废话不多说,直接上代码!
1.生成imagesets/main文件下的
import os import random import argparse parser = argparse.ArgumentParser() parser.add_argument('--xml_path', default='Annotations', type=str, help='input xml label path') parser.add_argument('--txt_path', default='ImageSets/Main', type=str, help='output txt label path') opt = parser.parse_args() trainval_percent = 1.0 train_percent = 0.9 xmlfilepath = opt.xml_path txtsavepath = opt.txt_path total_xml = os.listdir(xmlfilepath) if not os.path.exists(txtsavepath): os.makedirs(txtsavepath) num = len(total_xml) list_index = range(num) tv = int(num * trainval_percent) tr = int(tv * train_percent) trainval = random.sample(list_index, tv) train = random.sample(trainval, tr) file_trainval = open(txtsavepath + '/trainval.txt', 'w') file_test = open(txtsavepath + '/test.txt', 'w') file_train = open(txtsavepath + '/train.txt', 'w') file_val = open(txtsavepath + '/val.txt', 'w') for i in list_index: name = total_xml[i][:-4] + '\n' if i in trainval: file_trainval.write(name) if i in train: file_train.write(name) else: file_val.write(name) else: file_test.write(name) file_trainval.close() file_train.close() file_val.close() file_test.close()
2.生成标签文件
import xml.etree.ElementTree as ET import os from os import getcwd sets = ['train', 'val', 'test'] classes = ["hat",'person'] # 改成自己的类别 abs_path = os.getcwd() print(abs_path) def convert(size, box): dw = 1. / (size[0]) dh = 1. / (size[1]) 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(image_id): in_file = open('./data/Annotations/%s.xml' % (image_id), encoding='UTF-8') out_file = open('./data/labels/%s.txt' % (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 # 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 = (float(xmlbox.find('xmin').text), float(xmlbox.find('xmax').text), float(xmlbox.find('ymin').text), float(xmlbox.find('ymax').text)) b1, b2, b3, b4 = b # 标注越界修正 if b2 > w: b2 = w if b4 > h: b4 = h b = (b1, b2, b3, b4) bb = convert((w, h), b) out_file.write(str(cls_id) + " " + " ".join([str(a) for a in bb]) + '\n') wd = getcwd() for image_set in sets: if not os.path.exists('./data/labels/'): os.makedirs('./data/labels/') image_ids = open('./data/ImageSets/Main/%s.txt' % (image_set)).read().strip().split() list_file = open('./data/%s.txt' % (image_set), 'w') for image_id in image_ids: list_file.write(abs_path + './data/images/%s.jpg\n' % (image_id)) convert_annotation(image_id) list_file.close()
年代久远兮,不知从何许?如有,请知汝,附君链接上
GAME OVER
如果理解错误,欢迎大家批评,及时纠正小琼的错误哦,真心感谢你的纠正!!!
如果小伙伴梦有疑问欢迎在评论区留言哦!!!
如果感觉不错的话!点个赞呗,不用客气!(O(∩_∩)O哈哈~)
欢迎和小伙伴梦一起学习,共同努力,加油!!!
转载链接:
原文链接:https://blog.csdn.net/m0_56654441/article/details/120855131