yolo格式、voc格式、coco格式相互转换(xml，json，txt)

yolo转voc

keras版yolov3训练格式是name box class这种形式，转voc格式使用一下代码，根据别人的代码改了一点。list.txt为yolo的标签，转换的voc格式的标签为.xml文件，都存放在Annotations下。

from xml.dom.minidom import Document
from lxml.etree import Element, SubElement, tostring
import pprint
from xml.dom.minidom import parseString
import cv2
class XmlMaker:

    def __init__(self,txtpath,xmlpath):
        self.txtPath = txtpath
        self.xmlPath = xmlpath
        self.txtList = []

    def readtxt(self):
        jpg = []
        txtfile = open(self.txtPath,"r",encoding='gbk',errors='ignore')
        self.txtList = txtfile.readlines()
        for i in self.txtList:
            jpg = i.strip().split(" ")[0]
            xys = i.strip().split(" ")[1:]
            #print(xys)
            node_root = Element('annotation')
            node_folder = SubElement(node_root, 'folder')
            node_folder.text = 'VOC2012'
            node_filename = SubElement(node_root, 'filename')
            node_filename.text = jpg

            img = cv2.imread(jpg)
            shape = img.shape

            node_size = SubElement(node_root, 'size')
            node_width = SubElement(node_size, 'width')

            node_width.text = str(shape[1])

            node_height = SubElement(node_size, 'height')
            node_height.text = str(shape[0])

            node_depth = SubElement(node_size, 'depth')
            node_depth.text = '3'

            for xy in xys:
                list_xy = xy.split(",")
                for tmp in list_xy:
                    x_min = list_xy[0]
                    y_min = list_xy[1]
                    x_max = list_xy[2]
                    y_max = list_xy[3]
                    classes = list_xy[4]
                    node_object = SubElement(node_root, 'object')
                    node_name = SubElement(node_object, 'name')
                    node_name.text = 'person'
                    node_difficult = SubElement(node_object, 'difficult')
                    node_difficult.text = '0'
                    node_bndbox = SubElement(node_object, 'bndbox')
                    node_xmin = SubElement(node_bndbox, 'xmin')
                    node_xmin.text = str(x_min)
                    node_ymin = SubElement(node_bndbox, 'ymin')
                    node_ymin.text = str(y_min)
                    node_xmax = SubElement(node_bndbox, 'xmax')
                    node_xmax.text = str(x_max)
                    node_ymax = SubElement(node_bndbox, 'ymax')
                    node_ymax.text = str(y_max)


            xml = tostring(node_root, pretty_print=True)  # 格式化显示，该换行的换行
            xml_name = jpg.split("/")[-1][:-4]+".xml"
            print(xml_name)
            with open(self.xmlPath+"/"+xml_name, "wb") as f:
                f.write(xml)
                f.close()

if __name__ == "__main__":
    read =XmlMaker("list.txt","Annotations")
    read.readtxt()

voc转yolo

import xml.etree.ElementTree as ET
from os import getcwd

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

classes = ["cola","milk tea","ice tea","beer","shampoo","toothpaste","soap","pear","apple","orange"]

def convert_annotation(year, image_id, list_file):
    in_file = open('VOCdevkit/VOC%s/Annotations/%s.xml'%(year, image_id))
    tree=ET.parse(in_file)
    root = tree.getroot()

    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 = (int(xmlbox.find('xmin').text), int(xmlbox.find('ymin').text), int(xmlbox.find('xmax').text), int(xmlbox.find('ymax').text))
        list_file.write(" " + ",".join([str(a) for a in b]) + ',' + str(cls_id))

wd = getcwd()

for year, image_set in sets:
    image_ids = open('VOCdevkit/VOC%s/ImageSets/Main/%s.txt'%(year, image_set)).read().strip().split()
    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'%(wd, year, image_id))
        convert_annotation(year, image_id, list_file)
        list_file.write('\n')
    list_file.close()

coco转yolo

import json
from collections import defaultdict

name_box_id = defaultdict(list)
id_name = dict()
f = open(
    "coco/annotations/instances_train2014.json",
    encoding='utf-8')
data = json.load(f)

annotations = data['annotations']
for ant in annotations:
    id = ant['image_id']
    name = 'coco/train2014/COCO_train2014_%012d.jpg' % id
    cat = ant['category_id']

    if cat >= 1 and cat <= 11:
        cat = cat - 1
    elif cat >= 13 and cat <= 25:
        cat = cat - 2
    elif cat >= 27 and cat <= 28:
        cat = cat - 3
    elif cat >= 31 and cat <= 44:
        cat = cat - 5
    elif cat >= 46 and cat <= 65:
        cat = cat - 6
    elif cat == 67:
        cat = cat - 7
    elif cat == 70:
        cat = cat - 9
    elif cat >= 72 and cat <= 82:
        cat = cat - 10
    elif cat >= 84 and cat <= 90:
        cat = cat - 11

    name_box_id[name].append([ant['bbox'], cat])

f = open('train.txt', 'w')
for key in name_box_id.keys():
    f.write(key)
    box_infos = name_box_id[key]
    for info in box_infos:
        x_min = int(info[0][0])
        y_min = int(info[0][1])
        x_max = x_min + int(info[0][2])
        y_max = y_min + int(info[0][3])

        box_info = " %d,%d,%d,%d,%d" % (
            x_min, y_min, x_max, y_max, int(info[1]))
        f.write(box_info)
    f.write('\n')
f.close()