YOLO模型训练VOC数据集设置说明

最新推荐文章于 2024-10-12 15:30:04 发布

Dehuan2024

最新推荐文章于 2024-10-12 15:30:04 发布

阅读量488

点赞数 13

文章标签：笔记

本文链接：https://blog.csdn.net/2201_75981172/article/details/131598041

版权

2024/8/29

前期准备

数据集文件结构如下

VOCdevkit

————VOC2007

————Annotations # 存放图片对应的xml文件，与JPEGImages图片名称一一对应

————ImageSets

————Main # 存放trainval.txt、train.txt、val.txt、test.txt，开始为空

————JPEGImages # 存放所有图片文件

新建文件

2. 数据集划分

将以下代码放入split_train_val.py里面

# -*- coding: utf-8 -*-
"""
Author:Dehuan
简介：分训练集、验证集和测试集，按照 8：1：1 的比例来分，训练集9，验证集1
"""
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='datasets/VOC2007/Annotations', type=str, help='input xml label path')
# 数据集的划分，地址选择自己数据下的ImageSets/Main
parser.add_argument('--txt_path', default='datasets/VOC2007/ImageSets/Main/', type=str, help='output txt label path')
opt = parser.parse_args()

train_percent = 0.9  # 训练集所占比例
val_percent = 0.1  # 验证集所占比例
 
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 = list(range(num))
 
t_train = int(num * train_percent)
t_val = int(num * val_percent)
 
train = random.sample(list, t_train)
num1 = len(train)
for i in range(num1):
    list.remove(train[i])
 
val_test = [i for i in list if not i in train]
val = random.sample(val_test, t_val)
num2 = len(val)
for i in range(num2):
    list.remove(val[i])
 
file_train = open(txtsavepath + '/train.txt', 'w')
file_val = open(txtsavepath + '/val.txt', 'w')
 
 
for i in train:
    name = total_xml[i][:-4] + '\n'
    file_train.write(name)
 
for i in val:
    name = total_xml[i][:-4] + '\n'
    file_val.write(name)

file_train.close()
file_val.close()

运行后

3 生成训练用的txt文件

将以下代码放入voc_label.py

# -*- coding: utf-8 -*-

import xml.etree.ElementTree as ET

import os


sets = ['train', 'val'] # 如果你的Main文件夹没有test.txt，就删掉'test'

# classes = ["a", "b"] # 改成自己的类别，VOC数据集有以下20类别

classes = ['Paaper', 'Rock','Scissors'] # class names

abs_path = os.getcwd()



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(abs_path + '/datasets/VOC2007/Annotations/%s.xml' % (image_id), encoding='UTF-8')

out_file = open(abs_path + '/datasets/VOC2007/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')



for image_set in sets:

if not os.path.exists(abs_path + '/datasets/VOC2007/labels/'):

os.makedirs(abs_path + '/datasets/VOC2007/labels/')



image_ids = open(abs_path + '/datasets/VOC2007/ImageSets/Main/%s.txt' % (image_set)).read().strip().split()

list_file = open(abs_path + '/datasets/VOC2007/%s.txt' % (image_set), 'w')

for image_id in image_ids:

list_file.write(abs_path + '/datasets/VOC2007/JPEGImages/%s.jpg\n' % (image_id)) # 要么自己补全路径，只写一半可能会报错

convert_annotation(image_id)

list_file.close()

运行后