赞
踩
目录
1.1.1 通过split_train_val.py得到trainval.txt、val.txt、test.txt
1.1.2 通过voc_label.py得到适合yolov5训练需要的
缺陷类型:crack
数据集数量:195张
通过medianBlur、GaussianBlur、Blur3倍扩充得到780张图片
按照train、val、test进行8:1:1进行划分
- # coding:utf-8
-
- import os
- import random
- import argparse
-
- parser = argparse.ArgumentParser()
- #xml文件的地址,根据自己的数据进行修改 xml一般存放在Annotations下
- parser.add_argument('--xml_path', default='Annotations', type=str, help='input xml label path')
- #数据集的划分,地址选择自己数据下的ImageSets/Main
- parser.add_argument('--txt_path', default='ImageSets/Main', type=str, help='output txt label path')
- opt = parser.parse_args()
-
- trainval_percent = 0.9
- train_percent = 0.8
- xmlfilepath = opt.xml_path
- txtsavepath = opt.txt_path
- total_xml = os.listdir(xmlfilepath)
- if not os.path.exists(txtsavepath):
- os.makedirs(txtsavepath)
-
- num = len(total_xml)
- list_index = range(num)
- tv = int(num * trainval_percent)
- tr = int(tv * train_percent)
- trainval = random.sample(list_index, tv)
- train = random.sample(trainval, tr)
-
- file_trainval = open(txtsavepath + '/trainval.txt', 'w')
- file_test = open(txtsavepath + '/test.txt', 'w')
- file_train = open(txtsavepath + '/train.txt', 'w')
- file_val = open(txtsavepath + '/val.txt', 'w')
-
- for i in list_index:
- name = total_xml[i][:-4] + '\n'
- if i in trainval:
- file_trainval.write(name)
- if i in train:
- file_train.write(name)
- else:
- file_val.write(name)
- else:
- file_test.write(name)
-
- file_trainval.close()
- file_train.close()
- file_val.close()
- file_test.close()
- # -*- coding: utf-8 -*-
- import xml.etree.ElementTree as ET
- import os
- from os import getcwd
-
- sets = ['train', 'val']
- classes = ["crack"] # 改成自己的类别
- abs_path = os.getcwd()
- print(abs_path)
-
- 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(image_id):
- in_file = open('Annotations/%s.xml' % (image_id), encoding='UTF-8')
- out_file = open('labels/%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
- #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))
- 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('labels/'):
- os.makedirs('labels/')
- image_ids = open('ImageSets/Main/%s.txt' % (image_set)).read().strip().split()
- list_file = open('%s.txt' % (image_set), 'w')
- for image_id in image_ids:
- list_file.write(abs_path + '/images/%s.jpg\n' % (image_id))
- convert_annotation(image_id)
- list_file.close()
- train: ./data/crack/train.txt
- val: ./data/crack/val.txt
-
- # number of classes
- nc: 1
-
- # class names
- names: ["crack"]
- # YOLOv5 声明:本文内容由网友自发贡献,不代表【wpsshop博客】立场,版权归原作者所有,本站不承担相应法律责任。如您发现有侵权的内容,请联系我们。转载请注明出处:https://www.wpsshop.cn/w/你好赵伟/article/detail/252432推荐阅读
相关标签
Copyright © 2003-2013 www.wpsshop.cn 版权所有,并保留所有权利。