使用ncnn在树莓派部署自己的yolov5lites模型

使用ncnn在树莓派部署自己的yolov5lites模型

---

---

前言

记录一下入门小白的树莓派部署记录，前前后后走过不少坑。

一、windows10上训练自己的yolov5lites模型

1 下载yolov5lites源码

git clone https://github.com/ppogg/YOLOv5-Lite.git

2 配置yolov5lites运行环境

默认你在windows10上已经会配置环境，由于我本身已经配置好torch=1.7,torchvision=0.8，对应的cuda版本为11.0，还有对应的cudnn版本以及显卡驱动，我就在此环境下进行训练。并使用requirements.txt里的依赖(不需要重新配置相应的cuda以及cudnn)进行.onnx的导出

pip install -r requirements.txt

3 修改参数进行yolov5lites的训练

这一部分是记录转换xml格式为txt文件以及yolov5lites训练自己的模型等所需要的准备工作。

3.1 修改.yaml文件

为自己的训练种类以及个数

3.2 修改输入为[320,320]

将下载的v5lite-s.pt文件放在创建的weights/文件夹下。

3.3 进行训练

点击train.py，训练保存的权重在runs文件夹下

3.4 生成先验框

使用autoanchor.py，将生成的数据保存到v5lites.yaml
自己手动添加到对应的是C:\Users\jxbj2\Desktop\yolov5lite\YOLOv5-Lite-master\models\v5lite-s.yaml

3.5 可能遇到的bug，比如爆显存等等自己可以csdn一下。（坚持下去，多舔一舔）

3.6 这里贴一个将xml格式转换成yolov5lites训练所需的txt文件

文件夹准备如下，images放入图片，indata放入对应的xml格式文件，生成的txt文件会在labels文件夹下。

转换代码如下，如需调动测试以及验证数据集自己手动调yolov5lites的代码,换上自己对应修改的种类即可。

import xml.etree.ElementTree as ET
 
import pickle
import os
from os import listdir , getcwd
from os.path import join
import glob
 
classes = ["desk", "projector","cup","laptop","trash","box","mecanum"]
 
def convert(size, box):
 
    dw = 1.0/size[0]
    dh = 1.0/size[1]
    x = (box[0]+box[1])/2.0
    y = (box[2]+box[3])/2.0
    w = box[1] - box[0]
    h = box[3] - box[2]
    x = x*dw
    w = w*dw
    y = y*dh
    h = h*dh
    return (x,y,w,h)
 
def convert_annotation(image_name):
    in_file = open('./indata/'+image_name[:-3]+'xml') #xml文件路径
    out_file = open('./labels/'+image_name[:-3]+'txt', 'w') #转换后的txt文件存放路径
    f = open('./indata/'+image_name[:-3]+'xml')
    xml_text = f.read()
    root = ET.fromstring(xml_text)
    f.close()
    size = root.find('size')
    w = int(size.find('width').text)
    h = int(size.find('height').text)
 
 
 
 
    for obj in root.iter('object'):
        cls = obj.find('name').text
        if cls not in classes:
            print(cls)
            continue
        cls_id = classes.index(cls)
        xmlbox = obj.find('bndbox')
        b = (float(xmlbox.find('xmin').text), float(xmlbox.find('xmax').text), float(xmlbox.find('ymin').text),
             float(xmlbox.find('ymax').text))
        bb = convert((w,h), b)
        out_file.write(str(cls_id) + " " + " ".join([str(a) for a in bb]) + '\n')
 
wd = getcwd()
 
if __name__ == '__main__':
 
    #for image_path in glob.glob("./images/train/*.jpg"): #每一张图片都对应一个xml文件这里写xml对应的图片的路径
    for image_path in glob.glob("./images/*.jpg"): #每一张图片都对应一个xml文件这里写xml对应的图片的路径
        image_name = image_path.split('\\')[-1]
        convert_annotation(image_name)

