【目标检测】DIOR遥感影像数据集,转为yolo系列模型训练所需格式。
标签文件位于Annotations下,格式为xml,yolo系列模型训练所需格式为txt,格式为
class_id x_center,y_center,w,h
其中,train,text,val按照官方方式划分(DIOR/ImageSets/Main/train.txt),分别含影像5062,5063,11738张。
在DIOR/ImageSets/Main/xx.txt 路径中,txt文件为不包含影像后缀的影像名称,如下图
yolo训练中需要的train.txt文件内容需要是包括后缀的绝对路径:
转换代码:
转换中的outpath可以自定义,为后续配置文件中的路径。
注意:
(1)将DIOR的影像文件夹改名为images,注意全小写,字母要对
(2)转换后的标签位于影像文件夹下的labels下,不要修改
**images和labels两个文件夹名称不要修改,不要修改,否则会报错:No labels in xx./train.cache
# -*- coding: utf-8 -*-
import xml.etree.ElementTree as ET
import os
from os import getcwd
sets = ['train', 'val', 'test']
# class names
classes = ['airplane', 'airport', 'baseballfield', 'basketballcourt', 'bridge', 'chimney', 'dam',
'Expressway-Service-area', 'Expressway-toll-station', 'golffield', 'groundtrackfield', 'harbor',
'overpass', 'ship', 'stadium', 'storagetank', 'tenniscourt', 'trainstation', 'vehicle', 'windmill'] # 改成自己的类别
abs_path = os.getcwd()
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
#修改路径-----------------------------
datasetpath="E:/dataset/DIOR"
imgpath="E:/dataset/DIOR/images"
outpath="E:/dataset/DIOR/myyolo"
def convert_annotation(image_id):
in_file = open(datasetpath+'/Annotations/%s.xml' % (image_id), encoding='UTF-8')
out_file = open(datasetpath+'/labels/%s.txt' % (image_id), 'w') #不要修改labels文件夹名称
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 = obj.find('name').text
if cls not in classes:
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))
b1, b2, b3, b4 = b
# 标注越界修正
if b2 > w:
b2 = w
if b4 > h:
b4 = h
b = (b1, b2, b3, b4)
bb = convert((w, h), b)
out_file.write(str(cls_id) + " " + " ".join([str(a) for a in bb]) + '\n')
wd = getcwd()
for image_set in sets:
if not os.path.exists(datasetpath+'/labels/'):
os.makedirs(datasetpath+'/labels/')
image_ids = open(datasetpath+'/ImageSets/Main/%s.txt' % (image_set)).read().strip().split()
if not os.path.exists(outpath):
os.makedirs(outpath)
list_file = open(outpath+'/%s.txt' % (image_set), 'w')
for image_id in image_ids:
list_file.write(imgpath+'/%s.jpg\n' % (image_id))
convert_annotation(image_id)
list_file.close()
转换后的text文件:
建立数据集配置文件DIOR.yaml,路径修改为outpath,
train: E:/dataset/DIOR/myyolo/train.txt
val: E:/dataset/DIOR/myyolo/val.txt
# number of classes
nc: 20
# class names
names: ['airplane', 'airport', 'baseballfield', 'basketballcourt', 'bridge', 'chimney', 'dam',
'Expressway-Service-area', 'Expressway-toll-station', 'golffield', 'groundtrackfield', 'harbor',
'overpass', 'ship', 'stadium', 'storagetank', 'tenniscourt', 'trainstation', 'vehicle', 'windmill']
在训练时将data参数设置为DIOR.yaml即可使用yolo系列模型训练DIOR。YOLOv5,v7,v8通用。
parser.add_argument('--data', type=str, default='data/DIOR.yaml', help='data.yaml path')