YOLO v11 目标检测+关键点检测 实战记录

流水账记录一下yolo目标检测
1.搭建pytorch 不做解释 看以往博客或网上搜都行
2.下载yolo源码 ： https://github.com/ultralytics/ultralytics
3.样本标注工具：labelimg 自己下载
4.准备数据集
4.1 新建一个放置数据集的路径


4.2 构建训练集和测试集
运行以下脚本，将数据集划分为训练集和测试集，比例是7：3，看自己需求

import os
import shutil

from tqdm import tqdm
import random

""" 使用：只需要修改 1. Dataset_folde，    
                  2. os.chdir(os.path.join(Dataset_folder, 'images'))里的 images, 
                  3. val_scal = 0.2 
                  4. os.chdir('../label_json')          label_json换成自己json标签文件夹名称   """

# 图片文件夹与json标签文件夹的根目录
Dataset_folder = r'D:\Software\Python\deeplearing\PytorchTest\ultralytics-main\datasets\PepperGrab'
# 把当前工作目录改为指定路径
os.chdir(os.path.join(Dataset_folder, 'images'))  # images ： 图片文件夹的名称
folder = '.'  # 代表os.chdir(os.path.join(Dataset_folder, 'images'))这个路径
imgs_list = os.listdir(folder)
random.seed(123)  # 固定随机种子，防止运行时出现bug后再次运行导致imgs_list 里面的图片名称顺序不一致
random.shuffle(imgs_list)  # 打乱
val_scal = 0.3  # 验证集比列
val_number = int(len(imgs_list) * val_scal)
val_files = imgs_list[:val_number]
train_files = imgs_list[val_number:]
print('all_files:', len(imgs_list))
print('train_files:', len(train_files))
print('val_files:', len(val_files))
os.mkdir('train')
for each in tqdm(train_files):
    shutil.move(each, 'train')
os.mkdir('val')
for each in tqdm(val_files):
    shutil.move(each, 'val')
os.chdir('../label_json')
os.mkdir('train')
for each in tqdm(train_files):
    json_file = os.path.splitext(each)[0] + '.json'
    shutil.move(json_file, 'train')
os.mkdir('val')
for each in tqdm(val_files):
    json_file = os.path.splitext(each)[0] + '.json'
    shutil.move(json_file, 'val')
print('划分完成')

4.2 然后就开始标样本了，用labelimg标，本次测试出了目标检测外，还需要检测关键点，类似标成下面这种，我之前标过一次样本，我就直接用了，没有标注的截图

4.3 因为labelimg标注完是json格式，要转化为yolo格式，运行以下脚本

import os
import json
import shutil
import numpy as np
from tqdm import tqdm

""""#使用：1.改 bbox_class = {'sjb_rect': 0}，我的框的类别是sjb_rect，赋值它为0，如你是dog则改成：bbox_cls = {'dog': 0}
          2.改 keypoint_class = ['angle_30', 'angle_60', 'angle_90']，我的关键点类别是三个，分别是'angle_30', 'angle_60', 'angle_90'  
          3.改 Dataset_root 成你自己的图片与json文件的路径 
          4.改 os.chdir('json_label/train')与os.chdir('json_label/val') 成你的json文件夹下的train与val文件夹 """

# 数据集根慕录(即图片文件夹与标签文件夹的上一级目录)
Dataset_root = r'D:\Software\Python\deeplearing\PytorchTest\ultralytics-main\datasets\PepperGrab'

# 框的类别
bbox_class = {
    'pepper': 0
}

# 关键点的类别
keypoint_class = ['head', 'end']  # 这里类别放的顺序对应关键点类别的标签 0，1，2

os.chdir(Dataset_root)

os.mkdir('labels')
os.mkdir('labels/train')
os.mkdir('labels/val')


def process_single_json(labelme_path, save_folder='../../labels/train'):
    with open(labelme_path, 'r', encoding='utf-8') as f:
        labelme = json.load(f)

    img_width = labelme['imageWidth']  # 图像宽度
    img_height = labelme['imageHeight']  # 图像高度

    # 生成 YOLO 格式的 txt 文件
    suffix = labelme_path.split('.')[-2]
    yolo_txt_path = suffix + '.txt'

    with open(yolo_txt_path, 'w', encoding='utf-8') as f:

        for each_ann in labelme['shapes']:  # 遍历每个标注

            if each_ann['shape_type'] == 'rectangle':  # 每个框，在 txt 里写一行

                yolo_str = ''

