", "hair drier", "toothbrush"
    };

    cv::Mat image = bgr.clone();

    for (size_t i = 0; i < objects.size(); i++)
    {
        const Object& obj = objects[i];

        fprintf(stderr, "%d = %.5f at %.2f %.2f %.2f x %.2f\n", obj.label, obj.prob,
            obj.rect.x, obj.rect.y, obj.rect.width, obj.rect.height);

        cv::rectangle(image, obj.rect, cv::Scalar(255, 0, 0));

        char text[256];
        sprintf(text, "%s %.1f%%", class_names[obj.label], obj.prob * 100);

        int baseLine = 0;
        cv::Size label_size = cv::getTextSize(text, cv::FONT_HERSHEY_SIMPLEX, 0.5, 1, &baseLine);

        int x = obj.rect.x;
        int y = obj.rect.y - label_size.height - baseLine;
        if (y < 0)
            y = 0;
        if (x + label_size.width > image.cols)
            x = image.cols - label_size.width;

        cv::rectangle(image, cv::Rect(cv::Point(x, y), cv::Size(label_size.width, label_size.height + baseLine)),
            cv::Scalar(255, 255, 255), -1);

        cv::putText(image, text, cv::Point(x, y + label_size.height),
            cv::FONT_HERSHEY_SIMPLEX, 0.5, cv::Scalar(0, 0, 0));
    }

    cv::imshow("image", image);

    if (is_streaming)
    {
        cv::waitKey(1);
    }
    else
    {
        cv::waitKey(0);
    }

    return 0;
}

int main(int argc, char** argv)
{
    cv::Mat frame;
    std::vector<Object> objects;

    cv::VideoCapture cap;

    ncnn::Net yolov4;

    const char* devicepath;

    int target_size = 160;
    int is_streaming = 0;
    /*
    const char* imagepath = "E:/ncnn/yolov5/person.jpg";

    cv::Mat m = cv::imread(imagepath, 1);
    if (m.empty())
    {
        fprintf(stderr, "cv::imread %s failed\n", imagepath);
        return -1;
    }

    double start = GetTickCount();


    std::vector<Object> objects;
    detect_yolov5(m, objects);


    double end = GetTickCount();

    fprintf(stderr, "cost time:  %.5f\n ms", (end - start)/1000);

    draw_objects(m, objects);

    */
    int ret = init_yolov4(&yolov4, &target_size); //We load model and param first!
    if (ret != 0)
    {
        fprintf(stderr, "Failed to load model or param, error %d", ret);
        return -1;
    }

    cv::VideoCapture capture;
    capture.open(0);  //修改这个参数可以选择打开想要用的摄像头

    //cv::Mat frame;
    while (true)
    {
        capture >> frame;

        cv::Mat m = frame;

        double start = GetTickCount();


        std::vector<Object> objects;

        detect_yolov4(frame, objects, 160, &yolov4);


        double end = GetTickCount();

        fprintf(stderr, "cost time:  %.5f ms \n", (end - start-10));

        // imshow("外接摄像头", m);	//remember, imshow() needs a window name for its first parameter
        draw_objects(m, objects, 8);

        if (cv::waitKey(30) >= 0)
            break;
    }


    return 0;
}