Yolov7 performs data enhancement and data partitioning

The previous article talked about the process of yolov7 training its own data set: link
But if the amount of data is not enough and the training results are not good, then data enhancement is needed.

Personal learning record: The format of the yolov7 data set is Yolo format, which is a txt file. Data enhancement is aimed at xml files, so it needs to be converted, and then converted back after enhancement.

Yolo format to xml format

import cv2
import os

xml_head = '''<annotation>
    <folder>VOC2007</folder>
    <filename>{}</filename>
    <source>
        <database>The VOC2007 Database</database>
        <annotation>PASCAL VOC2007</annotation>
        <image>flickr</image>
    </source>
    <size>
        <width>{}</width>
        <height>{}</height>
        <depth>{}</depth>
    </size>
    <segmented>0</segmented>
    '''
xml_obj = '''
    <object>        
        <name>{}</name>
        <pose>Rear</pose>
        <truncated>0</truncated>
        <difficult>0</difficult>
        <bndbox>
            <xmin>{}</xmin>
            <ymin>{}</ymin>
            <xmax>{}</xmax>
            <ymax>{}</ymax>
        </bndbox>
    </object>
    '''
xml_end = '''
</annotation>'''

# 需要修改为你自己数据集的分类
labels = ['baggage']  # label for datasets

cnt = 0
txt_path = os.path.join('train/labels/')  # yolo存放txt的文件目录
image_path = os.path.join('train/images/')  # 存放图片的文件目录
path = os.path.join('train/xml/')  # 存放生成xml的文件目录

for (root, dirname, files) in os.walk(image_path):  # 遍历图片文件夹
    for ft in files:
        ftxt = ft.replace('jpg', 'txt')  # ft是图片名字+扩展名，将jpg和txt替换
        fxml = ft.replace('jpg', 'xml')
        xml_path = path + fxml
        obj = ''

        img = cv2.imread(root + ft)
        img_h, img_w = img.shape[0], img.shape[1]
        head = xml_head.format(str(fxml), str(img_w), str(img_h), 3)

        with open(txt_path + ftxt, 'r') as f:  # 读取对应txt文件内容
            for line in f.readlines():
                yolo_datas = line.strip().split(' ')
                label = int(float(yolo_datas[0].strip()))
                center_x = round(float(str(yolo_datas[1]).strip()) * img_w)
                center_y = round(float(str(yolo_datas[2]).strip()) * img_h)
                bbox_width = round(float(str(yolo_datas[3]).strip()) * img_w)
                bbox_height = round(float(str(yolo_datas[4]).strip()) * img_h)

                xmin = str(int(center_x - bbox_width / 2))
                ymin = str(int(center_y - bbox_height / 2))
                xmax = str(int(center_x + bbox_width / 2))
                ymax = str(int(center_y + bbox_height / 2))
                obj += xml_obj.format(labels[label], xmin, ymin, xmax, ymax)
        with open(xml_path, 'w') as f_xml:
            f_xml.write(head + obj + xml_end)
        cnt += 1
        print(cnt)

Data enhancement of xml tags

'''
Author: CodingWZP
Email: [email protected]
Date: 2021-08-06 10:51:35
LastEditTime: 2021-08-09 10:53:43
Description: Image augmentation with label.
'''
import xml.etree.ElementTree as ET
import os
import imgaug as ia
import numpy as np
import shutil
from tqdm import tqdm
from PIL import Image
from imgaug import augmenters as iaa

ia.seed(1)


def read_xml_annotation(root, image_id):
    in_file = open(os.path.join(root, image_id))
    tree = ET.parse(in_file)
    root = tree.getroot()
    bndboxlist = []

    for object in root.findall('object'):  # 找到root节点下的所有country节点
        bndbox = object.find('bndbox')  # 子节点下节点rank的值

        xmin = int(bndbox.find('xmin').text)
        xmax = int(bndbox.find('xmax').text)
        ymin = int(bndbox.find('ymin').text)
        ymax = int(bndbox.find('ymax').text)
        # print(xmin,ymin,xmax,ymax)
        bndboxlist.append([xmin, ymin, xmax, ymax])
        # print(bndboxlist)

    bndbox = root.find('object').find('bndbox')
    return bndboxlist


def change_xml_list_annotation(root, image_id, new_target, saveroot, id):
    in_file = open(os.path.join(root, str(image_id) + '.xml'))  # 这里root分别由两个意思
    tree = ET.parse(in_file)
    # 修改增强后的xml文件中的filename
    elem = tree.find('filename')
    elem.text = (str(id) + '.jpg')
    xmlroot = tree.getroot()
    # 修改增强后的xml文件中的path
    elem = tree.find('path')
    if elem != None:
        elem.text = (saveroot + str(id) + '.jpg')

    index = 0
    for object in xmlroot.findall('object'):  # 找到root节点下的所有country节点
        bndbox = object.find('bndbox')  # 子节点下节点rank的值

