目录
本文是跑yolov8前的数据集配置记录
注意:
- 图片命名不要包含中文,不带空格
- 后缀统一为.jpg/.png
- 标注文件(Annotations)有对应的原图
1.将xml格式数据转换为txt格式
提前在VCOdevkit文件夹下建立一个名为txt的文件夹
先放一个完整目录结构:
- xml2txt脚本
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
执行split_data.py文件
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))
3.配置路径
在dataset文件夹下的data.yaml中完成下面几项内容
train: C:\Users\***\yolov8-main\data\images\train
val: C:\Users\***\yolov8-main\data\images\val
test: C:\Users\***\yolov8-main\data\images\test
# number of classes
nc: 20
# class names
names :['aeroplane','bicycle','bird','boat','bottle','bus','car','cat','chair','cow','diningtable','dog','horse','motorbike','person','pottedplant','sheep','sofa','train','tvmonitor']
4.使用
在指定参数时,只需要指定data.yaml文件即可
parser.add_argument('--data', type=str, default='yolov8-main/data/data.yaml', help='data yaml path')
标签:val,format,数据,配置,train,test,os,size
From: https://www.cnblogs.com/lushuang55/p/17744852.html