(训练三)王朗自然保护区---数据集部分补充说明:计算xml文件里面目标数量 & 生成训练和测试的txt文件

1 计算xml文件里面目标数量

# -*- coding:utf-8 -*-
import os
import xml.etree.ElementTree as ET
import numpy as np

np.set_printoptions(suppress=True, threshold=10000000)
import matplotlib
from PIL import Image


def parse_obj(xml_path, filename):
    tree = ET.parse(xml_path + filename)
    objects = []
    for obj in tree.findall('object'):
        obj_struct = {}
        obj_struct['name'] = obj.find('name').text
        objects.append(obj_struct)
    return objects


def read_image(image_path, filename):
    im = Image.open(image_path + filename)
    W = im.size[0]
    H = im.size[1]
    area = W * H
    im_info = [W, H, area]
    return im_info


if __name__ == '__main__':
    xml_path = 'Annotations/'
    filenamess = os.listdir(xml_path)
    filenames = []
    for name in filenamess:
        name = name.replace('.xml', '')
        filenames.append(name)
    recs = {}
    obs_shape = {}
    classnames = []
    num_objs = {}
    obj_avg = {}
    for i, name in enumerate(filenames):
        recs[name] = parse_obj(xml_path, name + '.xml')
    for name in filenames:
        for object in recs[name]:
            if object['name'] not in num_objs.keys():
                num_objs[object['name']] = 1
            else:
                num_objs[object['name']] += 1
            if object['name'] not in classnames:
                classnames.append(object['name'])
    sum = 0
    for name in classnames:
        print('{}:{}个'.format(name, num_objs[name]))
        sum += num_objs[name]

    print('信息统计算完毕。')
    print('总目标数:', sum)

如图位置放置-运行就可以统计xml文件里面目标数量

对应修改datasets/pascalvoc_2007.py 文件里面的数值即可　　（注意这里的NUM_CLASSES=14）

 

2 放在如图路径-生成test.txt等文件

import os
import random

trainval_percent = 0.8
train_percent = 0.7
xmlfilepath = 'Annotations'
txtsavepath = 'ImageSets\Main'
total_xml = os.listdir(xmlfilepath)

num = len(total_xml)
list = range(num)
tv = int(num * trainval_percent)
tr = int(tv * train_percent)
trainval = random.sample(list, tv)
train = random.sample(trainval, tr)

ftrainval = open('ImageSets/Main/trainval.txt', 'w')
ftest = open('ImageSets/Main/test.txt', 'w')
ftrain = open('ImageSets/Main/train.txt', 'w')
fval = open('ImageSets/Main/val.txt', 'w')

for i in list:
    name = total_xml[i][:-4] + '\n'
    if i in trainval:
        ftrainval.write(name)
        if i in train:
            ftrain.write(name)
        else:
            fval.write(name)
    else:
        ftest.write(name)

ftrainval.close()
ftrain.close()
fval.close()
ftest.close()