训练
1、 下载yolov11源码
如果打不开的话可以科学上网。
2、处理数据集（转换与划分）
数据集VOC格式转yolo格式
如何查看自己数据集格式，打开Annotations文件夹，如果看到文件后缀为.xml，则为VOC格式，如果文件后缀为.txt则为yolo格式。yolov11训练需要转为yolo格式训练，转换代码如下。
import os
import xml.etree.ElementTree as ET
# 定义类别顺序
categories = ['name1', 'name2']
category_to_index = {category: index for index, category in enumerate(categories)}
# 定义输入文件夹和输出文件夹
input_folder = r'D:\临时存放\数据集\VOC2028\Annotations' # 替换为实际的XML文件夹路径
output_folder = r'D:\临时存放\数据集\VOC2028\label' # 替换为实际的输出TXT文件夹路径
# 确保输出文件夹存在
os.makedirs(output_folder, exist_ok=True)
# 遍历输入文件夹中的所有XML文件
for filename in os.listdir(input_folder):
if filename.endswith('.xml'):
xml_path = os.path.join(input_folder, filename)
# 解析XML文件
tree = ET.parse(xml_path)
root = tree.getroot()
# 提取图像的尺寸
size = root.find('size')
width = int(size.find('width').text)
height = int(size.find('height').text)
# 存储name和对应的归一化坐标
objects = []
# 遍历XML中的object标签
for obj in root.findall('object'):
name = obj.find('name').text
if name in category_to_index:
category_index = category_to_index[name]
else:
continue # 如果name不在指定类别中，跳过该object
bndbox = obj.find('bndbox')
xmin = int(bndbox.find('xmin').text)
ymin = int(bndbox.find('ymin').text)
xmax = int(bndbox.find('xmax').text)
ymax = int(bndbox.find('ymax').text)
# 转换为中心点坐标和宽高
x_center = (xmin + xmax) / 2.0
y_center = (ymin + ymax) / 2.0
w = xmax - xmin
h = ymax - ymin
# 归一化
x = x_center / width
y = y_center / height
w = w / width
h = h / height
objects.append(f"{category_index} {x} {y} {w} {h}")
# 输出结果到对应的TXT文件
txt_filename = os.path.splitext(filename)[0] + '.txt'
txt_path = os.path.join(output_folder, txt_filename)
with open(txt_path, 'w') as f:
for obj in objects:
f.write(obj + '\n')数据集切分成 训练集、测试集和验证集
我代码中切分的比例是7：2：1，可以根据自己需求划分。代码如下。
import os
import shutil
import random
# random.seed(0) #随机种子，可自选开启
def split_data(file_path, label_path, new_file_path, train_rate, val_rate, test_rate):
images = os.listdir(file_path)
labels = os.listdir(label_path)
images_no_ext = {os.path.splitext(image)[0]: image for image in images}
labels_no_ext = {os.path.splitext(label)[0]: label for label in labels}
matched_data = [(img, images_no_ext[img], labels_no_ext[img]) for img in images_no_ext if img in labels_no_ext]
unmatched_images = [img for img in images_no_ext if img not in labels_no_ext]
unmatched_labels = [label for label in labels_no_ext if label not in images_no_ext]
if unmatched_images:
print("未匹配的图片文件:")
for img in unmatched_images:
print(images_no_ext[img])
if unmatched_labels:
print("未匹配的标签文件:")
for label in unmatched_labels:
print(labels_no_ext[label])
random.shuffle(matched_data)
total = len(matched_data)
train_data = matched_data[:int(train_rate * total)]
val_data = matched_data[int(train_rate * total):int((train_rate + val_rate) * total)]
test_data = matched_data[int((train_rate + val_rate) * total):]
# 处理训练集
for img_name, img_file, label_file in train_data:
old_img_path = os.path.join(file_path, img_file)
old_label_path = os.path.join(label_path, label_file)
new_img_dir = os.path.join(new_file_path, 'train', 'images')
new_label_dir = os.path.join(new_file_path, 'train', 'labels')
os.makedirs(new_img_dir, exist_ok=True)
os.makedirs(new_label_dir, exist_ok=True)
shutil.copy(old_img_path, os.path.join(new_img_dir, img_file))
shutil.copy(old_label_path, os.path.join(new_label_dir, label_file))
# 处理验证集
for img_name, img_file, label_file in val_data:
old_img_path = os.path.join(file_path, img_file)
old_label_path = os.path.join(label_path, label_file)
new_img_dir = os.path.join(new_file_path, 'val', 'images')
new_label_dir = os.path.join(new_file_path, 'val', 'labels')
os.makedirs(new_img_dir, exist_ok=True)
os.makedirs(new_label_dir, exist_ok=True)
shutil.copy(old_img_path, os.path.join(new_img_dir, img_file))
