在网上找了一大圈YOLOV5数据集的制作,都没有合适的,不是流程太复杂就是给出的代码有问题。所以我在这里记录一下YOLOV5数据集简单的制作过程。
首先一共要准备4样东西:
准备材料
Annotations
这里是标注信息,我用的是labelimg。Annotations内容
images
存放了标注的图像,最好都是jpg格式的。images内容
split_train_val.py
- # coding:utf-8
-
- import os
- import random
- import argparse
-
- parser = argparse.ArgumentParser()
- #xml文件的地址,根据自己的数据进行修改 xml一般存放在Annotations下
- parser.add_argument('--xml_path', default=r'Annotations', type=str, help='input xml label path')
- #数据集的划分,没有这个文件夹的话,程序会自动创建
- parser.add_argument('--txt_path', default=r'ImageSets', 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_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:
- if i in train:
- file_train.write(name)
- else:
- file_val.write(name)
- file_train.close()
- file_val.close()
- import xml.etree.ElementTree as ET
- import pickle
- import os
- from os import listdir, getcwd
- from os.path import join
-
- sets = ['train', 'val']
-
- classes = ["car", "person"] #根据自己的项目改
-
-
- 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(r'Annotations/%s.xml' % (image_id), 'r', encoding="UTF-8")
- out_file = open(r'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('labels/'):
- os.makedirs('labels/')
- image_ids = open(r'ImageSets/%s.txt' % (image_set)).read().strip().split()
- list_file = open(r'%s.txt' % (image_set), 'w')
- for image_id in image_ids:
- list_file.write(r'C:/F/cardata/images/%s.jpg' % (image_id)) #写入绝对路径
- list_file.write('\n')
- convert_annotation(image_id)
- list_file.close()
-
然后依次运行split_train_val.py和voc_label.py就行。
注意:唯一2处需要改的就是voc_label.py我写了注释的地方。