VOC格式标签转YOLO格式标签

'''
Author: hollis23
Date: 2021-10-22 16:39:24
LastEditTime: 2021-10-22 16:49:30
LastEditors: Please set LastEditors
Description: In User Settings Edit

'''
import xml.etree.ElementTree as ET
import pickle
import os
from os import listdir, getcwd
from os.path import join
import random
import shutil

'''
   1. 先将xml标签文件放到Anootations文件夹下，images放到JPEGImages文件夹下
'''
work_sapce_dir = os.path.join(tt100k_parent_dir, "VOCdevkit/")
if not os.path.isdir(work_sapce_dir):
    os.mkdir(work_sapce_dir)
work_sapce_dir = os.path.join(work_sapce_dir, "VOC2007/")
if not os.path.isdir(work_sapce_dir):
    os.mkdir(work_sapce_dir)
jpeg_images_path = os.path.join(work_sapce_dir, 'JPEGImages')
annotations_path = os.path.join(work_sapce_dir, 'Annotations')
if not os.path.isdir(jpeg_images_path):
    os.mkdir(jpeg_images_path)
if not os.path.isdir(annotations_path):
        os.mkdir(annotations_path)


'''
    2.根据xml文件的名字，将数据划分为训练集，验证集和测试集，并将生成的trainval.txt
    val.txt, test.txt放到ImageSets/Main文件夹下（这几个txt文件中的内容都是图像/xml
    标签的去后缀名称，即id）
'''

root_dir = 'I:/data/VOCdevkit/VOC2007/'

## 0.7train 0.1val 0.2test
trainval_percent = 0.8
train_percent = 0.7
xmlfilepath = root_dir + 'Annotations'
txtsavepath = root_dir + 'ImageSets/Main'
total_xml = os.listdir(xmlfilepath)

num = len(total_xml)  # 100
list = range(num)
tv = int(num * trainval_percent)  # 80
tr = int(tv * train_percent)  # 80*0.7=56
trainval = random.sample(list, tv)
train = random.sample(trainval, tr)

ftrainval = open(root_dir + 'ImageSets/Main/trainval.txt', 'w', encoding='utf-8')
ftest = open(root_dir + 'ImageSets/Main/test.txt', 'w', encoding='utf-8')
ftrain = open(root_dir + 'ImageSets/Main/train.txt', 'w', encoding='utf-8')
fval = open(root_dir + 'ImageSets/Main/val.txt', 'w', encoding='utf-8')

for i in list:
    name = total_xml[i][:-4] + '\n'
    if i in trainval:
        ftrainval.write(name)
        if i in train:
            ftrain.write(name)
        else:
            fval.write(name)
    else:
        ftest.write(name)

ftrainval.close()
ftrain.close()
fval.close()
ftest.close()



'''
    3.在VOCDevkit目录格式下，将xml标签格式转化为yolo的.txt文件格式，需要修改类别列表
'''


# sets=[('2012', 'train'), ('2012', 'val'), ('2007', 'train'), ('2007', 'val'), ('2007', 'test')]
sets=[('2007', 'trainval'), ('2007', 'test')]


# classes = ["aeroplane", "bicycle", "bird", "boat", "bottle", "bus", "car", "cat", "chair", "cow", "diningtable", "dog", "horse", "motorbike", "person", "pottedplant", "sheep", "sofa", "train", "tvmonitor"]
# classes = ["hat"]
classes = ["i2", "i4", "i5", "il100", "il60", "il80", "io", "ip", "p10", "p11", "p12", "p19", "p23", "p26", "p27", "p3", "p5", "p6", "pg", "ph4", "ph4.5", "ph5", "pl100", "pl120", "pl20", "pl30", "pl40", 
    "pl5", "pl50", "pl60", "pl70", "pl80", "pm20", "pm30", "pm55", "pn", "pne", "po", "pr40", "w13", "w32", "w55", "w57", "w59", "wo"]

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_annotation(year, image_id):
    in_file = open('/data/datasets/TT100K_45/VOCdevkit/VOC%s/Annotations/%s.xml'%(year, image_id))
    out_file = open('/data/datasets/TT100K_45/VOCdevkit/VOC%s/labels/%s.txt'%(year, 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
        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))
        bb = convert((w,h), b)
        out_file.write(str(cls_id) + " " + " ".join([str(a) for a in bb]) + '\n')

wd = '/data/datasets/TT100K_45/'

for year, image_set in sets:
    if not os.path.exists('/data/datasets/TT100K_45/VOCdevkit/VOC%s/labels/'%(year)):
        os.makedirs('/data/datasets/TT100K_45/VOCdevkit/VOC%s/labels/'%(year))
    image_ids = open('/data/datasets/TT100K_45/VOCdevkit/VOC%s/ImageSets/Main/%s.txt'%(year, image_set)).read().strip().split()
    list_file = open('%s_%s.txt'%(year, image_set), 'w')
    for image_id in image_ids:
        list_file.write('%s/VOCdevkit/VOC%s/JPEGImages/%s.jpg\n'%(wd, year, image_id))
        convert_annotation(year, image_id)
    list_file.close()


'''
    4. yolo格式标签划分训练集，验证机和测试集可以依据voc格式下的划分方法，即利用trainval.txt
    val.txt, test.txt中的id，将相应的图片和yolo的txt标签通过shutil.copyfile放到yolo格式的
    目录下
'''
# 训练集、验证集和测试集的比例分
root_image_path = '/data/datasets/TT100K_45/VOCdevkit/VOC2007/JPEGImages/'
root_label_path = '/data/datasets/TT100K_45/VOCdevkit/VOC2007/labels/'
# 标注文件的路径
image_path = '/data/datasets/TT100K_45/VOCdevkit/VOC2007/YOLO/'
label_path = '/data/datasets/TT100K_45/VOCdevkit/VOC2007/YOLO/'

images_files_list = os.listdir(root_image_path)
labels_files_list = os.listdir(root_label_path)
print('images files: {}'.format(images_files_list))
print('labels files: {}'.format(labels_files_list))
total_num = len(images_files_list)
print('total_num: {}'.format(total_num))

train_file = '/data/datasets/TT100K_45/VOCdevkit/VOC2007/ImageSets/Main/trainval.txt'
test_file = '/data/datasets/TT100K_45/VOCdevkit/VOC2007/ImageSets/Main/test.txt'

with open(train_file, 'r') as f:
    train_id = f.readlines()
    for id in train_id:
        id = id.strip()
        shutil.copyfile(root_image_path + id + '.jpg', image_path + 'train/images/' + id + '.jpg')
        shutil.copyfile(root_label_path + id + '.txt', label_path + 'train/labels/' + id + '.txt')
with open(test_file, 'r') as f1:
    test_id = f1.readlines()
    for id in test_id:
        id = id.strip()
        shutil.copyfile(root_image_path + id + '.jpg', image_path + 'test/images/' + id + '.jpg')
        shutil.copyfile(root_label_path + id + '.txt', label_path + 'test/labels/' + id + '.txt')