【深度学习】数据集划分、数据集格式转换一文带你搞定！复制就能用！！！

1、数据集划分

import os, shutil, random
random.seed(0)
import numpy as np
from sklearn.model_selection import train_test_split

val_size = 0.1
test_size = 0.2
postfix = 'jpg'
imgpath = 'VOCdevkit/JPEGImages'
txtpath = 'VOCdevkit/txt'

os.makedirs('images/train', exist_ok=True)
os.makedirs('images/val', exist_ok=True)
os.makedirs('images/test', exist_ok=True)
os.makedirs('labels/train', exist_ok=True)
os.makedirs('labels/val', exist_ok=True)
os.makedirs('labels/test', exist_ok=True)

listdir = np.array([i for i in os.listdir(txtpath) if 'txt' in i])
random.shuffle(listdir)
train, val, test = listdir[:int(len(listdir) * (1 - val_size - test_size))], listdir[int(len(listdir) * (1 - val_size - test_size)):int(len(listdir) * (1 - test_size))], listdir[int(len(listdir) * (1 - test_size)):]
print(f'train set size:{len(train)} val set size:{len(val)} test set size:{len(test)}')

for i in train:
    shutil.copy('{}/{}.{}'.format(imgpath, i[:-4], postfix), 'images/train/{}.{}'.format(i[:-4], postfix))
    shutil.copy('{}/{}'.format(txtpath, i), 'labels/train/{}'.format(i))

for i in val:
    shutil.copy('{}/{}.{}'.format(imgpath, i[:-4], postfix), 'images/val/{}.{}'.format(i[:-4], postfix))
    shutil.copy('{}/{}'.format(txtpath, i), 'labels/val/{}'.format(i))

for i in test:
    shutil.copy('{}/{}.{}'.format(imgpath, i[:-4], postfix), 'images/test/{}.{}'.format(i[:-4], postfix))
    shutil.copy('{}/{}'.format(txtpath, i), 'labels/test/{}'.format(i))

2、xml转txt格式

xml2txt

import xml.etree.ElementTree as ET
import os, cv2
import numpy as np
from os import listdir
from os.path import join

classes = []

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(xmlpath, xmlname):
    with open(xmlpath, "r", encoding='utf-8') as in_file:
        txtname = xmlname[:-4] + '.txt'
        txtfile = os.path.join(txtpath, txtname)
        tree = ET.parse(in_file)
        root = tree.getroot()
        filename = root.find('filename')
        img = cv2.imdecode(np.fromfile('{}/{}.{}'.format(imgpath, xmlname[:-4], postfix), np.uint8), cv2.IMREAD_COLOR)
        h, w = img.shape[:2]
        res = []
        for obj in root.iter('object'):
            cls = obj.find('name').text
            if cls not in classes:
                classes.append(cls)
            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)
            res.append(str(cls_id) + " " + " ".join([str(a) for a in bb]))
        if len(res) != 0:
            with open(txtfile, 'w+') as f:
                f.write('\n'.join(res))


if __name__ == "__main__":
    postfix = 'jpg'
    imgpath = 'VOCdevkit/JPEGImages'
    xmlpath = 'VOCdevkit/Annotations'
    txtpath = 'VOCdevkit/txt'
    
    if not os.path.exists(txtpath):
        os.makedirs(txtpath, exist_ok=True)
    
    list = os.listdir(xmlpath)
    error_file_list = []
    for i in range(0, len(list)):
        try:
            path = os.path.join(xmlpath, list[i])
            if ('.xml' in path) or ('.XML' in path):
                convert_annotation(path, list[i])
                print(f'file {list[i]} convert success.')
            else:
                print(f'file {list[i]} is not xml format.')
        except Exception as e:
            print(f'file {list[i]} convert error.')
            print(f'error message:\n{e}')
            error_file_list.append(list[i])
    print(f'this file convert failure\n{error_file_list}')
    print(f'Dataset Classes:{classes}')

3、yolo转coco格式

import os
import cv2
import json
from tqdm import tqdm
from sklearn.model_selection import train_test_split
import argparse

# visdrone2019
classes = ['pedestrain', 'people', 'bicycle', 'car', 'van', 'truck', 'tricycle', 'awning-tricycle', 'bus', 'motor']

parser = argparse.ArgumentParser()
parser.add_argument('--image_path', default='',type=str, help="path of images")
parser.add_argument('--label_path', default='',type=str, help="path of labels .txt")
parser.add_argument('--save_path', default='data.json', type=str, help="if not split the dataset, give a path to a json file")
arg = parser.parse_args()

def yolo2coco(arg):
    print("Loading data from ", arg.image_path, arg.label_path)

    assert os.path.exists(arg.image_path)
    assert os.path.exists(arg.label_path)
    
    originImagesDir = arg.image_path                                   
    originLabelsDir = arg.label_path
    # images dir name
    indexes = os.listdir(originImagesDir)

    dataset = {'categories': [], 'annotations': [], 'images': []}
    for i, cls in enumerate(classes, 0):
        dataset['categories'].append({'id': i, 'name': cls, 'supercategory': 'mark'})
    
    # 标注的id
    ann_id_cnt = 0
    for k, index in enumerate(tqdm(indexes)):
        # 支持 png jpg 格式的图片.
        txtFile = f'{index[:index.rfind(".")]}.txt'
        stem = index[:index.rfind(".")]
        # 读取图像的宽和高
        try:
            im = cv2.imread(os.path.join(originImagesDir, index))
            height, width, _ = im.shape
        except Exception as e:
            print(f'{os.path.join(originImagesDir, index)} read error.\nerror:{e}')
        # 添加图像的信息
        if not os.path.exists(os.path.join(originLabelsDir, txtFile)):
            # 如没标签，跳过，只保留图片信息.
            continue
        dataset['images'].append({'file_name': index,
                            'id': stem,
                            'width': width,
                            'height': height})
        with open(os.path.join(originLabelsDir, txtFile), 'r') as fr:
            labelList = fr.readlines()
            for label in labelList:
                label = label.strip().split()
                x = float(label[1])
                y = float(label[2])
                w = float(label[3])
                h = float(label[4])

                # convert x,y,w,h to x1,y1,x2,y2
                H, W, _ = im.shape
                x1 = (x - w / 2) * W
                y1 = (y - h / 2) * H
                x2 = (x + w / 2) * W
                y2 = (y + h / 2) * H
                # 标签序号从0开始计算, coco2017数据集标号混乱，不管它了。
                cls_id = int(label[0])   
                width = max(0, x2 - x1)
                height = max(0, y2 - y1)
                dataset['annotations'].append({
                    'area': width * height,
                    'bbox': [x1, y1, width, height],
                    'category_id': cls_id,
                    'id': ann_id_cnt,
                    'image_id': stem,
                    'iscrowd': 0,
                    # mask, 矩形是从左上角点按顺时针的四个顶点
                    'segmentation': [[x1, y1, x2, y1, x2, y2, x1, y2]]
                })
                ann_id_cnt += 1

    # 保存结果
    with open(arg.save_path, 'w') as f:
        json.dump(dataset, f)
        print('Save annotation to {}'.format(arg.save_path))

if __name__ == "__main__":
    yolo2coco(arg)