作者:RayChiu_Labloy
版权声明:著作权归作者所有,商业转载请联系作者获得授权,非商业转载请注明出处
VOC目录结构:
└── VOCdevkit #根目录
└── VOC2012 #不同年份的数据集,这里只下载了2012的,还有2007等其它年份的
├── Annotations #存放xml文件,与JPEGImages中的图片一一对应,解释图片的内容等等
├── ImageSets #该目录下存放的都是txt文件,txt文件中每一行包含一个图片的名称,末尾会加上±1表示正负样本
│ ├── Action #存放的是人的动作(例如running、jumping等等,这也是VOC challenge的一部分)
│ ├── Layout #存放的是具有人体部位的数据(人的head、hand、feet等等,这也是VOC challenge的一部分)
│ ├── Main #主要关注的文件夹,存放的是图像物体识别的数据,包含train、val、trainval的txt
│ └── Segmentation #存放的是可用于分割的数据。
├── JPEGImages #存放源图片
├── SegmentationClass #存放的是图片,分割后的效果,单个图片中同一类是同一种颜色
└── SegmentationObject #存放的是图片,分割后的效果,单个图片中同一类是不同颜色
其中Annotations中的xml和对应的图片提供一个样例供参考:
标注后的xml:
<annotation>
<folder>VOC2007</folder>
<filename>000005.jpg</filename>#文件名
<source>#文件来源
<database>The VOC2007 Database</database>
<annotation>PASCAL VOC2007</annotation>
<image>flickr</image>
<flickrid>325991873</flickrid>
</source>
<owner>
<flickrid>archintent louisville</flickrid>
<name>?</name>
</owner>
<size>#文件尺寸,包括长、宽、通道数
<width>500</width>
<height>375</height>
<depth>3</depth>
</size>
<segmented>0</segmented>#是否用于分割
<object>#检测目标
<name>chair</name>#目标类别
<pose>Rear</pose>#摄像头角度
<truncated>0</truncated>#是否被截断,0表示完整
<difficult>0</difficult>#目标是否难以识别,0表示容易识别
<bndbox>#bounding-box 左上角和右下角的4个坐标值
<xmin>263</xmin>
<ymin>211</ymin>
<xmax>324</xmax>
<ymax>339</ymax>
</bndbox>
</object>
<object>#检测到的多个物体, 可以看到上图中,图片000005中有多个椅子
<name>chair</name>
<pose>Unspecified</pose>
<truncated>0</truncated>
<difficult>0</difficult>
<bndbox>
<xmin>165</xmin>
<ymin>264</ymin>
<xmax>253</xmax>
<ymax>372</ymax>
</bndbox>
</object>
<object>#检测到的多个物体
<name>chair</name>
<pose>Unspecified</pose>
<truncated>1</truncated>
<difficult>1</difficult>
<bndbox>
<xmin>5</xmin>
<ymin>244</ymin>
<xmax>67</xmax>
<ymax>374</ymax>
</bndbox>
</object>
<object>
<name>chair</name>
<pose>Unspecified</pose>
<truncated>0</truncated>
<difficult>0</difficult>
<bndbox>
<xmin>241</xmin>
<ymin>194</ymin>
<xmax>295</xmax>
<ymax>299</ymax>
</bndbox>
</object>
<object>#检测到的多个物体
<name>chair</name>
<pose>Unspecified</pose>
<truncated>1</truncated>
<difficult>1</difficult>
<bndbox>
<xmin>277</xmin>
<ymin>186</ymin>
<xmax>312</xmax>
<ymax>220</ymax>
</bndbox>
</object>
</annotation>
对应的图片:
COCO数据集:相比较VOC数据集标注的XML格式,coco数据集的是json格式的,例如:
{
"images": [{
"file_name": "001004.jpg",
"height": 375,
"width": 500,
"id": 1004
}],
"type": "instances",
"annotations": [{
"area": 4278,
"iscrowd": 0,
"image_id": 1004,
"bbox": [142, 151, 93, 46],
"category_id": 0,
"id": 1,
"ignore": 0,
"segmentation": [
[142, 151, 142, 197, 235, 197, 235, 151]
]
}],
"categories": [{
"supercategory": "none",
"id": 0,
"name": "bird"
}]
}
VOC转COCO:
参考:VOC数据集格式转化成COCO数据集格式_sinat_28371057的博客-CSDN博客_voc格式转coco格式
import xml.etree.ElementTree as ET
import os
import json
coco = dict()
coco['images'] = []
coco['type'] = 'instances'
coco['annotations'] = []
coco['categories'] = []
category_set = dict()
image_set = set()
category_item_id = -1
image_id = 20180000000
annotation_id = 0
def addCatItem(name):
global category_item_id
category_item = dict()
category_item['supercategory'] = 'none'
category_item_id += 1
category_item['id'] = category_item_id
category_item['name'] = name
coco['categories'].append(category_item)
category_set[name] = category_item_id
return category_item_id
def addImgItem(file_name, size):
global image_id
if file_name is None:
raise Exception('Could not find filename tag in xml file.')
