赞
踩
我们通常把训练的数据分为三个文件夹:训练集、测试集和验证集。
我们来举一个栗子:模型的训练与学习,类似于老师教学生学知识的过程。
**参数(parameters):**指由模型通过学习得到的变量,如权重和偏置。
**超参数(hyperparameters):**指根据经验进行设定的参数,如迭代次数,隐层的层数,每层神经元的个数,学习率等。
第1步:在YOLOv5项目下创建对应文件夹
在YOLOv5项目目录下创建datasets文件夹(名字自定义),接着在该文件夹下新建Annotations和images****文件夹。
如下图所示:
第2步:打开labelimg开始标注数据集
标注后Annotations文件夹下面为xml文件,如下图所示:
images文件夹是我们的数据集图片,格式为jpg,如下图所示:
第3步:创建保存划分后数据集的文件夹
创建一个名为ImageSets的文件夹(名字自定义),用来保存一会儿划分好的训练集、测试集和验证集。
准备工作的注意事项:
- 所有训练所需的图像存于一个目录,所有训练所需的标签存于一个目录。
- 图像文件与标签文件都统一的格式。
- 图像名与标签名一一对应。
完成以上工作我们就可以来进行数据集的划分啦!
第1步:创建split.py
在YOLOv5项目目录下创建split.py项目。
第2步:将数据集打乱顺序
通过上面我们知道,数据集有images和Annotations这两个文件,我们需要把这两个文件绑定,然后将其打乱顺序。
首先设置空列表,将for循环读取这两个文件的每个数据放入对应表中,再将这两个文件通过zip()函数绑定,计算总长度。
def split_data(file_path,xml_path, new_file_path, train_rate, val_rate, test_rate):
each_class_image = []
each_class_label = []
for image in os.listdir(file_path):
each_class_image.append(image)
for label in os.listdir(xml_path):
each_class_label.append(label)
data=list(zip(each_class_image,each_class_label))
total = len(each_class_image)
然后用random.shuffle()函数打乱顺序,再将两个列表解绑。
random.shuffle(data)
each_class_image,each_class_label=zip(*data)
第3步:按照确定好的比例将两个列表元素分割
分别获取train、val、test这三个文件夹对应的图片和标签。
train_images = each_class_image[0:int(train_rate * total)]
val_images = each_class_image[int(train_rate * total):int((train_rate + val_rate) * total)]
test_images = each_class_image[int((train_rate + val_rate) * total):]
train_labels = each_class_label[0:int(train_rate * total)]
val_labels = each_class_label[int(train_rate * total):int((train_rate + val_rate) * total)]
test_labels = each_class_label[int((train_rate + val_rate) * total):]
第4步:在本地生成文件夹,将划分好的数据集分别保存
接下来就是设置相应的路径保存格式,将图片和标签对应保存下来。
for image in train_images:
print(image)
old_path = file_path + '/' + image
new_path1 = new_file_path + '/' + 'train' + '/' + 'images'
if not os.path.exists(new_path1):
os.makedirs(new_path1)
new_path = new_path1 + '/' + image
shutil.copy(old_path, new_path)
for label in train_labels:
print(label)
old_path = xml_path + '/' + label
new_path1 = new_file_path + '/' + 'train' + '/' + 'labels'
if not os.path.exists(new_path1):
os.makedirs(new_path1)
new_path = new_path1 + '/' + label
shutil.copy(old_path, new_path)
for image in val_images:
old_path = file_path + '/' + image
new_path1 = new_file_path + '/' + 'val' + '/' + 'images'
if not os.path.exists(new_path1):
os.makedirs(new_path1)
new_path = new_path1 + '/' + image
shutil.copy(old_path, new_path)
for label in val_labels:
old_path = xml_path + '/' + label
new_path1 = new_file_path + '/' + 'val' + '/' + 'labels'
if not os.path.exists(new_path1):
os.makedirs(new_path1)
new_path = new_path1 + '/' + label
shutil.copy(old_path, new_path)
for image in test_images:
old_path = file_path + '/' + image
new_path1 = new_file_path + '/' + 'test' + '/' + 'images'
if not os.path.exists(new_path1):
os.makedirs(new_path1)
new_path = new_path1 + '/' + image
shutil.copy(old_path, new_path)
for label in test_labels:
old_path = xml_path + '/' + label
new_path1 = new_file_path + '/' + 'test' + '/' + 'labels'
if not os.path.exists(new_path1):
os.makedirs(new_path1)
new_path = new_path1 + '/' + label
shutil.copy(old_path, new_path)
第5步:设置路径并设置划分比例
这里要设置的有三个:
if __name__ == '__main__':
file_path = "D:\yolov5-6.1\datasets\image"
xml_path = "D:\yolov5-6.1\datasets\Annotation"
