使用ppyoloe训练voc数据集（自制的）详细教程

一、数据集准备工作:
Voc数据集的格式：

通过labelimg标注后的数据集如图所示
分别存放原图与xml标注文件

二、在ppdetection的工程下面找到dataset文件夹

其中有许多的参考数据的格式样例
在dataset文件夹下，新建数据集文件夹（自己命名aaaa）
将制作好的数据集复制近来，格式如下：

三、在pcb文件下新建脚本，使用脚本生成代训练的文件

import argparse
import random
import re
from pathlib import Path
from matplotlib import pyplot as plt

annotations_name = 'Annotations'
jpegimages_name = 'JPEGImages'
trainval_name = 'trainval.txt'
text_file_name = 'test.txt'
val_file_name = 'val.txt'


def write_file(datas, file):
    results = []
    for data in datas:
        annotation = Path(annotations_name, f'{data}.xml')
        image = Path(jpegimages_name, f'{data}.jpg')
        result = f'{image} {annotation}'
        results.append(result)
    with file.open('w')as f:
        f.write("\n".join(results))
    print(file, "success")


def make_paddle_voc(dataset):
    dataset = Path(dataset)
    assert dataset.is_dir(), "Error dataset path"
    annotations_path = dataset / annotations_name
    images_path = dataset / jpegimages_name
    if not (annotations_path.is_dir() and images_path.is_dir()):
        print("Please use the following structure:")
        print(f"{dataset.name}")
        print(f'\t{annotations_name}\n\t\t|--00001.xml\n\t\t|--00002.xml')
        print(f'\t{jpegimages_name}\n\t\t|--00001.jpg\n\t\t|--00002.jpg')
        raise RuntimeError(f'Error {jpegimages_name} or {annotations_name} dir')
    paddle_path = dataset / 'paddle'
    paddle_path.mkdir(exist_ok=True, parents=True)
    trainval_path = paddle_path / trainval_name
    test_path = paddle_path / text_file_name
    val_path = paddle_path / val_file_name
    annotations = annotations_path.glob('*.xml')
    images = images_path.glob('*.jpg')
    images_list = [image.name for image in images]
    annotations_list = []
    for annotation in annotations:
        image = annotation.with_suffix('.jpg').name
        assert image in images_list, f"{annotation.name} has no image file"
        annotations_list.append(annotation.stem)
    random.shuffle(annotations_list)
    per = round(len(annotations_list) / 10)
    trainval = annotations_list[:per * 7]  # 此处切分比例为8:1:1 可行修改比例
    test = annotations_list[per * 7:per * 9]
    val = annotations_list[per * 9:]
    write_file(trainval, trainval_path)
    write_file(test, test_path)
    write_file(val, val_path)


def check_labels(dataset):
    dataset = Path(dataset)
    annotations_path = dataset / annotations_name
    class_list = {}
    for annotation_path in annotations_path.glob('*.xml'):
        with annotation_path.open('r')as f:
            names = re.findall(r'<name>(.+?)</name>', f.read())
            for name in names:
                if name not in class_list.keys():
                    class_list[name] = 0
                class_list[name] += 1
    class_list = dict(sorted(class_list.items()))
    label_list = dataset / 'label_list.txt'
    with label_list.open('w')as f:
        f.write('\n'.join(class_list.keys()))
    fig, ax = plt.subplots()
    [ax.text(a, b + 1, b, ha='center', va='bottom') for a, b in class_list.items()]
    plt.bar(*zip(*class_list.items()))
    plt.xticks(rotation=270)
    plt.title('Detection category distribution')
    plt.xlabel('Class')
    plt.ylabel('Number')
    plt.tight_layout()
    plt.savefig(f"{dataset / '类别分布.jpg'}", format="jpg")
    print(f"Save as {dataset / '类别分布.jpg'}")
    print(f"共{len(class_list)}类")


if __name__ == '__main__':
    parser = argparse.ArgumentParser()
    parser.add_argument('--dataset', required=True, help='input dataset path, necessary parameter')

    opt = parser.parse_args()
    # check_dataset(opt.dataset)
    make_paddle_voc(opt.dataset)
    check_labels(opt.dataset)

四、修改代码中的配置文件