        # xmin = int(bndbox.find('xmin').text)
        # xmax = int(bndbox.find('xmax').text)
        # ymin = int(bndbox.find('ymin').text)
        # ymax = int(bndbox.find('ymax').text)

        new_xmin = new_target[index][0]
        new_ymin = new_target[index][1]
        new_xmax = new_target[index][2]
        new_ymax = new_target[index][3]

        xmin = bndbox.find('xmin')
        xmin.text = str(new_xmin)
        ymin = bndbox.find('ymin')
        ymin.text = str(new_ymin)
        xmax = bndbox.find('xmax')
        xmax.text = str(new_xmax)
        ymax = bndbox.find('ymax')
        ymax.text = str(new_ymax)

        index = index + 1

    tree.write(os.path.join(saveroot, str(id + '.xml')))


def mkdir(path):
    # 去除首位空格
    path = path.strip()
    # 去除尾部 \ 符号
    path = path.rstrip("\\")
    # 判断路径是否存在
    # 存在     True
    # 不存在   False
    isExists = os.path.exists(path)
    # 判断结果
    if not isExists:
        # 如果不存在则创建目录
        # 创建目录操作函数
        os.makedirs(path)
        print(path + ' 创建成功')
        return True
    else:
        # 如果目录存在则不创建，并提示目录已存在
        print(path + ' 目录已存在')
        return False


if __name__ == "__main__":

    IMG_DIR = "./images/"
    XML_DIR = "./xml/"

    AUG_XML_DIR = "./AUG/Annotations/"  # 存储增强后的XML文件夹路径
    try:
        shutil.rmtree(AUG_XML_DIR)
    except FileNotFoundError as e:
        a = 1
    mkdir(AUG_XML_DIR)

    AUG_IMG_DIR = "./AUG/JPEGImages/"  # 存储增强后的影像文件夹路径
    try:
        shutil.rmtree(AUG_IMG_DIR)
    except FileNotFoundError as e:
        a = 1
    mkdir(AUG_IMG_DIR)

    AUGLOOP = 10  # 每张影像增强的数量

    boxes_img_aug_list = []
    new_bndbox = []
    new_bndbox_list = []

    # 影像增强
    seq = iaa.Sequential([
        iaa.Invert(0.5),
        iaa.Fliplr(0.5),  # 镜像
        iaa.Multiply((1.2, 1.5)),  # change brightness, doesn't affect BBs
        iaa.GaussianBlur(sigma=(0, 3.0)),  # iaa.GaussianBlur(0.5),
        iaa.Affine(
            translate_px={
    
    "x": 15, "y": 15},
            scale=(0.8, 0.95),
        )  # translate by 40/60px on x/y axis, and scale to 50-70%, affects BBs
    ])

    for name in tqdm(os.listdir(XML_DIR), desc='Processing'):

        bndbox = read_xml_annotation(XML_DIR, name)

        # 保存原xml文件
        shutil.copy(os.path.join(XML_DIR, name), AUG_XML_DIR)
        # 保存原图
        og_img = Image.open(IMG_DIR + '/' + name[:-4] + '.jpg')
        og_img.convert('RGB').save(AUG_IMG_DIR + name[:-4] + '.jpg', 'JPEG')
        og_xml = open(os.path.join(XML_DIR, name))
        tree = ET.parse(og_xml)
        # 修改增强后的xml文件中的filename
        elem = tree.find('filename')
        elem.text = (name[:-4] + '.jpg')
        tree.write(os.path.join(AUG_XML_DIR, name))

        for epoch in range(AUGLOOP):
            seq_det = seq.to_deterministic()  # 保持坐标和图像同步改变，而不是随机
            # 读取图片
            img = Image.open(os.path.join(IMG_DIR, name[:-4] + '.jpg'))
            # sp = img.size
            img = np.asarray(img)
            # bndbox 坐标增强
            for i in range(len(bndbox)):
                bbs = ia.BoundingBoxesOnImage([
                    ia.BoundingBox(x1=bndbox[i][0], y1=bndbox[i][1], x2=bndbox[i][2], y2=bndbox[i][3]),
                ], shape=img.shape)

                bbs_aug = seq_det.augment_bounding_boxes([bbs])[0]
                boxes_img_aug_list.append(bbs_aug)

