yololv5的教学可以参考下面这个炮哥的文章，讲的很详细，我就是从这里学会的跳转

下面分享一下我学习(ultralytics) yolov8的目标检测过程

1.首先就是下载源码 yolov8

2.解压进入根目录新建main.py

from ultralytics import YOLO

# Load a model
model = YOLO("yolov8n.yaml")  # build a new model from scratch
model = YOLO("yolov8n.pt")  # load a pretrained model (recommended for training)

# Use the model
model.train(data="coco128.yaml", epochs=3)  # train the model
metrics = model.val()  # evaluate model performance on the validation set
results = model("https://ultralytics.com/images/bus.jpg")  # predict on an image
path = model.export(format="onnx")  # export the model to ONNX format

上面为官网的代码配置文件在目录中有说明 链接

3.安装依赖pip3 install -r requirements.txt

4.将上面代码保存运行python main.py, 结果打印得到保存的目录，目录下有best.pt则是基于yolov8n.pt训练的。

该流程为加载模型配置 yolov8n.yaml， 加载权重yolov8n.pt，训练数据，验证数据，推理，导出onnx (导出一般用不到)

上面内容为官网的示例，python，gpu环境安装参考yolov5的文章，下面就可以自己操作，比如训练一个地下城的目标检测

1.录制一个游戏视频 保存D:/ChromeCoreDownloads/py/video/test.mp4

2.录制完讲视频切割帧

代码根目录为ultralytics的话
新建 /ultralytics/VOCdevkit/biaozhu/Annotations/
新建 /ultralytics/VOCdevkit/biaozhu/JPEGImages/
新建 /ultralytics/VOCdevkit/biaozhu/predefined_classes.txt
新建 /ultralytics/VOCdevkit/VOC2007/

这里有一些标注的标签提示，将他们复制到 predefined_classes.txt 中，此处演示删减了一些分类
character
money
item
epic
open_door
close_door
guai_wu



在下面的tool.py中， 自行修改参数

视频目录                 videoDir='D:/ChromeCoreDownloads/py/video/'
代码根目录               root="E:/ideaworkspace3/ultralytics/"       
标注文件根目录            biaozhuRoot = root+"VOCdevkit/biaozhu/"
xml格式的待切割的数据根目录 vocRoot = root+"VOCdevkit/VOC2007/"
标签	                   classes = ["character", "money", "item", "epic", "open_door", "close_door", "guai_wu"]


运行 mp4ToPic， 将视频转为图片保存到标注目录下（不会运行的右转 https://www.python.org/）

2. 上面的操作完不出意外的话标注目录下会有图片，接着下载标注软件https://github.com/HumanSignal/labelImg

下载labelImg标注工具，cmd启动，指定两个一个图片目录和提示文件
labelImg.exe D:\\ultralytics\\VOCdevkit\\biaozhu\\JPEGImages D:\\ultralytics\\VOCdevkit\\biaozhu\\predefined_classes.txt

3.上面完成回车应该打开软件，打不开软件？管理员运行或者自行百度。

设置自动保存，修改标注的xml的保存目录，完成后开始画框标注，这里应该会出现predefined_classes.txt内的提示标签

4.标注完后检查 标注的Annotations和JPEGImages文件是否齐全

5.上一步确认没问题，接着开始转换，分割数据集，用于训练

在下面的tool.py中 biaozhuTovoc2007 函数用于将标注的xml和图片转移到VOC2007目录下的对应文件夹，并将xml配置转换为yolo8的txt配置，同时分割90%为训练，10%为验证， 结果保存到 VOCdevkit/images和labels

6.代码根目录新建data.yaml和model.yaml, model.yaml中的nc值应该等于data.yaml中的names的总数，这里的model.yaml还可以自定义转换函数，提升模型精度，自己摸索吧

# data.yaml

train: "VOCdevkit/images/train"
val: "VOCdevkit/images/val"
test:

names:
  0: character
  1: money
  2: item
  3: epic
  4: open_door
  5: close_door
  6: guai_wu

