yolo voc_label 源码分析

import xml.etree.ElementTree as ET

import pickle

import os

from os import listdir, getcwd

from os.path import join









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



# 20类

classes = ["aeroplane", "bicycle", "bird", "boat", "bottle", "bus", "car", "cat", "chair", "cow", "diningtable", "dog",

           "horse", "motorbike", "person", "pottedplant", "sheep", "sofa", "train", "tvmonitor"]



# size w,h

# box x-min,x-max,y-min,y-max

def convert(size, box):

    dw = 1. / size[0]

    dh = 1. / size[1]

    x = (box[0] + box[1]) / 2.0 # 中心点位置

    y = (box[2] + box[3]) / 2.0

    w = box[1] - box[0]

    h = box[3] - box[2]

    x = x * dw

    w = w * dw

    y = y * dh

    h = h * dh # 全部转化为相对坐标

    return (x, y, w, h)





def convert_annotation(year, image_id):

    # 找到2个同样的文件

    in_file = open('VOCdevkit/VOC%s/Annotations/%s.xml' % (year, image_id))

    out_file = open('VOCdevkit/VOC%s/labels/%s.txt' % (year, 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: # difficult ==1 的不要了

            continue

        cls_id = classes.index(cls) # 排在第几位

        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))

        # 传入的是w,h 与框框的周边

        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:

    # ('2012', 'train') 循环5次

    # 创建目录 一次性

    if not os.path.exists('VOCdevkit/VOC%s/labels/' % (year)):

        os.makedirs('VOCdevkit/VOC%s/labels/' % (year))



    # 图片的id数据

    image_ids = open('VOCdevkit/VOC%s/ImageSets/Main/%s.txt' % (year, image_set)).read().strip().split()



    # 结果写入这个文件

    list_file = open('%s_%s.txt' % (year, image_set), 'w')



    for image_id in image_ids:

        list_file.write('%s/VOCdevkit/VOC%s/JPEGImages/%s.jpg\n' % (wd, year, image_id)) # 补全路径

        convert_annotation(year, image_id)

    list_file.close()