                # new_bndbox_list:[[x1,y1,x2,y2],...[],[]]
                n_x1 = int(max(1, min(img.shape[1], bbs_aug.bounding_boxes[0].x1)))
                n_y1 = int(max(1, min(img.shape[0], bbs_aug.bounding_boxes[0].y1)))
                n_x2 = int(max(1, min(img.shape[1], bbs_aug.bounding_boxes[0].x2)))
                n_y2 = int(max(1, min(img.shape[0], bbs_aug.bounding_boxes[0].y2)))
                if n_x1 == 1 and n_x1 == n_x2:
                    n_x2 += 1
                if n_y1 == 1 and n_y2 == n_y1:
                    n_y2 += 1
                if n_x1 >= n_x2 or n_y1 >= n_y2:
                    print('error', name)
                new_bndbox_list.append([n_x1, n_y1, n_x2, n_y2])
            # 存储变化后的图片
            image_aug = seq_det.augment_images([img])[0]
            path = os.path.join(AUG_IMG_DIR,
                                str(str(name[:-4]) + '_' + str(epoch)) + '.jpg')
            image_auged = bbs.draw_on_image(image_aug, size=0)
            Image.fromarray(image_auged).convert('RGB').save(path)

            # 存储变化后的XML
            change_xml_list_annotation(XML_DIR, name[:-4], new_bndbox_list, AUG_XML_DIR,
                                       str(name[:-4]) + '_' + str(epoch))
            # print(str(str(name[:-4]) + '_' + str(epoch)) + '.jpg')
            new_bndbox_list = []
    print('Finish!')

xml format to Yolo format

import xml.etree.ElementTree as ET
import pickle
import os
from os import listdir, getcwd
from os.path import join
 
def convert(size, box):
    # size=(width, height)  b=(xmin, xmax, ymin, ymax)
    # x_center = (xmax+xmin)/2        y_center = (ymax+ymin)/2
    # x = x_center / width            y = y_center / height
    # w = (xmax-xmin) / width         h = (ymax-ymin) / height
    
    x_center = (box[0]+box[1])/2.0
    y_center = (box[2]+box[3])/2.0
    x = x_center / size[0]
    y = y_center / size[1]
 
    w = (box[1] - box[0]) / size[0]
    h = (box[3] - box[2]) / size[1]
 
    # print(x, y, w, h)
    return (x,y,w,h)
 
def convert_annotation(xml_files_path, save_txt_files_path, classes):  
    xml_files = os.listdir(xml_files_path)
    # print(xml_files)
    for xml_name in xml_files:
        # print(xml_name)
        xml_file = os.path.join(xml_files_path, xml_name)
        out_txt_path = os.path.join(save_txt_files_path, xml_name.split('.')[0] + '.txt')
        out_txt_f = open(out_txt_path, 'w')
        tree=ET.parse(xml_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))
            # b=(xmin, xmax, ymin, ymax)
            # print(w, h, b)
            bb = convert((w,h), b)
            out_txt_f.write(str(cls_id) + " " + " ".join([str(a) for a in bb]) + '\n')
 
 
if __name__ == "__main__":
    # 把forklift_pallet的voc的xml标签文件转化为yolo的txt标签文件
    # 1、需要转化的类别
    classes = ['contact']#注意：这里根据自己的类别名称及种类自行更改
    # 2、voc格式的xml标签文件路径
    xml_files1 = r'./xml_labelf'
    # 3、转化为yolo格式的txt标签文件存储路径
    save_txt_files1 = r'./yolo_label'
 
    convert_annotation(xml_files1, save_txt_files1, classes)

Divide training set, test set, validation set

# 将图片和标注数据按比例切分为 训练集和测试集
import shutil
import random
import os
 
# 原始路径
image_original_path = "C:/Users/A/Desktop/datasets/images/"
label_original_path = "C:/Users/A/Desktop/datasets/labels/"
 
cur_path = os.getcwd()
 
