yolov3 训练voc2012 （一、转换成yolo的数据格式脚本的理解）

import xml.etree.ElementTree as ET
import pickle
import os
from os import listdir, getcwd
# getcwd 获得当前的工作地址的绝对路径

from os.path import join

sets=[('2012', 'train'), ('2012', 'val'), ('2007', 'train'), ('2007', 'val'), ('2007', 'test')]

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


def convert(size, box):  # size[w,h] box[xmin, xmax, ymin. ymax]
    dw = 1./(size[0])  # size[0] 为宽
    dh = 1./(size[1])  # size[1] 为高
    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(year, image_id):
    # 打开VOCdevkit/VOC2012/Annotations/2008_000008.xml
    in_file = open('VOCdevkit/VOC%s/Annotations/%s.xml'%(year, image_id))
    # 结果写入VOCdevkit/VOC2012/labels/2008_000008.xml
    out_file = open('VOCdevkit/VOC%s/labels/%s.txt'%(year, image_id), 'w')
    #  解析XML
    tree = ET.parse(in_file)
    # 获得根节点
    root = tree.getroot()
    # 找到size 值
    size = root.find('size')
    # 找到宽
    w = int(size.find('width').text)
    # 找到 boundingbox 的高
    h = int(size.find('height').text)

    #  找到"object" 的根节点
    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) # 获取标签名字的编号
        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))
        # 转化为yolov3 的数据格式
        bb = convert((w, h), b)
        out_file.write(str(cls_id) + " " + " ".join([str(a) for a in bb]) + '\n')

wd = getcwd()

for year, image_set in sets:
    if not os.path.exists('VOCdevkit/VOC%s/labels/'%(year)):   # VOCdevkit/VOC2012/labels 如果不存在
        os.makedirs('VOCdevkit/VOC%s/labels/'%(year))          # 创建文件夹
    # 打开 VOCdevkit/VOC2012/ImageSets/Main/train.txt  读取为列表  ["2008_000008","2008_000019", ...]
    image_ids = open('VOCdevkit/VOC%s/ImageSets/Main/%s.txt'%(year, image_set)).read().strip().split()
    # 写入2012_train.txt
    list_file = open('%s_%s.txt' % (year, image_set), 'w')
    for image_id in image_ids:
        # 将path/to/VOCdevkit/VOC2012/JPEGImages/2008_000008.jpg 写入 2012_train.txt
        list_file.write('%s/VOCdevkit/VOC%s/JPEGImages/%s.jpg\n'%(wd, year, image_id))
        # 转换为yolov3 的格式
        convert_annotation(year, image_id)
    list_file.close()

    1.得到train.txt 、val.txt 、test.txt
        1.1 打开 VOCdevkit/VOC2012/ImageSets/Main/train.txt  读取为列表  ["2008_000008","2008_000019", ...]
        1.2 将path/to/VOCdevkit/VOC2012/JPEGImages/2008_000008.jpg 写入 2012_train.txt 2012_val.txt
        在这三个文件夹中分别得到对应数据集的绝对路径
    2.得到标注文件
        2.1 打开图片对应的原始标注文件 VOCdevkit/VOC2012/Annotations/2008_000008.xml
        2.2 转换为yolo 的数据格式
        2.3 写入VOCdevkit/VOC2012/labels/2008_000008.xml中