new_file_path = "D:\yolov5-6.1\datasets\ImageSets"
split_data(file_path,xml_path, new_file_path, train_rate=0.7, val_rate=0.1, test_rate=0.2)
最后一行是设置划分比例,这里的比例分配大家可以随便划分,我选取的是7:1:2。
至此,我们的数据集就划分好了。
来运行一下看看效果吧:
我们可以看到,数据集图片和标签已经划分成了train、val和test三个文件夹。
比例也符合7:1:2
split.py完整代码
import os
import shutil
import random
random.seed(0) # 确保随机操作的可复现性
def split_data(file_path, xml_path, new_file_path, train_rate, val_rate, test_rate):
# 存储图片和标注文件的列表
each_class_image = []
each_class_label = []
# 将图片文件名添加到列表
for image in os.listdir(file_path):
each_class_image.append(image)
# 将标注文件名添加到列表
for label in os.listdir(xml_path):
each_class_label.append(label)
# 将图片和标注文件打包成元组列表并随机打乱
data = list(zip(each_class_image, each_class_label))
total = len(each_class_image)
random.shuffle(data)
# 解压元组列表,回到图片和标注文件列表
each_class_image, each_class_label = zip(*data)
# 按照指定的比例分配数据到训练集、验证集和测试集
train_images = each_class_image[0:int(train_rate * total)]
val_images = each_class_image[int(train_rate * total):int((train_rate + val_rate) * total)]
test_images = each_class_image[int((train_rate + val_rate) * total):]
train_labels = each_class_label[0:int(train_rate * total)]
val_labels = each_class_label[int(train_rate * total):int((train_rate + val_rate) * total)]
test_labels = each_class_label[int((train_rate + val_rate) * total):]
# 定义复制文件到新路径的操作
def copy_files(files, old_path, new_path1):
# 遍历列表中的每一个文件名
for file in files:
# 打印当前处理的文件名,这只是为了在处理过程中输出信息,便于跟踪进度
print(file)
# 使用os.path.join连接旧路径和新文件名,形成完整的旧文件路径
old_file_path = os.path.join(old_path, file)
# 检查新的路径是否存在,如果不存在则创建新的路径,这可以确保复制操作不会因为路径不存在而出错
if not os.path.exists(new_path1):
os.makedirs(new_path1)
# 使用os.path.join连接新路径和新文件名,形成完整的新文件路径
new_file_path = os.path.join(new_path1, file)
# 使用shutil模块的copy函数复制旧文件到新路径,生成与旧文件相同的新的文件
shutil.copy(old_file_path, new_file_path)
# 复制训练、验证和测试的图片和标注文件到指定目录
copy_files(train_images, file_path, os.path.join(new_file_path, 'train', 'images'))
copy_files(train_labels, xml_path, os.path.join(new_file_path, 'train', 'labels'))
copy_files(val_images, file_path, os.path.join(new_file_path, 'val', 'images'))
copy_files(val_labels, xml_path, os.path.join(new_file_path, 'val', 'labels'))
copy_files(test_images, file_path, os.path.join(new_file_path, 'test', 'images'))
copy_files(test_labels, xml_path, os.path.join(new_file_path, 'test', 'labels'))
# 判断当前脚本是否为主程序入口,即直接运行该脚本
if __name__ == '__main__':
# 定义文件路径变量,指向数据集的图像文件所在路径
file_path = "D:\yolov5-6.1\datasets\image"
# 定义xml路径变量,指向数据集的标注文件所在路径
xml_path = "D:\yolov5-6.1\datasets\Annotation"
# 定义新文件路径变量,指向输出结果文件的新路径
new_file_path = "D:\yolov5-6.1\datasets\ImageSets"
# 调用split_data函数,分割数据集,并将结果分别存储到指定的路径中
split_data(file_path, xml_path, new_file_path, train_rate=0.7, val_rate=0.1, test_rate=0.2)
import xml.etree.ElementTree as ET
import pickle
import os
from os import listdir, getcwd
from os.path import join
import random
from shutil import copyfile
# from lxml import etree
#自己的类别
classes = ["0", "1",'2','3','person']
# classes=["ball"]
TRAIN_RATIO = 80 #训练集比例
def clear_hidden_files(path):
dir_list = os.listdir(path)
for i in dir_list:
abspath = os.path.join(os.path.abspath(path), i)
if os.path.isfile(abspath):
if i.startswith("._"):
os.remove(abspath)
else:
clear_hidden_files(abspath)
#数据转换
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)
