1、VOC（xml）标签格式转换为yolo（txt）格式并划分训练集和测试集
由于我们标注的时候将标签设置了voc（xml）格式，但yolov5训练过程中所需要的数据集是yolo（txt）格式，所以这里我们需要对数据格式进行转换。同时使用yolov5在训练自己的数据集模型的时候，需要将数据集划分为训练集和验证集，以下代码可以将xml格式的标注文件转换为txt格式的标注文件，同时按比例将数据集划分为训练集和验证集。
import xml.etree.ElementTree as ET
import pickle
import os
from os import listdir, getcwd
from os.path import join
import random
from shutil import copyfile
classes = ["baicao", "yecigu","kongxinlianzicao","cuimiqi","lichang","dingxiangiao_caolong","qianjinzi"]
# classes=["ball"]
TRAIN_RATIO = 80
def clear_hidden_files(path):
dir_list = os.listdir(path)
for i in dir_list:
abspath = os.path.join(os.path.abspath(path), i)
if os.path.isfile(abspath):
if i.startswith("._"):
os.remove(abspath)
else:
clear_hidden_files(abspath)
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(image_id):
in_file = open('VOCdevkit/VOC2007/Annotations/%s.xml' % image_id)
out_file = open('VOCdevkit/VOC2007/YOLOLabels/%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
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')
in_file.close()
out_file.close()
wd = os.getcwd()
wd = os.getcwd()
data_base_dir = os.path.join(wd, "VOCdevkit/")
if not os.path.isdir(data_base_dir):
os.mkdir(data_base_dir)
work_sapce_dir = os.path.join(data_base_dir, "VOC2007/")
if not os.path.isdir(work_sapce_dir):
os.mkdir(work_sapce_dir)
annotation_dir = os.path.join(work_sapce_dir, "Annotations/")
if not os.path.isdir(annotation_dir):
os.mkdir(annotation_dir)
clear_hidden_files(annotation_dir)
image_dir = os.path.join(work_sapce_dir, "JPEGImages/")
if not os.path.isdir(image_dir):
os.mkdir(image_dir)
clear_hidden_files(image_dir)
yolo_labels_dir = os.path.join(work_sapce_dir, "YOLOLabels/")
if not os.path.isdir(yolo_labels_dir):
os.mkdir(yolo_labels_dir)
clear_hidden_files(yolo_labels_dir)
yolov5_images_dir = os.path.join(data_base_dir, "images/")
if not os.path.isdir(yolov5_images_dir):
os.mkdir(yolov5_images_dir)
clear_hidden_files(yolov5_images_dir)
yolov5_labels_dir = os.path.join(data_base_dir, "labels/")
if not os.path.isdir(yolov5_labels_dir):
os.mkdir(yolov5_labels_dir)
clear_hidden_files(yolov5_labels_dir)
yolov5_images_train_dir = os.path.join(yolov5_images_dir, "train/")
if not os.path.isdir(yolov5_images_train_dir):
os.mkdir(yolov5_images_train_dir)
clear_hidden_files(yolov5_images_train_dir)
yolov5_images_test_dir = os.path.join(yolov5_images_dir, "val/")
if not os.path.isdir(yolov5_images_test_dir):
os.mkdir(yolov5_images_test_dir)
clear_hidden_files(yolov5_images_test_dir)
yolov5_labels_train_dir = os.path.join(yolov5_labels_dir, "train/")
if not os.path.isdir(yolov5_labels_train_dir):
os.mkdir(yolov5_labels_train_dir)
clear_hidden_files(yolov5_labels_train_dir)
yolov5_labels_test_dir = os.path.join(yolov5_labels_dir, "val/")
if not os.path.isdir(yolov5_labels_test_dir):
os.mkdir(yolov5_labels_test_dir)
clear_hidden_files(yolov5_labels_test_dir)
train_file = open(os.path.join(wd, "yolov5_train.txt"), 'w')
test_file = open(os.path.join(wd, "yolov5_val.txt"), 'w')
train_file.close()
test_file.close()
train_file = open(os.path.join(wd, "yolov5_train.txt"), 'a')
test_file = open(os.path.join(wd, "yolov5_val.txt"), 'a')
list_imgs = os.listdir(image_dir) # list image files
prob = random.randint(1, 100)
print("Probability: %d" % prob)
for i in range(0, len(list_imgs)):
path = os.path.join(image_dir, list_imgs[i])
if os.path.isfile(path):
image_path = image_dir + list_imgs[i]
voc_path = list_imgs[i]
(nameWithoutExtention, extention) = os.path.splitext(os.path.basename(image_path))
(voc_nameWithoutExtention, voc_extention) = os.path.splitext(os.path.basename(voc_path))
annotation_name = nameWithoutExtention + '.xml'
annotation_path = os.path.join(annotation_dir, annotation_name)
label_name = nameWithoutExtention + '.txt'
label_path = os.path.join(yolo_labels_dir, label_name)
prob = random.randint(1, 100)
print("Probability: %d" % prob)
if (prob < TRAIN_RATIO): # train dataset
if os.path.exists(annotation_path):
train_file.write(image_path + '\n')
convert_annotation(nameWithoutExtention) # convert label
copyfile(image_path, yolov5_images_train_dir + voc_path)
copyfile(label_path, yolov5_labels_train_dir + label_name)
else: # test dataset
if os.path.exists(annotation_path):
test_file.write(image_path + '\n')
convert_annotation(nameWithoutExtention) # convert label
copyfile(image_path, yolov5_images_test_dir + voc_path)
copyfile(label_path, yolov5_labels_test_dir + label_name)
train_file.close()
test_file.close()
新建一个文件夹，并将其命名为VOCdevkit，接着将之前标注好的数据集（VOC2007）文件复制到VOCdevkit文件里面，具体的数据集的标注流程可以看我另一篇博客有详细的说明（深度学习目标检测---使用labelimg对自己的数据集进行标记（windows系统））然后新建一个后缀为py的文件，存放上面的代码，我将上面的代码放在（1.py）文件上，该文件与VOCdevkit在同一个目录上。
注意：首先数据集的格式结构和文件名称必须严格按照如图的样式来，因为代码已经将文件名写固定在里面了。若想要修改需要更改代码里的文件路径（这里要是嫌麻烦的话就跟我一样的文件夹命名）。
JPEGImages文件为图片数据集所在的目录
Annotations文件为xml格式的标签数据集所在目录
1.py文件中存放的代码是我们上面的代码---格式转换和数据集划分
注意：如下图⬇这里要对应好：（1）为你训练标注的标签类别。（2）为训练集和验证集的比例（这里 训练集：验证集=80：20）
运行代码1.py结束后，就可以将数据集格式转换且划分好训练集和验证集。
在VOCdevkit目录下会生成images和labels文件夹，文件夹下分别生成train文件夹和val文件夹，里面分别保存着训练集的照片和txt格式的标签，还有验证集的照片和txt格式的标签。images文件夹和labels文件夹就是训练yolov5模型所需的训练集和验证集。在VOCdevkit/VOC2007目录下还生成了一个YOLOLabels文件夹，里面存放着所有的txt格式的标签文件。