本文详细介绍了VOC、COCO和YOLO三种数据集的格式，以及如何进行格式转换。VOC数据集包括Annotations、ImageSets和JPEGImages三个部分，通过test.py生成txt文件进行训练集和验证集划分。COCO数据集以json文件存储图像注释，而YOLO数据集则需要将XML标注转换为txt文件并按比例划分训练集和测试集。转换过程涉及LabelMe工具和自定义脚本。
仅做个人学习记录使用~
VOC数据集格式如下：
看清楚VOC数据集的格式，而不是VOC数据格式，你用LabelImg刚标注好的数据算是VOC的数据格式，它只是包含两个文件夹：一个是images，存放的是原始图片，一个是annotations,存放的是标注好的xml文件。再次基础上你若是想把VOC的数据格式变成VOC数据集的格式，需要参照下图次序重新建立文件夹，将已有的数据移入，然后利用下述代码生成ImageSets文件下的两个txt文件，我这里都是把测试集跟验证集共用，就只分了训练集与验证集。
─VOCdevkit
└─VOC2007
│ test.py
├─Annotations
└─train
└─x1.xml
└─val
└─x2.xml
├─ImageSets
└─Main
└─train.txt
└─val.txt
└─JPEGImages
└─train
└─x1.jpg
└─val
└─x2.jpg
VOC数据集分为三部分，分别是Annotations，ImageSets，JPEGImages，上图中test.py是用于生成ImageSets下的train.txt和val.txt，具体后面会讲，Annotations用于存放对图像进行标注的xml文件;
ImageSets下存放的是利用test.py生成的train.txt和val.txt，这两个txt文件里面存放的是去除后缀名的xml文件的文件名，用于模型训练和测试时查找文件使用;
JPEGImages存放的是我们采集的图片;
test.py内容如下所示：
import os
import random
# 训练集和验证集的比例分配
trainval_percent = 0.1
train_percent = 0.9
# 标注文件的路径
xmlfilepath = 'Annotations'
# 生成的txt文件存放路径
txtsavepath = 'ImageSets\Main'
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('ImageSets/Main/trainval.txt', 'w')
ftest = open('ImageSets/Main/test.txt', 'w')
ftrain = open('ImageSets/Main/train.txt', 'w')
fval = open('ImageSets/Main/val.txt', 'w')
for i in list:
name = total_xml[i][:-4] + '\n'
if i in trainval:
ftrainval.write(name)
if i in train:
ftest.write(name)
else:
fval.write(name)
else:
ftrain.write(name)
ftrainval.close()
ftrain.close()
fval.close()
ftest.close()
COCO数据集格式如下：
─annotations
└─instances_train2017.json
└─instances_test2017.json
─train2017
└─x1.jpg
...
─test2017
└─x2.jpg
...
上式中，annotations下的instances_train2017.json文件是对train2017下jpg图片生成的json注释文件进行汇总到一个文件中，代码如下：
# -*- coding:utf-8 -*-
# !/usr/bin/env python
import argparse
import json
import matplotlib.pyplot as plt
import skimage.io as io
#import cv2
from labelme import utils
import numpy as np
import glob
import PIL.Image
class MyEncoder(json.JSONEncoder):
def default(self, obj):
if isinstance(obj, np.integer):
return int(obj)
elif isinstance(obj, np.floating):
return float(obj)
elif isinstance(obj, np.ndarray):
return obj.tolist()
else:
return super(MyEncoder, self).default(obj)
class labelme2coco(object):
def __init__(self, labelme_json=[], save_json_path='./test.json'): #save_json_path='./test.json'
'''
:param labelme_json: 所有labelme的json文件路径组成的列表
:param save_json_path: json保存位置
'''
self.labelme_json = labelme_json
self.save_json_path = save_json_path
self.images = []
self.categories = []
self.annotations = []
# self.data_coco = {}
self.label = []
self.annID = 1
self.height = 0
self.width = 0
self.save_json()
def data_transfer(self):
for num, json_file in enumerate(self.labelme_json):
print("############:",json_file)
with open(json_file, 'r') as fp:
data = json.load(fp) # 加载json文件
print(data['imagePath'])
self.images.append(self.image(data, num))
for shapes in data['shapes']:
label = shapes['label']
if label not in self.label:
self.categories.append(self.categorie(label))
self.label.append(label)
