赞
踩
参考我之前的链接来制作制作自己的PASCAL VOC2007格式的数据集(二)
import os import random trainval_percent = 0.9 train_percent = 0.9 xmlfilepath = 'Annotations' txtsavepath = 'ImageSets' 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(txtsavepath + '/trainval.txt', 'w') ftest = open(txtsavepath + '/test.txt', 'w') ftrain = open(txtsavepath + '/train.txt', 'w') fval = open(txtsavepath + '/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()
运行结果如下:
import xml.etree.ElementTree as ET import pickle import os from os import listdir, getcwd from os.path import join sets = ['train', 'test','val'] classes = ['crazing', 'inclusion', 'patches','pitted_surface', 'rolled-in_scale','scratches'] 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(image_id): in_file = open('data/Annotations/%s.xml' % (image_id)) 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 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)) bb = convert((w, h), b) out_file.write(str(cls_id) + " " + " ".join([str(a) for a in bb]) + '\n') wd = getcwd() print(wd) for image_set in sets: if not os.path.exists('data/labels/'): os.makedirs('data/labels/') image_ids = open('data/ImageSets/%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('data/images/%s.jpg\n' % (image_id)) convert_annotation(image_id) list_file.close()
运行结果如下:
tips: 这里是voc2yolo哈不是xml2yolo!!所以运行代码前检查一下自己的数据标注的格式,一定要是pascalvoc格式的xml哦,标签有difficult
等的
参考我之前写的博客改就行,很简单
YOLOv5超详细的入门级教程(训练篇)(一)——训练自制数据集(识别鱼类)
第一次训练,只设置了最基本的
epoch 200
batch-size 8
Copyright © 2003-2013 www.wpsshop.cn 版权所有,并保留所有权利。