# model.yaml

nc: 7
depth_multiple: 0.33  # model depth multiple
width_multiple: 0.50  # layer channel multiple
anchors:
  - [10,13, 16,30, 33,23]  # P3/8
  - [30,61, 62,45, 59,119]  # P4/16
  - [116,90, 156,198, 373,326]  # P5/32

scales: # model compound scaling constants, i.e. 'model=yolov8n.yaml' will call yolov8.yaml with scale 'n'
  # [depth, width, max_channels]
  n: [0.33, 0.25, 1024]  # YOLOv8n summary: 225 layers,  3157200 parameters,  3157184 gradients,   8.9 GFLOPs
  s: [0.33, 0.50, 1024]  # YOLOv8s summary: 225 layers, 11166560 parameters, 11166544 gradients,  28.8 GFLOPs
  m: [0.67, 0.75, 768]   # YOLOv8m summary: 295 layers, 25902640 parameters, 25902624 gradients,  79.3 GFLOPs
  l: [1.00, 1.00, 512]   # YOLOv8l summary: 365 layers, 43691520 parameters, 43691504 gradients, 165.7 GFLOPs
  x: [1.00, 1.25, 512]   # YOLOv8x summary: 365 layers, 68229648 parameters, 68229632 gradients, 258.5 GFLOPs

# YOLOv8.0n backbone
backbone:
  # [from, repeats, module, args]
  - [-1, 1, Conv, [64, 3, 2]]  # 0-P1/2
  - [-1, 1, Conv, [128, 3, 2]]  # 1-P2/4
  - [-1, 3, C2f, [128, True]]
  - [-1, 1, Conv, [256, 3, 2]]  # 3-P3/8
  - [-1, 6, C2f, [256, True]]
  - [-1, 1, Conv, [512, 3, 2]]  # 5-P4/16
  - [-1, 6, C2f, [512, True]]
  - [-1, 1, Conv, [1024, 3, 2]]  # 7-P5/32
  - [-1, 3, C2f, [1024, True]]
  - [-1, 1, SPPF, [1024, 5]]  # 9

# YOLOv8.0n head
head:
  - [-1, 1, nn.Upsample, [None, 2, 'nearest']]
  - [[-1, 6], 1, Concat, [1]]  # cat backbone P4
  - [-1, 3, C2f, [512]]  # 12

  - [-1, 1, nn.Upsample, [None, 2, 'nearest']]
  - [[-1, 4], 1, Concat, [1]]  # cat backbone P3
  - [-1, 3, C2f, [256]]  # 15 (P3/8-small)

  - [-1, 1, Conv, [256, 3, 2]]
  - [[-1, 12], 1, Concat, [1]]  # cat head P4
  - [-1, 3, C2f, [512]]  # 18 (P4/16-medium)

  - [-1, 1, Conv, [512, 3, 2]]
  - [[-1, 9], 1, Concat, [1]]  # cat head P5
  - [-1, 3, C2f, [1024]]  # 21 (P5/32-large)

  - [[15, 18, 21], 1, Detect, [nc]]  # Detect(P3, P4, P5)

7.开始训练

到这里根目录下应该存在 data.yaml, model.yaml best.pt以及切割好的数据集图片

新建train.py

if __name__ == '__main__':
    wd = os.getcwd()
    model = YOLO(os.path.join(wd, "model.yaml"))
    model = YOLO(os.path.join(wd, "best.pt"))
    model.train(data=os.path.join(wd, "data.yaml"), epochs=1000, patience=200, batch=-1, imgsz=640, device=0, workers=2)
    metrics = model.val()


大概意思你们应该懂了， 其他进阶参数自己研究去吧，我也在学习中
epochs=1000（训练次数）
patience=200（超过多少次没进展终止）
batch=-1（每次加载多少张图到内存，建议自动-1
workers=2 （电脑带不动设置为0，带得动设置8）
device=0（gpu训练，不会安装pytorch gpu的参考yolo5的文章，cuda跳转 https://developer.nvidia.com/）

8.到这里整体的一个训练流程完成了，下面你们可以开始狱来狱勇了，充了钱尽头还不是搬砖（笑死）

用到的工具类 tool.py

import os
import random
import shutil
import time
import xml.etree.ElementTree as ET
from shutil import copyfile
from xml.dom.minidom import Document

import cv2

videoDir='D:/ChromeCoreDownloads/py/video/'
root="E:/ideaworkspace3/ultralytics/"
biaozhuRoot = root+"VOCdevkit/biaozhu/"
vocRoot = root+"VOCdevkit/VOC2007/"
classes = ["character", "money", "item", "epic", "open_door", "close_door", "guai_wu",
           "shang_ren", "fan_pai", "purple_card"]
TRAIN_RATIO = 90

def mp4ToPic():
    biaozhuImgDir=biaozhuRoot + "JPEGImages/"

    clearVocDir(biaozhuImgDir)

