万能模板计算ｍAP(一)数据集制作voc格式

1.  首先根据自己情况制作测试结果数据集格式如下：

　

我的数据是两分类，所以只有一个标签，按自己情况修改class

ＧＴ数据集是ｘｍｌ转换为ｔｘｔ,转换代码附在下面，建立文件夹然后在此文件夹下建立文件夹：，在此文件夹下建立：

，将xml文件放在第一个文件夹下，ImageSet下建立文件夹Ｍain，用于存放生成的train.txt,trainval.txt等文档。将以下程序放于桌面，运行。

import xml.etree.ElementTree as ET
import pickle
import os
from os import listdir, getcwd
from os.path import join

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

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


def convert(size, box):
    dw = 1./size[0]
    dh = 1./size[1]
    x = (box[0] + box[1])/2.0
    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

    return (x,y,w,h)

def convert_annotation(year, image_id):
    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)
    filename = root.find('filename').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 = cls
        xmlbox = obj.find('bndbox')
        b = (float(xmlbox.find('xmin').text), float(xmlbox.find('ymin').text), float(xmlbox.find('xmax').text), float(xmlbox.find('ymax').text))
        #bb = convert((w,h), b)＃视需求而修改，这段是保留w,h,去掉xmax,ymax
        out_file.write(str(cls_id)+" "+" ".join([str(a) for a in b]) +" "+'\n')

wd = getcwd()

for year, image_set in sets:
    if not os.path.exists('VOCdevkit/VOC%s/labels/'%(year)):
        os.makedirs('VOCdevkit/VOC%s/labels/'%(year))
    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\n'%(wd, year, image_id))
        convert_annotation(year, image_id)
    list_file.close()