shutil.copy(old_label_path, os.path.join(new_label_dir, label_file))
# 处理测试集
for img_name, img_file, label_file in test_data:
old_img_path = os.path.join(file_path, img_file)
old_label_path = os.path.join(label_path, label_file)
new_img_dir = os.path.join(new_file_path, 'test', 'images')
new_label_dir = os.path.join(new_file_path, 'test', 'labels')
os.makedirs(new_img_dir, exist_ok=True)
os.makedirs(new_label_dir, exist_ok=True)
shutil.copy(old_img_path, os.path.join(new_img_dir, img_file))
shutil.copy(old_label_path, os.path.join(new_label_dir, label_file))
print("数据集已划分完成")
if __name__ == '__main__':
file_path = r"D:\临时存放\数据集\VOC2028\JPEGImages" # 图片文件夹
label_path = r'D:\临时存放\数据集\VOC2028\label' # 标签文件夹
new_file_path = r"D:\临时存放\数据集\helmet_det" # 新数据存放位置
split_data(file_path, label_path, new_file_path, train_rate=0.7, val_rate=0.2, test_rate=0.1)3、创建data.yaml
在下载的源码根目录下创建一个新的data.yaml文件内容如下。主要是数据集路径和标签信息，根据自己的数据集去替换。
train: D:/临时存放/数据集/helmet_det/train/images
val: D:/临时存放/数据集/helmet_det/val/images
test: D:/临时存放/数据集/helmet_det/test/images
nc: 2 #你的数据集标签类别数
# Classes
names: ['name1','name2']4、创建一个自己的yolo11.yaml
打开yolov11源码，找到路径 ultralytics-main\ultralytics\cfg\models\11\yolo11.yaml。复制该文件内容，创建一个yolo11_copy.yaml文件，也可命名其他的名字后缀为.yaml就行，内容如下。
# Parameters
nc: 2 # number of classes
scales: # model compound scaling constants, i.e. 'model=yolo11n.yaml' will call yolo11.yaml with scale 'n'
# [depth, width, max_channels]
# n: [0.50, 0.25, 1024] # summary: 319 layers, 2624080 parameters, 2624064 gradients, 6.6 GFLOPs
s: [0.50, 0.50, 1024] # summary: 319 layers, 9458752 parameters, 9458736 gradients, 21.7 GFLOPs
# m: [0.50, 1.00, 512] # summary: 409 layers, 20114688 parameters, 20114672 gradients, 68.5 GFLOPs
# l: [1.00, 1.00, 512] # summary: 631 layers, 25372160 parameters, 25372144 gradients, 87.6 GFLOPs
# x: [1.00, 1.50, 512] # summary: 631 layers, 56966176 parameters, 56966160 gradients, 196.0 GFLOPs
# YOLO11n 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, 2, C3k2, [256, False, 0.25]]
- [-1, 1, Conv, [256, 3, 2]] # 3-P3/8
- [-1, 2, C3k2, [512, False, 0.25]]
- [-1, 1, Conv, [512, 3, 2]] # 5-P4/16
- [-1, 2, C3k2, [512, True]]
- [-1, 1, Conv, [1024, 3, 2]] # 7-P5/32
- [-1, 2, C3k2, [1024, True]]
- [-1, 1, SPPF, [1024, 5]] # 9
- [-1, 2, C2PSA, [1024]] # 10
# YOLO11n head
head:
- [-1, 1, nn.Upsample, [None, 2, "nearest"]]
- [[-1, 6], 1, Concat, [1]] # cat backbone P4
- [-1, 2, C3k2, [512, False]] # 13
- [-1, 1, nn.Upsample, [None, 2, "nearest"]]
- [[-1, 4], 1, Concat, [1]] # cat backbone P3
- [-1, 2, C3k2, [256, False]] # 16 (P3/8-small)
- [-1, 1, Conv, [256, 3, 2]]
- [[-1, 13], 1, Concat, [1]] # cat head P4
- [-1, 2, C3k2, [512, False]] # 19 (P4/16-medium)
- [-1, 1, Conv, [512, 3, 2]]
- [[-1, 10], 1, Concat, [1]] # cat head P5
- [-1, 2, C3k2, [1024, True]] # 22 (P5/32-large)
- [[16, 19, 22], 1, Detect, [nc]] # Detect(P3, P4, P5)5、下载预训练模型
yolo官网地址： yolo官网
模型大小n<s<m<l<x，需要用到那个型号的模型直接下载就行。
6、开始训练
训练代码如下，epochs是训练轮数，可以由少变多看训练效果，workers和batch根据电脑性能进行调整。
# -*- coding: utf-8 -*-
import warnings
from re import search
warnings.filterwarnings('ignore')
from ultralytics import YOLO
if __name__ == '__main__':
model = YOLO(model=r'C:\Users\Desktop\yolov11\ultralytics-main\ultralytics\cfg\models\11\yolo11_copy.yaml')
model.load('yolo11s.pt') # 加载预训练权重,改进或者做对比实验时候不建议打开，因为用预训练模型整体精度没有很明显的提升
model.train(data=r'data.yaml',
imgsz=640,
epochs=120,
batch=16,
workers=0,
device='',
optimizer='SGD',
close_mosaic=10,
resume=False,
project='runs/train',
name='exp',
single_cls=False,
cache=False,
)推理
推理代码如下，记得替换自己的模型和图片路径。
from ultralytics import YOLO
# 加载训练好的模型，改为自己的路径
model = YOLO('runs/train/exp/weights/best.pt')
source = 'test.jpg' #修改为自己的图片路径及文件名
# 运行推理，并附加参数
model.predict(source, save=True)
扫一扫
5万+
被折叠的 条评论
为什么被折叠?
到【灌水乐园】发言