二、数据的导出以及转换

这部分的导出我是在windows上完成的，我尝试了一下在树莓派上去导出，但一直报导出错误。

1.last.onnx文件导出以及简化

python export.py --weights weights/last.pt

会在weights/文件夹下生成对应的last.onnx文件

使用onnx-simplifier对转换后的onnx进行简化,将last.onnx文件放到yolov5lite-master文件下输入在终端输入以下指令

python -m onnxsim last.onnx lastsim.onnx

将简化后的lastsim.onnx放入u盘，导入到树莓派中

三、树莓派环境依赖已经ncnn编译

1.树莓派环境依赖配置

sudo apt-get install git cmake
sudo apt-get install -y gfortran
sudo apt-get install -y libprotobuf-dev libleveldb-dev libsnappy-dev libopencv-dev libhdf5-serial-dev protobuf-compiler
sudo apt-get install --no-install-recommends libboost-all-dev
sudo apt-get install -y libgflags-dev libgoogle-glog-dev liblmdb-dev libatlas-base-dev

2.ncnn配置以及编译

$ git clone https://gitee.com/Tencent/ncnn.git
cd ncnn
mkdir build
cd build
cmake ..
make -j4
make install

四、树莓派部署lite的ncnn细节

1.将lastsim.onnx转换为fp16的last.param和last.bin文件

对应路径自己修改（应当具备基础的命令行使用能力哈哈哈哈哈）

cd ncnn/build
./tools/onnx/onnx2ncnn lastsim.onnx lastsim.param lastsim.bin
./tools/ncnnoptimize lastsim.param lastsim.bin last.param last.bin 65536

2.添加yolov5lite.cpp到ncnn/examples文件夹下

具体代码如下所示

// 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.
 
#include "layer.h"
#include "net.h"
 
#if defined(USE_NCNN_SIMPLEOCV)
#include "simpleocv.h"
#else
#include 
#include 
#include 
#endif
#include 
#include 
#include 
#include 
 
// 0 : FP16
// 1 : INT8
#define USE_INT8 0
 
// 0 : Image
// 1 : Camera
#define USE_CAMERA 1
 
struct Object
{
    cv::Rect_<float> rect;
    int label;
    float prob;
};
 
static inline float intersection_area(const Object& a, const Object& b)
{
    cv::Rect_<float> inter = a.rect & b.rect;
    return inter.area();
}
 
static void qsort_descent_inplace(std::vector<Object>& faceobjects, int left, int right)
{
    int i = left;
    int j = right;
    float p = faceobjects[(left + right) / 2].prob;
 
    while (i <= j)
    {
        while (faceobjects[i].prob > p)
            i++;
 
        while (faceobjects[j].prob < p)
            j--;
 
        if (i <= j)
        {
            // swap
            std::swap(faceobjects[i], faceobjects[j]);
 
            i++;
            j--;
        }
    }
 
    #pragma omp parallel sections
    {
        #pragma omp section
        {
            if (left < j) qsort_descent_inplace(faceobjects, left, j);
        }
        #pragma omp section
        {
            if (i < right) qsort_descent_inplace(faceobjects, i, right);
        }
    }
}
 
static void qsort_descent_inplace(std::vector<Object>& faceobjects)
{
    if (faceobjects.empty())
        return;
 
    qsort_descent_inplace(faceobjects, 0, faceobjects.size() - 1);
}
 
static void nms_sorted_bboxes(const std::vector<Object>& faceobjects, std::vector<int>& picked, float nms_threshold)
{
    picked.clear();
 
    const int n = faceobjects.size();
 
    std::vector<float> areas(n);
    for (int i = 0; i < n; i++)
    {
        areas[i] = faceobjects[i].rect.area();
    }
 
    for (int i = 0; i < n; i++)
    {
        const Object& a = faceobjects[i];
 
        int keep = 1;
        for (int j = 0; j < (int)picked.size(); j++)
        {
            const Object& b = faceobjects[picked[j]];
 
            // intersection over union
            float inter_area = intersection_area(a, b);
            float union_area = areas[i] + areas[picked[j]] - inter_area;
            // float IoU = inter_area / union_area
            if (inter_area / union_area > nms_threshold)
                keep = 0;
        }
 
        if (keep)
            picked.push_back(i);
    }
}
 
static inline float sigmoid(float x)
{
    return static_cast<float>(1.f / (1.f + exp(-x)));
}
 