    files = os.listdir(videoDir)
    for file in files:
        file_path = os.path.join(videoDir, file)
        if os.path.isfile(file_path) and file.endswith(".mp4"):
            cap = cv2.VideoCapture(file_path)

            frame_count = int(cap.get(cv2.CAP_PROP_FRAME_COUNT))
            frame_rate = int(cap.get(cv2.CAP_PROP_FPS))

            target_interval = 10
            if frame_rate < target_interval:
                target_interval = frame_rate

            c = 1
            cut_num = 0
            while c <= frame_count:
                ok, frame = cap.read()
                if not ok:
                    break
                if c % target_interval == 0 or c == frame_count:
                    writePath = biaozhuImgDir + str(int(time.time() * 1000000)) + ".jpg"
                    cv2.imwrite(writePath, frame)
                    cut_num += 1

                c += 1

            cap.release()
            cv2.destroyAllWindows()
            print("mp4 task -> total: %d, cut: %d" % (frame_count, cut_num))

def biaozhuTovoc2007():
    clearVocDir(vocRoot+"Annotations")
    clearVocDir(vocRoot+"JPEGImages")
    clearVocDir(vocRoot+"YOLOLabels")
    # clearVocDir(root+"VOCdevkit/images")
    # clearVocDir(root+"VOCdevkit/labels")

    arr = list()

    files = os.listdir(biaozhuRoot + "Annotations")
    for file in files:
        xml = os.path.join(biaozhuRoot + "Annotations/", file)
        xmlw = os.path.join(vocRoot + "Annotations/", file)

        jpg = os.path.join(biaozhuRoot + "JPEGImages/", file.replace(".xml", ".jpg"))
        jpgw = os.path.join(vocRoot + "JPEGImages/", file.replace(".xml", ".jpg"))

        if os.path.exists(jpg):
            shutil.copy(xml, xmlw)
            shutil.copy(jpg, jpgw)

            arr.append(xml)
            arr.append(jpg)


    for p in arr:
        os.remove(p)

    vocToTxt()
    print("biaozhuTovoc2007 end!")


def clearVocDir(dir_path):
    if os.path.exists(dir_path):
        try:
            shutil.rmtree(dir_path)
            os.mkdir(dir_path)
        except Exception as e:
            print(f"Error while deleting folder: {e}")
    else:
        os.mkdir(dir_path)

def vocToTxt():
    wd = os.getcwd()
    data_base_dir = os.path.join(wd, "VOCdevkit/")
    if not os.path.isdir(data_base_dir):
        os.mkdir(data_base_dir)
    work_sapce_dir = os.path.join(data_base_dir, "VOC2007/")
    if not os.path.isdir(work_sapce_dir):
        os.mkdir(work_sapce_dir)
    annotation_dir = os.path.join(work_sapce_dir, "Annotations/")
    if not os.path.isdir(annotation_dir):
        os.mkdir(annotation_dir)
    clear_hidden_files(annotation_dir)
    image_dir = os.path.join(work_sapce_dir, "JPEGImages/")
    if not os.path.isdir(image_dir):
        os.mkdir(image_dir)
    clear_hidden_files(image_dir)
    yolo_labels_dir = os.path.join(work_sapce_dir, "YOLOLabels/")
    if not os.path.isdir(yolo_labels_dir):
        os.mkdir(yolo_labels_dir)
    clear_hidden_files(yolo_labels_dir)
    yolov5_images_dir = os.path.join(data_base_dir, "images/")
    if not os.path.isdir(yolov5_images_dir):
        os.mkdir(yolov5_images_dir)
    clear_hidden_files(yolov5_images_dir)
    yolov5_labels_dir = os.path.join(data_base_dir, "labels/")
    if not os.path.isdir(yolov5_labels_dir):
        os.mkdir(yolov5_labels_dir)
    clear_hidden_files(yolov5_labels_dir)
    yolov5_images_train_dir = os.path.join(yolov5_images_dir, "train/")
    if not os.path.isdir(yolov5_images_train_dir):
        os.mkdir(yolov5_images_train_dir)
    clear_hidden_files(yolov5_images_train_dir)
    yolov5_images_test_dir = os.path.join(yolov5_images_dir, "val/")
    if not os.path.isdir(yolov5_images_test_dir):
        os.mkdir(yolov5_images_test_dir)
    clear_hidden_files(yolov5_images_test_dir)
    yolov5_labels_train_dir = os.path.join(yolov5_labels_dir, "train/")
    if not os.path.isdir(yolov5_labels_train_dir):
        os.mkdir(yolov5_labels_train_dir)
    clear_hidden_files(yolov5_labels_train_dir)
    yolov5_labels_test_dir = os.path.join(yolov5_labels_dir, "val/")
    if not os.path.isdir(yolov5_labels_test_dir):
        os.mkdir(yolov5_labels_test_dir)
    clear_hidden_files(yolov5_labels_test_dir)

