yolov5学习笔记1-xml2txt

写在开头：

本文是学习他人博客之后的学习心得，正文开头处与结尾已经注明出处，如果涉及违背原文作者的利益，请私聊我进行删除，谢谢。
注：（共有两处觉得可以更改）

in_file = open(xml_file_path + image_name + '.xml')
可能会报出无法读取文件的错误
修改如下

in_file = open(xml_file_path + image_name + '.xml', 'r', encoding='UTF-8')

for obj in root.iter('item'):
    # difficult = obj.find('difficult').text
    cls = obj.find('name').text
    # if cls not in classes or int(difficult) == 1:
    #     continue
    if cls not in classes == 1:
        continue
  这里如果不做修改，会导致生成的.txt文件是空的
  修改如下：

  for obj in root.iter('object'):
# obj = root.iter('object')
difficult = obj.find('difficult').text
cls = obj.find('name').text
if cls not in classes or int(difficult) == 1:
    continue

————————————————

yolov5学习笔记1

原文链接：https://blog.csdn.net/a18838956649/article/details/118639052
原文相关B站视频链接：https://www.bilibili.com/video/BV1ao4y1D7bG?share_source=copy_web

import xml.etree.ElementTree as ET
import os
import shutil
import random

xml_file_path = 'data/xml/'       # 检查和自己的xml文件夹名称是否一致
images_file_path = 'data/img/'  # 检查和自己的图像文件夹名称是否一致

classes = ["a","b","c","d","e","f","g","m","n","p","w","x","y","2","3","4","5","6","7","8"]

train_percent = 0.7
val_percent = 0.15
test_percent = 0.15

if not os.path.exists('data/temp_labels/'):
    os.makedirs('data/temp_labels/')

txt_file_path = 'data/temp_labels/'


def convert(size, box):
    dw = 1. / size[0]
    dh = 1. / size[1]
    x = (box[0] + box[1]) / 2.0
    y = (box[2] + box[3]) / 2.0
    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_annotations(image_name):
    # in_file = open(xml_file_path + image_name + '.xml')
    in_file = open(xml_file_path + image_name + '.xml', 'r', encoding='UTF-8')
    out_file = open(txt_file_path + image_name + '.txt', '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'):
        # obj = root.iter('object')
        difficult = obj.find('difficult').text
        cls = obj.find('name').text
        if cls not in classes or int(difficult) == 1:
            continue
        # if cls not in classes == 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))
        bb = convert((w, h), b)
        out_file.write(str(cls_id) + " " + " ".join([str(a) for a in bb]) + '\n')


total_xml = os.listdir(xml_file_path)
num_xml = len(total_xml)  # XML文件总数

for i in range(num_xml):
    name = total_xml[i][:-4]
    convert_annotations(name)



def create_dir():
    if not os.path.exists('data/images/'):
        os.makedirs('data/images/')
    if not os.path.exists('data/labels/'):
        os.makedirs('data/labels/')

    if not os.path.exists('data/images/train/'):
        os.makedirs('data/images/train')
    if not os.path.exists('data/images/val/'):
        os.makedirs('data/images/val/')
    if not os.path.exists('data/images/test/'):
        os.makedirs('data/images/test/')

    if not os.path.exists('data/labels/train/'):
        os.makedirs('data/labels/train/')
    if not os.path.exists('data/labels/val/'):
        os.makedirs('data/labels/val/')
    if not os.path.exists('data/labels/test/'):
        os.makedirs('data/labels/test/')

    return



# 读取所有的txt文件
create_dir()
total_txt = os.listdir(txt_file_path)
num_txt = len(total_txt)
list_all_txt = range(num_txt)  # 范围 range(0, num)

num_train = int(num_txt * train_percent)
num_val = int(num_txt * val_percent)
num_test = num_txt - num_train - num_val

train = random.sample(list_all_txt, num_train)
# train从list_all_txt取出num_train个元素
# 所以list_all_txt列表只剩下了这些元素：val_test
val_test = [i for i in list_all_txt if not i in train]
# 再从val_test取出num_val个元素，val_test剩下的元素就是test
val = random.sample(val_test, num_val)


print("训练集数目：{}, 验证集数目：{},测试集数目：{}".format(len(train), len(val), len(val_test) - len(val)))
for i in list_all_txt:
    name = total_txt[i][:-4]

    srcImage = images_file_path + name + '.png'
    srcLabel = txt_file_path + name + '.txt'

    if i in train:
        dst_train_Image = 'data/images/train/' + name + '.png'
        dst_train_Label = 'data/labels/train/' + name + '.txt'
        shutil.copyfile(srcImage, dst_train_Image)
        shutil.copyfile(srcLabel, dst_train_Label)
    elif i in val:
        dst_val_Image = 'data/images/val/' + name + '.png'
        dst_val_Label = 'data/labels/val/' + name + '.txt'
        shutil.copyfile(srcImage, dst_val_Image)
        shutil.copyfile(srcLabel, dst_val_Label)
    else:
        dst_test_Image = 'data/images/test/' + name + '.png'
        dst_test_Label = 'data/labels/test/' + name + '.txt'
        shutil.copyfile(srcImage, dst_test_Image)
        shutil.copyfile(srcLabel, dst_test_Label)
shutil.rmtree(txt_file_path)

最后，感谢原文作者的分享，以下是原文链接和相关B站视频链接：
https://blog.csdn.net/a18838956649/article/details/118639052
https://www.bilibili.com/video/BV1ao4y1D7bG?share_source=copy_web