YOLOv10训练自己的数据集（AutoDL算力云）

一、在GitHub上下载YOLOv10代码

二、将自己的数据集放在YOLOv10中

1、创建dataset目录

将数据集放在dataset目录下

目录格式如下：

图片以JPG格式放在JPEGImages中

标签放在Annotations中

YOLO格式需要的txt放在txt中

2、划分数据集

(1)VOC格式先将Annotations的XML转换成txt

import xml.etree.ElementTree as ET
import os, cv2
import numpy as np
from os import listdir
from os.path import join

classes = []

def convert(size, box):
    dw = 1. / (size[0])
    dh = 1. / (size[1])
    x = (box[0] + box[1]) / 2.0 - 1
    y = (box[2] + box[3]) / 2.0 - 1
    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(xmlpath, xmlname):
    with open(xmlpath, "r", encoding='utf-8') as in_file:
        txtname = xmlname[:-4] + '.txt'
        txtfile = os.path.join(txtpath, txtname)
        tree = ET.parse(in_file)
        root = tree.getroot()
        filename = root.find('filename')
        img = cv2.imdecode(np.fromfile('{}/{}.{}'.format(imgpath, xmlname[:-4], postfix), np.uint8), cv2.IMREAD_COLOR)
        h, w = img.shape[:2]
        res = []
        for obj in root.iter('object'):
            cls = obj.find('name').text
            if cls not in classes:
                classes.append(cls)
            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)
            res.append(str(cls_id) + " " + " ".join([str(a) for a in bb]))
        if len(res) != 0:
            with open(txtfile, 'w+') as f:
                f.write('\n'.join(res))


if __name__ == "__main__":
    postfix = 'jpg'
    imgpath = 'VOCdevkit/JPEGImages'
    xmlpath = 'VOCdevkit/Annotations'
    txtpath = 'VOCdevkit/txt'
    
    if not os.path.exists(txtpath):
        os.makedirs(txtpath, exist_ok=True)
    
    list = os.listdir(xmlpath)
    error_file_list = []
    for i in range(0, len(list)):
        try:
            path = os.path.join(xmlpath, list[i])
            if ('.xml' in path) or ('.XML' in path):
                convert_annotation(path, list[i])
                print(f'file {list[i]} convert success.')
            else:
                print(f'file {list[i]} is not xml format.')
        except Exception as e:
            print(f'file {list[i]} convert error.')
            print(f'error message:\n{e}')
            error_file_list.append(list[i])
    print(f'this file convert failure\n{error_file_list}')
    print(f'Dataset Classes:{classes}')

(2)划分数据集

import os, shutil, random
random.seed(0)
import numpy as np
from sklearn.model_selection import train_test_split

val_size = 0.1
test_size = 0.2
postfix = 'jpg'
imgpath = 'VOCdevkit/JPEGImages'
txtpath = 'VOCdevkit/txt'

os.makedirs('images/train', exist_ok=True)
os.makedirs('images/val', exist_ok=True)
os.makedirs('images/test', exist_ok=True)
os.makedirs('labels/train', exist_ok=True)
os.makedirs('labels/val', exist_ok=True)
os.makedirs('labels/test', exist_ok=True)

listdir = np.array([i for i in os.listdir(txtpath) if 'txt' in i])
random.shuffle(listdir)
train, val, test = listdir[:int(len(listdir) * (1 - val_size - test_size))], listdir[int(len(listdir) * (1 - val_size - test_size)):int(len(listdir) * (1 - test_size))], listdir[int(len(listdir) * (1 - test_size)):]
print(f'train set size:{len(train)} val set size:{len(val)} test set size:{len(test)}')

for i in train:
    shutil.copy('{}/{}.{}'.format(imgpath, i[:-4], postfix), 'images/train/{}.{}'.format(i[:-4], postfix))
    shutil.copy('{}/{}'.format(txtpath, i), 'labels/train/{}'.format(i))

for i in val:
    shutil.copy('{}/{}.{}'.format(imgpath, i[:-4], postfix), 'images/val/{}.{}'.format(i[:-4], postfix))
    shutil.copy('{}/{}'.format(txtpath, i), 'labels/val/{}'.format(i))

for i in test:
    shutil.copy('{}/{}.{}'.format(imgpath, i[:-4], postfix), 'images/test/{}.{}'.format(i[:-4], postfix))
    shutil.copy('{}/{}'.format(txtpath, i), 'labels/test/{}'.format(i))

 划分完数据集后：

三、将整个文件压缩为ZIP文件

 四、创建AutoDL实例

五、上传刚才压缩好的YOLOv10，并创建终端解压

解压：

在终端中输入unzip yolov10-main

六、配置环境

1、在终端中先进入yolov10-main的目录

cd yolov10-main

2、下载环境需求

在终端中输入pip install -r requirements.txt

回车等待

七、创建数据集的.yaml文件

train: /root/yolov10-main/dataset/images/train
val: /root/yolov10-main/dataset/images/val
test: /root/yolov10-main/dataset/images/test


nc: 1
names: ['pothole']

八、训练

1、方法一

yolo detect train data=自己数据集.yaml model=yolov10n.yaml epochs=100 batch=32 imgsz=640 device=0

2、方法二

创建train.py

import warnings
warnings.filterwarnings('ignore')
from ultralytics import YOLOv10

if __name__ == '__main__':
    model = YOLOv10('ultralytics/cfg/models/v10/yolov10n.yaml')
    model.load('yolov10n.pt') # loading pretrain weights
    model.train(data='dataset/pothole.yaml',
                cache=False,
                imgsz=640,
                epochs=100,
                batch=32,
                close_mosaic=0,
                workers=8,
                device='0',
                optimizer='SGD', # using SGD
                project='runs/train',
                name='exp',
                )

 在终端中运行：

root@autodl-container-892a42a68f-b0b3bc8e:~/yolov10-main# python train.py

开始训练：

100轮训练完毕

九、验证

1、方法一

官网方法

yolo val model=jameslahm/yolov10{n/s/m/b/l/x} data=coco.yaml batch=256

2、方法二（自己创建Python脚本）

创建val.py

import warnings
warnings.filterwarnings('ignore')
from ultralytics import YOLOv10

if __name__ == '__main__':
    model = YOLOv10('runs/train/exp/weights/best.pt')
    model.val(data='dataset/pothole.yaml',
              split='val',
              imgsz=640,
              batch=16,
              # iou=0.7,
              # rect=False,
              # save_json=True, # if you need to cal coco metrice
              project='runs/val',
              name='exp',
              )

在终端中运行

root@autodl-container-892a42a68f-b0b3bc8e:~/yolov10-main# python val.py

 

十、测试

import warnings
warnings.filterwarnings('ignore')
from ultralytics import YOLOv10

if __name__ == '__main__':
    model = YOLOv10('runs/train/exp/weights/best.pt')
    model.val(data='dataset/pothole.yaml',
              split='test',
              imgsz=640,
              batch=16,
              # iou=0.7,
              # rect=False,
              # save_json=True, # if you need to cal coco metrice
              project='runs/test',
              name='exp',
              )

 运行脚本：

python test.py