    train_file = open(os.path.join(wd, "yolov5_train.txt"), 'w')
    test_file = open(os.path.join(wd, "yolov5_val.txt"), 'w')
    train_file.close()
    test_file.close()
    train_file = open(os.path.join(wd, "yolov5_train.txt"), 'a')
    test_file = open(os.path.join(wd, "yolov5_val.txt"), 'a')
    list_imgs = os.listdir(image_dir) # list image files
    prob = random.randint(1, 100)
    print("Probability: %d" % prob)
    for i in range(0,len(list_imgs)):
        path = os.path.join(image_dir,list_imgs[i])
        if os.path.isfile(path):
            image_path = image_dir + list_imgs[i]
            voc_path = list_imgs[i]
            (nameWithoutExtention, extention) = os.path.splitext(os.path.basename(image_path))
            (voc_nameWithoutExtention, voc_extention) = os.path.splitext(os.path.basename(voc_path))
            annotation_name = nameWithoutExtention + '.xml'
            annotation_path = os.path.join(annotation_dir, annotation_name)
            label_name = nameWithoutExtention + '.txt'
            label_path = os.path.join(yolo_labels_dir, label_name)
        prob = random.randint(1, 100)
        print("Probability: %d" % prob)
        if(prob < TRAIN_RATIO): # train dataset
            if os.path.exists(annotation_path):
                train_file.write(image_path + '\n')
                convert_annotation(nameWithoutExtention) # convert label
                copyfile(image_path, yolov5_images_train_dir + voc_path)
                copyfile(label_path, yolov5_labels_train_dir + label_name)
        else:
            if os.path.exists(annotation_path):
                test_file.write(image_path + '\n')
                convert_annotation(nameWithoutExtention) # convert label
                copyfile(image_path, yolov5_images_test_dir + voc_path)
                copyfile(label_path, yolov5_labels_test_dir + label_name)
    train_file.close()
    test_file.close()

def txtToXml(picPath, txtPath, xmlPath):  # txt所在文件夹路径，xml文件保存路径，图片所在文件夹路径
    """此函数用于将yolo格式txt标注文件转换为voc格式xml标注文件
    在自己的标注图片文件夹下建三个子文件夹，分别命名为picture、txt、xml
    """
    dic = {'0': "hat",  # 创建字典用来对类型进行转换
           '1': "person",  # 此处的字典要与自己的classes.txt文件中的类对应，且顺序要一致
           }
    files = os.listdir(txtPath)
    for i, name in enumerate(files):
        xmlBuilder = Document()
        annotation = xmlBuilder.createElement("annotation")  # 创建annotation标签
        xmlBuilder.appendChild(annotation)
        txtFile = open(txtPath + name)
        txtList = txtFile.readlines()
        img = cv2.imread(picPath + name[0:-4] + ".jpg")
        Pheight, Pwidth, Pdepth = img.shape

        folder = xmlBuilder.createElement("folder")  # folder标签
        foldercontent = xmlBuilder.createTextNode("driving_annotation_dataset")
        folder.appendChild(foldercontent)
        annotation.appendChild(folder)  # folder标签结束

        filename = xmlBuilder.createElement("filename")  # filename标签
        filenamecontent = xmlBuilder.createTextNode(name[0:-4] + ".jpg")
        filename.appendChild(filenamecontent)
        annotation.appendChild(filename)  # filename标签结束

        size = xmlBuilder.createElement("size")  # size标签
        width = xmlBuilder.createElement("width")  # size子标签width
        widthcontent = xmlBuilder.createTextNode(str(Pwidth))
        width.appendChild(widthcontent)
        size.appendChild(width)  # size子标签width结束

        height = xmlBuilder.createElement("height")  # size子标签height
        heightcontent = xmlBuilder.createTextNode(str(Pheight))
        height.appendChild(heightcontent)
        size.appendChild(height)  # size子标签height结束

        depth = xmlBuilder.createElement("depth")  # size子标签depth
        depthcontent = xmlBuilder.createTextNode(str(Pdepth))
        depth.appendChild(depthcontent)
        size.appendChild(depth)  # size子标签depth结束

