二 . voc 数据集转yolov5

一. 数据集拆分 train&val

根据第一步得到如下数据集组成结构:

 由下代码变成:

import xml.etree.ElementTree as ET
import os


sets = ['train', 'val']  # 需要转换训练集. 验证集
Root = '../datasets/voc-end/' # 数据集目录
classes = ["person", "chef_uniform", "voc_clothes"]  # 修改为自己的label


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 = round(x*dw, 6)
    w = round(w*dw, 6)
    y = round(y*dh, 6)
    h = round(h*dh, 6)
    return (x, y, w, h)


def convert_annotation(image_set, image_id):
    in_file = open(Root + 'annotations/' + image_set + '/%s.xml' % (image_id))
    out_file = open(Root + 'labels/' + image_set + '/%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))
        bb = convert((w, h), b)
        out_file.write(str(cls_id) + " " + " ".join([str(a) for a in bb]) + '\n')


if __name__ == '__main__':
    for image_set in sets:    # train / val
        if not os.path.exists(Root + 'labels/'):
            os.makedirs(Root + 'labels/')  
        if not os.path.exists(Root + 'labels/' + image_set + '/'):
            os.makedirs(Root + 'labels/' + image_set + '/')
              
        image_ids = open(Root + '%s.txt' % (image_set)).read().strip().split()   # 按行读取

        for image_id in image_ids:
            print(image_id)
            convert_annotation(image_set, image_id)