#编写格式
def convert_annotation(image_id):
in_file = open('./dataset/annotations/%s.xml' % image_id)
out_file = open('./dataset/YOLOLabels/%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')
in_file.close()
out_file.close()
#创建上述目录结构
wd = os.getcwd()
work_sapce_dir = os.path.join(wd, "dataset/")
if not os.path.isdir(work_sapce_dir):
os.mkdir(work_sapce_dir)
annotation_dir = os.path.join(work_sapce_dir, "annotations/")
if not os.path.isdir(annotation_dir):
os.mkdir(annotation_dir)
clear_hidden_files(annotation_dir)
image_dir = os.path.join(work_sapce_dir, "JPEGImages/")
if not os.path.isdir(image_dir):
os.mkdir(image_dir)
clear_hidden_files(image_dir)
yolo_labels_dir = os.path.join(work_sapce_dir, "YOLOLabels/")
if not os.path.isdir(yolo_labels_dir):
os.mkdir(yolo_labels_dir)
clear_hidden_files(yolo_labels_dir)
yolov5_images_dir = os.path.join(work_sapce_dir, "images/")
if not os.path.isdir(yolov5_images_dir):
os.mkdir(yolov5_images_dir)
clear_hidden_files(yolov5_images_dir)
yolov5_labels_dir = os.path.join(work_sapce_dir, "labels/")
if not os.path.isdir(yolov5_labels_dir):
os.mkdir(yolov5_labels_dir)
clear_hidden_files(yolov5_labels_dir)
yolov5_images_train_dir = os.path.join(yolov5_images_dir, "train/")
if not os.path.isdir(yolov5_images_train_dir):
os.mkdir(yolov5_images_train_dir)
clear_hidden_files(yolov5_images_train_dir)
yolov5_images_test_dir = os.path.join(yolov5_images_dir, "val/")
if not os.path.isdir(yolov5_images_test_dir):
os.mkdir(yolov5_images_test_dir)
clear_hidden_files(yolov5_images_test_dir)
yolov5_labels_train_dir = os.path.join(yolov5_labels_dir, "train/")
if not os.path.isdir(yolov5_labels_train_dir):
os.mkdir(yolov5_labels_train_dir)
clear_hidden_files(yolov5_labels_train_dir)
yolov5_labels_test_dir = os.path.join(yolov5_labels_dir, "val/")
if not os.path.isdir(yolov5_labels_test_dir):
os.mkdir(yolov5_labels_test_dir)
clear_hidden_files(yolov5_labels_test_dir)
#创建两个记录照片名字的文件
train_file = open(os.path.join(yolov5_images_dir, "yolov5_train.txt"), 'w')
test_file = open(os.path.join(yolov5_images_dir, "yolov5_val.txt"), 'w')
train_file.close()
test_file.close()
train_file = open(os.path.join(yolov5_images_dir, "yolov5_train.txt"), 'a')
test_file = open(os.path.join(yolov5_images_dir, "yolov5_val.txt"), 'a')
#随机划分
list_imgs = os.listdir(image_dir) # list image files
prob = random.randint(1, 100)
print("Probability: %d" % prob)
for i in range(0, len(list_imgs)):
path = os.path.join(image_dir, list_imgs[i])
if os.path.isfile(path):
image_path = image_dir + list_imgs[i]
voc_path = list_imgs[i]
(nameWithoutExtention, extention) = os.path.splitext(os.path.basename(image_path))
(voc_nameWithoutExtention, voc_extention) = os.path.splitext(os.path.basename(voc_path))
annotation_name = nameWithoutExtention + '.xml'
annotation_path = os.path.join(annotation_dir, annotation_name)
label_name = nameWithoutExtention + '.txt'
label_path = os.path.join(yolo_labels_dir, label_name)
prob = random.randint(1, 100)
print("Probability: %d" % prob)
if (prob < TRAIN_RATIO): # train dataset
if os.path.exists(annotation_path):
train_file.write(image_path + '\n')
convert_annotation(nameWithoutExtention) # convert label
copyfile(image_path, yolov5_images_train_dir + voc_path)
copyfile(label_path, yolov5_labels_train_dir + label_name)
else: # test dataset