        annotation.appendChild(size)  # size标签结束

        for j in txtList:
            oneline = j.strip().split(" ")
            object = xmlBuilder.createElement("object")  # object 标签
            picname = xmlBuilder.createElement("name")  # name标签
            namecontent = xmlBuilder.createTextNode(dic[oneline[0]])
            picname.appendChild(namecontent)
            object.appendChild(picname)  # name标签结束

            pose = xmlBuilder.createElement("pose")  # pose标签
            posecontent = xmlBuilder.createTextNode("Unspecified")
            pose.appendChild(posecontent)
            object.appendChild(pose)  # pose标签结束

            truncated = xmlBuilder.createElement("truncated")  # truncated标签
            truncatedContent = xmlBuilder.createTextNode("0")
            truncated.appendChild(truncatedContent)
            object.appendChild(truncated)  # truncated标签结束

            difficult = xmlBuilder.createElement("difficult")  # difficult标签
            difficultcontent = xmlBuilder.createTextNode("0")
            difficult.appendChild(difficultcontent)
            object.appendChild(difficult)  # difficult标签结束

            bndbox = xmlBuilder.createElement("bndbox")  # bndbox标签
            xmin = xmlBuilder.createElement("xmin")  # xmin标签
            mathData = int(((float(oneline[1])) * Pwidth + 1) - (float(oneline[3])) * 0.5 * Pwidth)
            xminContent = xmlBuilder.createTextNode(str(mathData))
            xmin.appendChild(xminContent)
            bndbox.appendChild(xmin)  # xmin标签结束

            ymin = xmlBuilder.createElement("ymin")  # ymin标签
            mathData = int(((float(oneline[2])) * Pheight + 1) - (float(oneline[4])) * 0.5 * Pheight)
            yminContent = xmlBuilder.createTextNode(str(mathData))
            ymin.appendChild(yminContent)
            bndbox.appendChild(ymin)  # ymin标签结束

            xmax = xmlBuilder.createElement("xmax")  # xmax标签
            mathData = int(((float(oneline[1])) * Pwidth + 1) + (float(oneline[3])) * 0.5 * Pwidth)
            xmaxContent = xmlBuilder.createTextNode(str(mathData))
            xmax.appendChild(xmaxContent)
            bndbox.appendChild(xmax)  # xmax标签结束

            ymax = xmlBuilder.createElement("ymax")  # ymax标签
            mathData = int(((float(oneline[2])) * Pheight + 1) + (float(oneline[4])) * 0.5 * Pheight)
            ymaxContent = xmlBuilder.createTextNode(str(mathData))
            ymax.appendChild(ymaxContent)
            bndbox.appendChild(ymax)  # ymax标签结束

            object.appendChild(bndbox)  # bndbox标签结束

            annotation.appendChild(object)  # object标签结束

        f = open(xmlPath + name[0:-4] + ".xml", 'w')
        xmlBuilder.writexml(f, indent='\t', newl='\n', addindent='\t', encoding='utf-8')
        f.close()


def clear_hidden_files(path):
    dir_list = os.listdir(path)
    for i in dir_list:
        abspath = os.path.join(os.path.abspath(path), i)
        if os.path.isfile(abspath):
            if i.startswith("._"):
                os.remove(abspath)
        else:
            clear_hidden_files(abspath)

def convert(size, box):
    dw = 1./size[0]
    dh = 1./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_id):
    in_file = open('VOCdevkit/VOC2007/Annotations/%s.xml' %image_id)
    out_file = open('VOCdevkit/VOC2007/YOLOLabels/%s.txt' %image_id, 'w')
    tree=ET.parse(in_file)
    root = tree.getroot()
    size = root.find('size')
    w = int(size.find('width').text)
    h = int(size.find('height').text)

    for obj in root.iter('object'):
        difficult = obj.find('difficult').text
        cls = obj.find('name').text
        if cls not in classes or int(difficult) == 1:
            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')
    in_file.close()
    out_file.close()


if __name__=='__main__':
    mp4ToPic()
    biaozhuTovoc2007()


    # picPath = "VOCdevkit/VOC2007/JPEGImages/"  # 图片所在文件夹路径，后面的/一定要带上
    # txtPath = "VOCdevkit/VOC2007/YOLO/"  # txt所在文件夹路径，后面的/一定要带上
    # xmlPath = "VOCdevkit/VOC2007/Annotations/"  # xml文件保存路径，后面的/一定要带上
    # txtToXml(picPath, txtPath, xmlPath)

nvidia相关链接

cudnn
gpu算力查询
pytorch gpu安装