YOLOv5将自己数据集划分为训练集、验证集和测试集

在用自己数据集跑YOLOv5代码时候，需要将自己的VOC标签格式数据集转为yolo格式。

首先是要获取自己的数据集，然后再对数据集进行标注，保存为VOC(xml格式)。然后再把标注完的数据集划分为训练集和验证集，这样更加方便模型的训练和测试。首先上划分数据集的代码。这里提供了一份代码将xml格式的标注文件转换为txt格式的标注文件，并按比例划分为训练集、验证集和测试集。代码如下：

 classes为自己数据集的类别名称，TRAIN_RATIO为训练集比例，本代码按照6：2：2比例划分为训练集、验证集和测试集，可自行调整。

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 = ["hens"]
# classes = ["hat", "person"]
#classes =  ['aeroplane', 'bicycle', 'bird', 'boat', 'bottle', 'bus', 'car', 'cat', 'chair', 'cow', 'diningtable', 'dog',
        #'horse', 'motorbike', 'person', 'pottedplant', 'sheep', 'sofa', 'train', 'tvmonitor']

TRAIN_RATIO = 60


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, encoding="utf_8")
    out_file = open('VOCdevkit/VOC2007/YOLOLabels/%s.txt' % image_id, 'w', encoding="utf_8")
    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'):
        if obj.find('difficult'):
            difficult = obj.find('difficult').text
        else:
            difficult = 0
        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_val_dir = os.path.join(yolov5_images_dir, "val/")
if not os.path.isdir(yolov5_images_val_dir):
    os.mkdir(yolov5_images_val_dir)
clear_hidden_files(yolov5_images_val_dir)
yolov5_images_test_dir = os.path.join(yolov5_images_dir, "test/")
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_val_dir = os.path.join(yolov5_labels_dir, "val/")
if not os.path.isdir(yolov5_labels_val_dir):
    os.mkdir(yolov5_labels_val_dir)
clear_hidden_files(yolov5_labels_val_dir)
yolov5_labels_test_dir = os.path.join(yolov5_labels_dir, "test/")
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')
val_file = open(os.path.join(wd, "yolov5_val.txt"), 'w')
test_file = open(os.path.join(wd, "yolov5_test.txt"), 'w')
train_file.close()
val_file.close()
test_file.close()
train_file = open(os.path.join(wd, "yolov5_train.txt"), 'a')
val_file = open(os.path.join(wd, "yolov5_val.txt"), 'a')
test_file = open(os.path.join(wd, "yolov5_test.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)
    elif (prob > TRAIN_RATIO and prob < 80):
        if os.path.exists(annotation_path):
            val_file.write(image_path + '\n')
            convert_annotation(nameWithoutExtention)  # convert label
            copyfile(image_path, yolov5_images_val_dir + voc_path)
            copyfile(label_path, yolov5_labels_val_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()

    运行上述代码后，在VOCdevkit目录下生成images和labels文件夹，文件夹下分别生成了train文件夹、val文件夹和test文件夹，里面分别保存着训练集的照片和txt格式的标签、验证集的照片和txt格式的标签以及测试集的照片和txt格式的标签images文件夹和labels文件夹。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。

yaml文件按如下路径修改即可，注意将nc调整为自己数据集类别个数，names调整为自己数据集类别名称。