if os.path.exists(annotation_path):
test_file.write(image_path + '\n')
convert_annotation(nameWithoutExtention) # convert label
copyfile(image_path, yolov5_images_test_dir + voc_path)
copyfile(label_path, yolov5_labels_test_dir + label_name)
train_file.close()
test_file.close()
from xml.dom.minidom import Document
import os
import cv2
# def makexml(txtPath, xmlPath, picPath): # txt所在文件夹路径,xml文件保存路径,图片所在文件夹路径
def makexml(picPath, txtPath, xmlPath): # txt所在文件夹路径,xml文件保存路径,图片所在文件夹路径
"""此函数用于将yolo格式txt标注文件转换为voc格式xml标注文件
"""
dic = {'0': "0", # 创建字典用来对类型进行转换
'1': "1", # 此处的字典要与自己的classes.txt文件中的类对应,且顺序要一致
'3' :'person'
}
files = os.listdir(txtPath)
for i, name in enumerate(files):
xmlBuilder = Document()
annotation = xmlBuilder.createElement("annotation") # 创建annotation标签
xmlBuilder.appendChild(annotation)
txtFile = open(txtPath + name)
txtList = txtFile.readlines()
img = cv2.imread(picPath + name[0:-4] + ".jpg")
Pheight, Pwidth, Pdepth = img.shape
folder = xmlBuilder.createElement("folder") # folder标签
foldercontent = xmlBuilder.createTextNode("driving_annotation_dataset")
folder.appendChild(foldercontent)
annotation.appendChild(folder) # folder标签结束
filename = xmlBuilder.createElement("filename") # filename标签
filenamecontent = xmlBuilder.createTextNode(name[0:-4] + ".jpg")
filename.appendChild(filenamecontent)
annotation.appendChild(filename) # filename标签结束
size = xmlBuilder.createElement("size") # size标签
width = xmlBuilder.createElement("width") # size子标签width
widthcontent = xmlBuilder.createTextNode(str(Pwidth))
width.appendChild(widthcontent)
size.appendChild(width) # size子标签width结束
height = xmlBuilder.createElement("height") # size子标签height
heightcontent = xmlBuilder.createTextNode(str(Pheight))
height.appendChild(heightcontent)
size.appendChild(height) # size子标签height结束
depth = xmlBuilder.createElement("depth") # size子标签depth
depthcontent = xmlBuilder.createTextNode(str(Pdepth))
depth.appendChild(depthcontent)
size.appendChild(depth) # size子标签depth结束
annotation.appendChild(size) # size标签结束
for j in txtList:
oneline = j.strip().split(" ")
object = xmlBuilder.createElement("object") # object 标签
picname = xmlBuilder.createElement("name") # name标签
namecontent = xmlBuilder.createTextNode(dic[oneline[0]])
picname.appendChild(namecontent)
object.appendChild(picname) # name标签结束
pose = xmlBuilder.createElement("pose") # pose标签
posecontent = xmlBuilder.createTextNode("Unspecified")
pose.appendChild(posecontent)
object.appendChild(pose) # pose标签结束
truncated = xmlBuilder.createElement("truncated") # truncated标签
truncatedContent = xmlBuilder.createTextNode("0")
truncated.appendChild(truncatedContent)
object.appendChild(truncated) # truncated标签结束
difficult = xmlBuilder.createElement("difficult") # difficult标签
difficultcontent = xmlBuilder.createTextNode("0")
difficult.appendChild(difficultcontent)
object.appendChild(difficult) # difficult标签结束
bndbox = xmlBuilder.createElement("bndbox") # bndbox标签
xmin = xmlBuilder.createElement("xmin") # xmin标签
mathData = int(((float(oneline[1])) * Pwidth + 1) - (float(oneline[3])) * 0.5 * Pwidth)
xminContent = xmlBuilder.createTextNode(str(mathData))
xmin.appendChild(xminContent)
bndbox.appendChild(xmin) # xmin标签结束
ymin = xmlBuilder.createElement("ymin") # ymin标签
mathData = int(((float(oneline[2])) * Pheight + 1) - (float(oneline[4])) * 0.5 * Pheight)