// unsigmoid
static inline float unsigmoid(float y) {
    return static_cast<float>(-1.0 * (log((1.0 / y) - 1.0)));
}
 
static void generate_proposals(const ncnn::Mat &anchors, int stride, const ncnn::Mat &in_pad,
                               const ncnn::Mat &feat_blob, float prob_threshold,
                               std::vector <Object> &objects) {
    const int num_grid = feat_blob.h;
    float unsig_pro = 0;
    if (prob_threshold > 0.6)
        unsig_pro = unsigmoid(prob_threshold);
 
    int num_grid_x;
    int num_grid_y;
    if (in_pad.w > in_pad.h) {
        num_grid_x = in_pad.w / stride;
        num_grid_y = num_grid / num_grid_x;
    } else {
        num_grid_y = in_pad.h / stride;
        num_grid_x = num_grid / num_grid_y;
    }
 
    const int num_class = feat_blob.w - 5;
 
    const int num_anchors = anchors.w / 2;
 
    for (int q = 0; q < num_anchors; q++) {
        const float anchor_w = anchors[q * 2];
        const float anchor_h = anchors[q * 2 + 1];
 
        const ncnn::Mat feat = feat_blob.channel(q);
 
        for (int i = 0; i < num_grid_y; i++) {
            for (int j = 0; j < num_grid_x; j++) {
                const float *featptr = feat.row(i * num_grid_x + j);
 
                // find class index with max class score
                int class_index = 0;
                float class_score = -FLT_MAX;
                float box_score = featptr[4];
                if (prob_threshold > 0.6) {
                    // while prob_threshold > 0.6, unsigmoid better than sigmoid
                    if (box_score > unsig_pro) {
                        for (int k = 0; k < num_class; k++) {
                            float score = featptr[5 + k];
                            if (score > class_score) {
                                class_index = k;
                                class_score = score;
                            }
                        }
 
                        float confidence = sigmoid(box_score) * sigmoid(class_score);
 
                        if (confidence >= prob_threshold) {
 
                            float dx = sigmoid(featptr[0]);
                            float dy = sigmoid(featptr[1]);
                            float dw = sigmoid(featptr[2]);
                            float dh = sigmoid(featptr[3]);
 
                            float pb_cx = (dx * 2.f - 0.5f + j) * stride;
                            float pb_cy = (dy * 2.f - 0.5f + i) * stride;
 
                            float pb_w = pow(dw * 2.f, 2) * anchor_w;
                            float pb_h = pow(dh * 2.f, 2) * anchor_h;
 
                            float x0 = pb_cx - pb_w * 0.5f;
                            float y0 = pb_cy - pb_h * 0.5f;
                            float x1 = pb_cx + pb_w * 0.5f;
                            float y1 = pb_cy + pb_h * 0.5f;
 
                            Object obj;
                            obj.rect.x = x0;
                            obj.rect.y = y0;
                            obj.rect.width = x1 - x0;
                            obj.rect.height = y1 - y0;
                            obj.label = class_index;
                            obj.prob = confidence;
 
                            objects.push_back(obj);
                        }
                    } else {
                        for (int k = 0; k < num_class; k++) {
                            float score = featptr[5 + k];
                            if (score > class_score) {
                                class_index = k;
                                class_score = score;
                            }
                        }
                        float confidence = sigmoid(box_score) * sigmoid(class_score);
 
                        if (confidence >= prob_threshold) {
                            float dx = sigmoid(featptr[0]);
                            float dy = sigmoid(featptr[1]);
                            float dw = sigmoid(featptr[2]);
                            float dh = sigmoid(featptr[3]);
 
                            float pb_cx = (dx * 2.f - 0.5f + j) * stride;
                            float pb_cy = (dy * 2.f - 0.5f + i) * stride;
 
                            float pb_w = pow(dw * 2.f, 2) * anchor_w;
                            float pb_h = pow(dh * 2.f, 2) * anchor_h;
 
                            float x0 = pb_cx - pb_w * 0.5f;
                            float y0 = pb_cy - pb_h * 0.5f;
                            float x1 = pb_cx + pb_w * 0.5f;
                            float y1 = pb_cy + pb_h * 0.5f;
 
                            Object obj;
                            obj.rect.x = x0;
                            obj.rect.y = y0;
                            obj.rect.width = x1 - x0;
                            obj.rect.height = y1 - y0;
                            obj.label = class_index;
                            obj.prob = confidence;
 
                            objects.push_back(obj);
                        }
                    }
                }
            }
        }
    }
}
 
static int detect_yolov5(const cv::Mat& bgr, std::vector<Object>& objects)
{
    ncnn::Net yolov5;
 