                ## 框的信息
                # 框的类别 ID
                bbox_class_id = bbox_class[each_ann['label']]
                yolo_str += '{} '.format(bbox_class_id)
                # 左上角和右下角的 XY 像素坐标
                bbox_top_left_x = int(min(each_ann['points'][0][0], each_ann['points'][1][0]))
                bbox_bottom_right_x = int(max(each_ann['points'][0][0], each_ann['points'][1][0]))
                bbox_top_left_y = int(min(each_ann['points'][0][1], each_ann['points'][1][1]))
                bbox_bottom_right_y = int(max(each_ann['points'][0][1], each_ann['points'][1][1]))
                # 框中心点的 XY 像素坐标
                bbox_center_x = int((bbox_top_left_x + bbox_bottom_right_x) / 2)
                bbox_center_y = int((bbox_top_left_y + bbox_bottom_right_y) / 2)
                # 框宽度
                bbox_width = bbox_bottom_right_x - bbox_top_left_x
                # 框高度
                bbox_height = bbox_bottom_right_y - bbox_top_left_y
                # 框中心点归一化坐标
                bbox_center_x_norm = bbox_center_x / img_width
                bbox_center_y_norm = bbox_center_y / img_height
                # 框归一化宽度
                bbox_width_norm = bbox_width / img_width
                # 框归一化高度
                bbox_height_norm = bbox_height / img_height

                yolo_str += '{:.5f} {:.5f} {:.5f} {:.5f} '.format(bbox_center_x_norm, bbox_center_y_norm,
                                                                  bbox_width_norm, bbox_height_norm)

                ## 找到该框中所有关键点，存在字典 bbox_keypoints_dict 中
                bbox_keypoints_dict = {}
                for each_ann in labelme['shapes']:  # 遍历所有标注
                    if each_ann['shape_type'] == 'point':  # 筛选出关键点标注
                        # 关键点XY坐标、类别
                        x = int(each_ann['points'][0][0])
                        y = int(each_ann['points'][0][1])
                        label = each_ann['label']
                        if (x > bbox_top_left_x) & (x < bbox_bottom_right_x) & (y < bbox_bottom_right_y) & (
                                y > bbox_top_left_y):  # 筛选出在该个体框中的关键点
                            bbox_keypoints_dict[label] = [x, y]

                ## 把关键点按顺序排好
                for each_class in keypoint_class:  # 遍历每一类关键点
                    if each_class in bbox_keypoints_dict:
                        keypoint_x_norm = bbox_keypoints_dict[each_class][0] / img_width
                        keypoint_y_norm = bbox_keypoints_dict[each_class][1] / img_height
                        yolo_str += '{:.5f} {:.5f} {} '.format(keypoint_x_norm, keypoint_y_norm,
                                                               2)  # 2-可见不遮挡 1-遮挡 0-没有点
                    else:  # 不存在的点，一律为0
                        yolo_str += '0 0 0 '
                # 写入 txt 文件中
                f.write(yolo_str + '\n')

    shutil.move(yolo_txt_path, save_folder)
    print('{} --> {} 转换完成'.format(labelme_path, yolo_txt_path))


os.chdir('label_json/train')

save_folder = '../../labels/train'
for labelme_path in os.listdir():
    try:
        process_single_json(labelme_path, save_folder=save_folder)
    except:
        print('******有误******', labelme_path)
print('YOLO格式的txt标注文件已保存至 ', save_folder)

os.chdir('../../')

os.chdir('label_json/val')

save_folder = '../../labels/val'
for labelme_path in os.listdir():
    try:
        process_single_json(labelme_path, save_folder=save_folder)
    except:
        print('******有误******', labelme_path)
print('YOLO格式的txt标注文件已保存至 ', save_folder)

os.chdir('../../')

os.chdir('../')

4.3 构造yaml
直接拷贝…\ultralytics-main\ultralytics\cfg\models\11\yolo11-pose.yaml
修改内容如下：

4.4 开始训练模型
先下载预训练模型 yolo11n.pt yolo11n-pose.pt
然后直接训练，先不看详细训练参数，先能跑起来

from ultralytics import YOLO
import cv2
# #训练
model = YOLO("./yolo11n-pose.pt")
model.train(data = "...../ultralytics-main_0829/ultralytics-main/yolo11-pose.yaml",workers=0,epochs=640,batch=8)

跑起来了

4.5 开始预测结果

yolo = YOLO("best.pt", task = "detect")
result = yolo(source=".../ultralytics-main_0829/ultralytics-main/datasets/PepperGrab/images/val",conf=0.4,vid_stride=1,iou=0.3,save = True)

效果一般般，起码是把流程走通了，精度后面再看吧

4.6 移植到C++测试
后面再说吧