yminContent = xmlBuilder.createTextNode(str(mathData))
ymin.appendChild(yminContent)
bndbox.appendChild(ymin) # ymin标签结束
xmax = xmlBuilder.createElement("xmax") # xmax标签
mathData = int(((float(oneline[1])) * Pwidth + 1) + (float(oneline[3])) * 0.5 * Pwidth)
xmaxContent = xmlBuilder.createTextNode(str(mathData))
xmax.appendChild(xmaxContent)
bndbox.appendChild(xmax) # xmax标签结束
ymax = xmlBuilder.createElement("ymax") # ymax标签
mathData = int(((float(oneline[2])) * Pheight + 1) + (float(oneline[4])) * 0.5 * Pheight)
ymaxContent = xmlBuilder.createTextNode(str(mathData))
ymax.appendChild(ymaxContent)
bndbox.appendChild(ymax) # ymax标签结束
object.appendChild(bndbox) # bndbox标签结束
annotation.appendChild(object) # object标签结束
f = open(xmlPath + name[0:-4] + ".xml", 'w')
xmlBuilder.writexml(f, indent='\t', newl='\n', addindent='\t', encoding='utf-8')
f.close()
if __name__ == "__main__":
picPath = "dataset/JPEGImages/" # 图片所在文件夹路径,后面的/一定要带上
txtPath = "dataset/YOLO/" # txt所在文件夹路径,后面的/一定要带上
xmlPath = "dataset/annotations/" # xml文件保存路径,后面的/一定要带上
makexml(picPath, txtPath, xmlPath)
#COCO 格式的数据集转化为 YOLO 格式的数据集
#--json_path 输入的json文件路径
#--save_path 保存的文件夹名字,默认为当前目录下的labels。
import os
import json
from tqdm import tqdm
import argparse
parser = argparse.ArgumentParser()
#这里根据自己的json文件位置,换成自己的就行
parser.add_argument('--json_path', default='D:/workSpace/pycharm/yolov5/MyTest/SAR_coco/annotations/instances_val2017.json',type=str, help="input: coco format(json)")
#这里设置.txt文件保存位置
parser.add_argument('--save_path', default='D:/workSpace/pycharm/yolov5/MyTest/SAR_coco/Lable/val2017', type=str, help="specify where to save the output dir of labels")
arg = parser.parse_args()
def convert(size, box):
dw = 1. / (size[0])
dh = 1. / (size[1])
x = box[0] + box[2] / 2.0
y = box[1] + box[3] / 2.0
w = box[2]
h = box[3]
#round函数确定(xmin, ymin, xmax, ymax)的小数位数
x = round(x * dw, 6)
w = round(w * dw, 6)
y = round(y * dh, 6)
h = round(h * dh, 6)
return (x, y, w, h)
if __name__ == '__main__':
json_file = arg.json_path # COCO Object Instance 类型的标注
ana_txt_save_path = arg.save_path # 保存的路径
data = json.load(open(json_file, 'r'))
if not os.path.exists(ana_txt_save_path):
os.makedirs(ana_txt_save_path)
id_map = {} # coco数据集的id不连续!重新映射一下再输出!
with open(os.path.join(ana_txt_save_path, 'classes.txt'), 'w') as f:
# 写入classes.txt
for i, category in enumerate(data['categories']):
f.write(f"{category['name']}\n")
id_map[category['id']] = i
# print(id_map)
#这里需要根据自己的需要,更改写入图像相对路径的文件位置。
list_file = open(os.path.join(ana_txt_save_path, 'train2017.txt'), 'w')
for img in tqdm(data['images']):
filename = img["file_name"]
img_width = img["width"]
img_height = img["height"]
img_id = img["id"]
head, tail = os.path.splitext(filename)
ana_txt_name = head + ".txt" # 对应的txt名字,与jpg一致
f_txt = open(os.path.join(ana_txt_save_path, ana_txt_name), 'w')
for ann in data['annotations']:
if ann['image_id'] == img_id:
box = convert((img_width, img_height), ann["bbox"])
f_txt.write("%s %s %s %s %s\n" % (id_map[ann["category_id"]], box[0], box[1], box[2], box[3]))
f_txt.close()
#将图片的相对路径写入train2017或val2017的路径
list_file.write('./images/train2017/%s.jpg\n' %(head))
print("convert successful!")
list_file.close()
官方数据集解读:
https://zhuanlan.zhihu.com/p/337850513
Copyright © 2003-2013 www.wpsshop.cn 版权所有,并保留所有权利。