#if USE_INT8
    yolov5.opt.use_int8_inference=true;
#else
    yolov5.opt.use_vulkan_compute = true;
    yolov5.opt.use_bf16_storage = true;
#endif
 
    // original pretrained model from https://github.com/ultralytics/yolov5
    // the ncnn model https://github.com/nihui/ncnn-assets/tree/master/models
 
#if USE_INT8
    yolov5.load_param("/home/corvin/Mask/weights/e.param");
    yolov5.load_model("/home/corvin/Mask/weights/e.bin");
#else
    yolov5.load_param("/home/corvin/Mask/weights/eopt.param");
    yolov5.load_model("/home/corvin/Mask/weights/eopt.bin");
#endif
 
    const int target_size = 320;
    const float prob_threshold = 0.60f;
    const float nms_threshold = 0.60f;
 
    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.input("images", in_pad);
 
    std::vector<Object> proposals;
 
    // stride 8
    {
        ncnn::Mat out;
        ex.extract("451", 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("479", 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("507", 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;
}
 
static void draw_objects(const cv::Mat& bgr, const std::vector<Object>& objects)
{
	    static const char* class_names[] = {
	        "face","face_mask"
    };
 
    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(0, 255, 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));
    }
#if USE_CAMERA
    imshow("camera", image);
    cv::waitKey(1);
#else
    cv::imwrite("result.jpg", image);
#endif
}
 
#if USE_CAMERA
int main(int argc, char** argv)
{
    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;
 
        std::vector<Object> objects;
        detect_yolov5(frame, objects);
 
        draw_objects(m, objects);
        if (cv::waitKey(30) >= 0)
            break;
    }
}
#else
int main(int argc, char** argv)
{
    if (argc != 2)
    {
        fprintf(stderr, "Usage: %s [imagepath]\n", argv[0]);
        return -1;
    }
 
    const char* imagepath = argv[1];
 
    struct timespec begin, end;
    long time;
    clock_gettime(CLOCK_MONOTONIC, &begin);
 
    cv::Mat m = cv::imread(imagepath, 1);
    if (m.empty())
    {
        fprintf(stderr, "cv::imread %s failed\n", imagepath);
        return -1;
    }
 
    std::vector<Object> objects;
    detect_yolov5(m, objects);
 
    clock_gettime(CLOCK_MONOTONIC, &end);
    time = (end.tv_sec - begin.tv_sec) + (end.tv_nsec - begin.tv_nsec);
    printf(">> Time : %lf ms\n", (double)time/1000000);
 
    draw_objects(m, objects);
 
    return 0;
}
#endif

3.修改yolov5lite.cpp

3.1 修改classclass_names

修改成你所需要的检测种类,“desk”, “bicycle”, “cup”, “laptop”, “trash”, “box”, “mecanum”

3.2 修改anchor的数据

对应的是C:\Users\jxbj2\Desktop\yolov5lite\YOLOv5-Lite-master\models\v5lite-s.yaml

将上面这些anchor的数据（15，28，19，35，23，46）放入yolov5lite.cpp中的以下代码中，第一行的六个数据对应10，13，16，30，33，23）
对应的还有两个对应的地方也做出同样修改即可。

3.3 修改lastsim.param

将Reshape 0=x全部设置为0=-1，如画圈所示

3.4 修改yolov5lites的ex.extract

打开lastsim.param文件，对应上图三个方框里的 onnx：：Sigmoid_647改写到ex.extract里面。

3.5 在yolov5lites.cpp内修改路径

修改好yolov5.cpp中lastsim.param和lastsim.bin的路径，并放到测试的文件夹内（路径）。

3.6 修改CMakelists.txt

进入到ncnn/examples/CMakelist.txt，如下图所示

输入指令

cd ncnn/build
cmake ..
make

完成编译。

五、测试效果

打开测试的文件夹，将编译好的yolov5.cpp可执行文件放到测试文件夹下，（在yolov5lite.cpp文件内选择摄像头还是图片，如果有图片记得放在测试文件夹下）。

cd pi/ceshi
./yolov5_lite.cpp

说实话，我用的树莓派4B，yolov5lites感觉效果都不是很好，接下来我要继续试一下int8的量化。