points = shapes['points']#这里的point是用rectangle标注得到的，只有两个点，需要转成四个点
#points.append([points[0][0],points[1][1]])
#points.append([points[1][0],points[0][1]])
self.annotations.append(self.annotation(points, label, num))
self.annID += 1
def image(self, data, num):
image = {}
img = utils.img_b64_to_arr(data['imageData']) # 解析原图片数据
# img=io.imread(data['imagePath']) # 通过图片路径打开图片
# img = cv2.imread(data['imagePath'], 0)
height, width = img.shape[:2]
img = None
image['height'] = height
image['width'] = width
image['id'] = num + 1
image['file_name'] = data['imagePath'].split('/')[-1]
#image['file_name'] = data['imagePath'][3:14]
self.height = height
self.width = width
return image
def categorie(self, label):
categorie = {}
categorie['supercategory'] = 'waxberry'
categorie['id'] = len(self.label) + 1 # 0 默认为背景
categorie['name'] = label
return categorie
def annotation(self, points, label, num):
annotation = {}
annotation['segmentation'] = [list(np.asarray(points).flatten())]
annotation['iscrowd'] = 0
annotation['image_id'] = num + 1
# annotation['bbox'] = str(self.getbbox(points)) # 使用list保存json文件时报错（不知道为什么）
# list(map(int,a[1:-1].split(','))) a=annotation['bbox'] 使用该方式转成list
annotation['bbox'] = list(map(float, self.getbbox(points)))
annotation['area'] = annotation['bbox'][2] * annotation['bbox'][3]
# annotation['category_id'] = self.getcatid(label)
annotation['category_id'] = self.getcatid(label)#注意，源代码默认为1
annotation['id'] = self.annID
return annotation
def getcatid(self, label):
for categorie in self.categories:
if label == categorie['name']:
return categorie['id']
return 1
def getbbox(self, points):
# img = np.zeros([self.height,self.width],np.uint8)
# cv2.polylines(img, [np.asarray(points)], True, 1, lineType=cv2.LINE_AA) # 画边界线
# cv2.fillPoly(img, [np.asarray(points)], 1) # 画多边形 内部像素值为1
polygons = points
mask = self.polygons_to_mask([self.height, self.width], polygons)
return self.mask2box(mask)
def mask2box(self, mask):
'''从mask反算出其边框
mask：[h,w] 0、1组成的图片
1对应对象，只需计算1对应的行列号（左上角行列号，右下角行列号，就可以算出其边框）
'''
# np.where(mask==1)
index = np.argwhere(mask == 1)
rows = index[:, 0]
clos = index[:, 1]
# 解析左上角行列号
left_top_r = np.min(rows) # y
left_top_c = np.min(clos) # x
# 解析右下角行列号
right_bottom_r = np.max(rows)
right_bottom_c = np.max(clos)
# return [(left_top_r,left_top_c),(right_bottom_r,right_bottom_c)]
# return [(left_top_c, left_top_r), (right_bottom_c, right_bottom_r)]
# return [left_top_c, left_top_r, right_bottom_c, right_bottom_r] # [x1,y1,x2,y2]
return [left_top_c, left_top_r, right_bottom_c - left_top_c,
right_bottom_r - left_top_r] # [x1,y1,w,h] 对应COCO的bbox格式
def polygons_to_mask(self, img_shape, polygons):
mask = np.zeros(img_shape, dtype=np.uint8)
mask = PIL.Image.fromarray(mask)
xy = list(map(tuple, polygons))
PIL.ImageDraw.Draw(mask).polygon(xy=xy, outline=1, fill=1)
mask = np.array(mask, dtype=bool)
return mask
def data2coco(self):
data_coco = {}
data_coco['images'] = self.images
data_coco['categories'] = self.categories
data_coco['annotations'] = self.annotations
return data_coco
def save_json(self):
