YOLOv5划分数据集

我看到大佬http://t.csdn.cn/s1J8T更新了关于Yolov5训练自己的数据集（详细完整版），有朋友划分数据集时路径有问题，我介绍一下我的方法：

首先是split_train_val.py文件：

import os
import random

trainval_percent = 0.8
train_percent = 0.6
xmlfilepath = 'annotations'
total_xml = os.listdir(xmlfilepath)
num = len(total_xml)
list = range(num)
tv = int(num * trainval_percent)
tr = int(num * train_percent)
trainval = random.sample(list, tv)
train = random.sample(trainval, tr)

# ImageSets目录不存在，就创建
if not os.path.exists('ImageSets/'):
    os.makedirs('ImageSets/')
# ImageSets/Main目录不存在，就创建
if not os.path.exists('ImageSets/Main/'):
    os.makedirs('ImageSets/Main/')

ftrainval = open('ImageSets/Main/trainval.txt', 'w')
ftest = open('ImageSets/Main/test.txt', 'w')
ftrain = open('ImageSets/Main/train.txt', 'w')
fval = open('ImageSets/Main/val.txt', 'w')

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()

其次是voc_label.py文件

import xml.etree.ElementTree as ET
import os
from os import getcwd

sets = ['train', 'val', 'test']
classes = ['2.0', '2.5', '3.0', '3.5', '4.0', '5.0']
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


def convert_annotation(image_id):
    in_file = open('D:/yolov5/dataset_1128-483/annotations/%s.xml' % (image_id),encoding='UTF-8')
    out_file = open('D:/yolov5/dataset_1128-483/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
        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()
    if not os.path.exists('D:/yolov5/dataset_1128-483/dataSet_path/'):
#设置一个dataSet_path文件夹，用来存放train、val、test的数据的绝对路径
        os.makedirs('D:/yolov5/dataset_1128-483/dataSet_path/')
    list_file = open('dataSet_path/%s.txt' % (image_set), 'w')
    for image_id in image_ids:
        list_file.write('D:/yolov5/dataset_1128-483/images/%s.jpg\n'% (image_id))
        convert_annotation(image_id)
    list_file.close()

我发现出现问题主要是路径设置错误，按照上面的步骤，应该在Main文件夹中存放train、val、test的数据的名称，在dataSet_path文件夹中存放train、val、test的数据的绝对路径，在后面读取路径时候就没有问题了。