# 训练集路径
train_image_path = os.path.join(cur_path, "datasets/defect/images/train/")
train_label_path = os.path.join(cur_path, "datasets/defect/labels/train/")
 
# 验证集路径
val_image_path = os.path.join(cur_path, "datasets/defect/images/val/")
val_label_path = os.path.join(cur_path, "datasets/defect/labels/val/")
 
# 测试集路径
test_image_path = os.path.join(cur_path, "datasets/defect/images/test/")
test_label_path = os.path.join(cur_path, "datasets/defect/labels/test/")
 
# 训练集目录
list_train = os.path.join(cur_path, "datasets/defect/train.txt")
list_val = os.path.join(cur_path, "datasets/defect/val.txt")
list_test = os.path.join(cur_path, "datasets/defect/test.txt")
 
train_percent = 0.6
val_percent = 0.2
test_percent = 0.2
 
 
def del_file(path):
    for i in os.listdir(path):
        file_data = path + "\\" + i
        os.remove(file_data)
 
 
def mkdir():
    if not os.path.exists(train_image_path):
        os.makedirs(train_image_path)
    else:
        del_file(train_image_path)
    if not os.path.exists(train_label_path):
        os.makedirs(train_label_path)
    else:
        del_file(train_label_path)
 
    if not os.path.exists(val_image_path):
        os.makedirs(val_image_path)
    else:
        del_file(val_image_path)
    if not os.path.exists(val_label_path):
        os.makedirs(val_label_path)
    else:
        del_file(val_label_path)
 
    if not os.path.exists(test_image_path):
        os.makedirs(test_image_path)
    else:
        del_file(test_image_path)
    if not os.path.exists(test_label_path):
        os.makedirs(test_label_path)
    else:
        del_file(test_label_path)
 
 
def clearfile():
    if os.path.exists(list_train):
        os.remove(list_train)
    if os.path.exists(list_val):
        os.remove(list_val)
    if os.path.exists(list_test):
        os.remove(list_test)
 
 
def main():
    mkdir()
    clearfile()
 
    file_train = open(list_train, 'w')
    file_val = open(list_val, 'w')
    file_test = open(list_test, 'w')
 
    total_txt = os.listdir(label_original_path)
    num_txt = len(total_txt)
    list_all_txt = range(num_txt)
 
    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 = [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 = image_original_path + name + '.jpg'
        srcLabel = label_original_path + name + ".txt"
 
        if i in train:
            dst_train_Image = train_image_path + name + '.jpg'
            dst_train_Label = train_label_path + name + '.txt'
            shutil.copyfile(srcImage, dst_train_Image)
            shutil.copyfile(srcLabel, dst_train_Label)
            file_train.write(dst_train_Image + '\n')
        elif i in val:
            dst_val_Image = val_image_path + name + '.jpg'
            dst_val_Label = val_label_path + name + '.txt'
            shutil.copyfile(srcImage, dst_val_Image)
            shutil.copyfile(srcLabel, dst_val_Label)
            file_val.write(dst_val_Image + '\n')
        else:
            dst_test_Image = test_image_path + name + '.jpg'
            dst_test_Label = test_label_path + name + '.txt'
            shutil.copyfile(srcImage, dst_test_Image)
            shutil.copyfile(srcLabel, dst_test_Label)
            file_test.write(dst_test_Image + '\n')
 
    file_train.close()
    file_val.close()
    file_test.close()
 
 
if __name__ == "__main__":
    main()

Get path

import os
paths= "./images/test/"
f=open('test.txt', 'w')
filenames=os.listdir(paths)
filenames.sort()
for filename in filenames:
 
    out_path="D:/jmcode/2/yolov7-main/datasets/findcontact/images/test/" + filename
    print(out_path)
    f.write(out_path+'\n')
f.close()

import os
paths= "./images/train/"
f=open('train.txt', 'w')
filenames=os.listdir(paths)
filenames.sort()
for filename in filenames:
 
    out_path="D:/jmcode/2/yolov7-main/datasets/findcontact/images/train/" + filename
    print(out_path)
    f.write(out_path+'\n')
f.close()

import os
paths= "./images/val/"
f=open('val.txt', 'w')
filenames=os.listdir(paths)
filenames.sort()
for filename in filenames:
 
    out_path="D:/jmcode/2/yolov7-main/datasets/findcontact/images/val/" + filename
    print(out_path)
    f.write(out_path+'\n')
f.close()