self.data_transfer()
self.data_coco = self.data2coco()
# 保存json文件
json.dump(self.data_coco, open(self.save_json_path, 'w'), indent=4, cls=MyEncoder) # indent=4 更加美观显示
# labelme_json = glob.glob('./data/coco/valset/*.json')
# labelme_json=['./Annotations/*.json']
labelme_json = glob.glob(r'I:\xxx\xxx/*.json')
labelme2coco(labelme_json, r'I:\xxx\xxx/instances_test2017.json')
只需更改三处
1-最后一行生成的instances_test2017.json的地址
2-倒数第二行，train文件下图片的注释json文件
3-第八十行的标签类别
Yolo数据集
--Root
--Annotations
--videoDir1
--0.xml
--1.xml
--videoDir2
--0.xml
--1.xml
--Images
--videoDir1
--0.jpg
--1.jpg
--videoDir2
--0.jpg
--1.jpg
--labels
--videoDir1
--0.txt
--1.txt
--videoDir2
--0.txt
--1.txt
--train.txt
--test.txt
将VOC数据集转换成YOLO利用如下代码：
import os
import glob
import random
import xml.etree.ElementTree as ET
currentRoot = os.getcwd()
classes = ["alive_fish","dead_fish"] #这里改成你自己的类名
train_percent = 0.8
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(xmlfile,labelfile):
with open(xmlfile,'r') as in_file:
with open(labelfile, 'w') as out_file:
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')
if __name__ == "__main__":
currentRoot = os.getcwd()
imgdirpath = os.path.join(currentRoot,"images","*")
imgdirlist = glob.glob(imgdirpath)
for i in range(len(imgdirlist)):
imgdir = imgdirlist[i]
labeldir = imgdir.replace('images','labels')
if(not os.path.exists(labeldir)):
os.mkdir(labeldir)
imgdirpath = os.path.join(imgdirpath,"*.jpg")
imgpathlist = glob.glob(imgdirpath)
for i in range(len(imgpathlist)):
imgfilepath = imgpathlist[i]
labelfilepath = imgfilepath.replace('images','labels')
labelfilepath = labelfilepath.replace('.jpg','.txt')
if(not os.path.exists(labelfilepath)):
xmlfilepath = imgfilepath.replace('images','Annotations')
xmlfilepath = xmlfilepath.replace('.jpg','.xml')
if(not os.path.exists(xmlfilepath)):
print("no xml file exists: "+xmlfilepath)
continue
else:
convert_annotation(xmlfilepath,labelfilepath)
labelfilepath = os.path.join(os.path.join(currentRoot,"labels","*","*.txt"))
labelfilepathlist = glob.glob(labelfilepath)
imagelist = []
for i in range(len(labelfilepathlist)):
labelfilepath = labelfilepathlist[i]
image = labelfilepath.replace('labels','images')
image = image.replace('.txt','.jpg')
imagelist.append(image)
print(len(imagelist))
num = len(imagelist)
trainnum = int(num * train_percent)
random.shuffle(imagelist)
print(len(imagelist))
for i in range(num):
if(i<trainnum):
with open('train.txt', 'a') as trainf:
trainf.write(imagelist[i]+'\n')
else:
with open('test.txt', 'a') as testf:
testf.write(imagelist[i]+'\n')
参考 链接：
https://blog.csdn.net/weixin_38616018/article/details/112397396?ops_request_misc=%257B%2522request%255Fid%2522%253A%2522161995714616780262563315%2522%252C%2522scm%2522%253A%252220140713.130102334.pc%255Fblog.%2522%257D&request_id=161995714616780262563315&biz_id=0&utm_medium=distribute.pc_search_result.none-task-blog-2blogfirst_rank_v2~rank_v29-6-112397396.nonecase&utm_term=voc+to+yolo%E8%AE%AD%E7%BB%83%E8%87%AA%E5%B7%B1%E7%9A%84%E6%95%B0%E6%8D%AE
扫一扫
9871
被折叠的 条评论
为什么被折叠?
到【灌水乐园】发言
