yolo训练voc数据集划分

1、划分数据集比例split_train_val.py

import os
import random
import argparseparser = argparse.ArgumentParser()
#xml文件的地址或者label的地址，根据自己的数据进行修改 xml一般存放在Annotations下 主要是获取每个数据的地址名字
parser.add_argument('--xml_path', default='/home/jovyan/exp_2607/dataset-445/yolo_labels', type=str, help='input xml label path')
#数据集的划分保存的位置，地址一般选择自己数据下的ImageSets/Main
parser.add_argument('--txt_path', default='/home/jovyan/exp_2607/data/mydata/ImageSets/Main', type=str, help='output txt label path')
opt = parser.parse_args()trainval_percent = 1.0  # 训练集和验证集所占比例。 这里没有划分测试集
train_percent = 0.7     # 训练集所占比例，可自己进行调整
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.xml_to_yolo

import xml.etree.ElementTree as ET
import os
from os import getcwdsets = ['train', 'val', 'test']
classes = ["door_close", "door_open", "billboard", "tear up","person", "forklift", "shovel loader", "nothing forklift","conveyer belt"]  # 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 - 1y = (box[2] + box[3]) / 2.0 - 1w = box[1] - box[0]h = box[3] - box[2]x = x * dww = w * dwy = y * dhh = h * dhreturn x, y, w, hdef convert_annotation(image_id):in_file = open('/home/jovyan/exp_2529/data/mydata/xml/%s.xml' % (image_id), encoding='UTF-8')out_file = open('/home/jovyan/exp_2529/data/mydata/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').textcls = obj.find('name').textif cls not in classes or int(difficult) == 1:continuecls_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 = wif b4 > h:b4 = hb = (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:image_ids = open('/home/jovyan/exp_2607/data/mydata/ImageSets/Main/%s.txt' % (image_set)).read().strip().split()if not os.path.exists('/home/jovyan/exp_2607/dataset_copy/'):os.makedirs('/home/jovyan/exp_2607/dataset_copy/')if not os.path.exists('/home/jovyan/exp_2607/dataset_copy/images'):os.symlink('/home/jovyan/exp_2607/dataset-445/images', '/home/jovyan/exp_2607/dataset_copy/images')if not os.path.exists('/home/jovyan/exp_2607/dataset_copy/labels'):os.symlink('/home/jovyan/exp_2607/dataset-445/yolo_labels', '/home/jovyan/exp_2607/dataset_copy/labels')if not os.path.exists('/home/jovyan/exp_2607/data/mydata/dataSet_path/'):os.makedirs('/home/jovyan/exp_2607/data/mydata/dataSet_path/')list_file = open('/home/jovyan/exp_2607/data/mydata/dataSet_path/%s.txt' % (image_set), 'w')# 这行路径不需更改，这是相对路径for image_id in image_ids:list_file.write('/home/jovyan/exp_2607/dataset_copy/images/%s.png\n' % (image_id))# convert_annotation(image_id)  存在xml转txt文件的时候才使用  如果数据有现成的txt文件就不用运行list_file.close()

3.mydata.yaml

train: /home/jovyan/exp_2607/data/mydata/dataSet_path/train.txt  
val: /home/jovyan/exp_2607/data/mydata/dataSet_path/val.txt  
test: /home/jovyan/exp_2607/data/mydata/dataSet_path/test.txt  # number of classes
nc: 9# class names
names: [ 'door_close', 'door_open', 'billboard', 'tear up', 'person', 'forklift', 'shovel loader', 'nothing forklift', 'conveyer belt']