if size['width'] is None:
raise Exception('Could not find width tag in xml file.')
if size['height'] is None:
raise Exception('Could not find height tag in xml file.')
image_id += 1
image_item = dict()
image_item['id'] = image_id
image_item['file_name'] = file_name
image_item['width'] = size['width']
image_item['height'] = size['height']
coco['images'].append(image_item)
image_set.add(file_name)
return image_id
def addAnnoItem(object_name, image_id, category_id, bbox):
global annotation_id
annotation_item = dict()
annotation_item['segmentation'] = []
seg = []
# bbox[] is x,y,w,h
# left_top
seg.append(bbox[0])
seg.append(bbox[1])
# left_bottom
seg.append(bbox[0])
seg.append(bbox[1] + bbox[3])
# right_bottom
seg.append(bbox[0] + bbox[2])
seg.append(bbox[1] + bbox[3])
# right_top
seg.append(bbox[0] + bbox[2])
seg.append(bbox[1])
annotation_item['segmentation'].append(seg)
annotation_item['area'] = bbox[2] * bbox[3]
annotation_item['iscrowd'] = 0
annotation_item['ignore'] = 0
annotation_item['image_id'] = image_id
annotation_item['bbox'] = bbox
annotation_item['category_id'] = category_id
annotation_id += 1
annotation_item['id'] = annotation_id
coco['annotations'].append(annotation_item)
def _read_image_ids(image_sets_file):
ids = []
with open(image_sets_file) as f:
for line in f:
ids.append(line.rstrip())
return ids
"""通过txt文件生成"""
# split ='train' 'va' 'trainval' 'test'
def parseXmlFiles_by_txt(data_dir, json_save_path, split='train'):
print("hello")
labelfile = split + ".txt"
image_sets_file = data_dir + "/ImageSets/Main/" + labelfile
ids = _read_image_ids(image_sets_file)
for _id in ids:
xml_file = data_dir + f"/Annotations/{_id}.xml"
bndbox = dict()
size = dict()
current_image_id = None
current_category_id = None
file_name = None
size['width'] = None
size['height'] = None
size['depth'] = None
tree = ET.parse(xml_file)
root = tree.getroot()
if root.tag != 'annotation':
raise Exception('pascal voc xml root element should be annotation, rather than {}'.format(root.tag))
# elem is <folder>, <filename>, <size>, <object>
for elem in root:
current_parent = elem.tag
current_sub = None
object_name = None
if elem.tag == 'folder':
continue
if elem.tag == 'filename':
file_name = elem.text
if file_name in category_set:
raise Exception('file_name duplicated')
# add img item only after parse <size> tag
elif current_image_id is None and file_name is not None and size['width'] is not None:
if file_name not in image_set:
current_image_id = addImgItem(file_name, size)
print('add image with {} and {}'.format(file_name, size))
else:
raise Exception('duplicated image: {}'.format(file_name))
# subelem is <width>, <height>, <depth>, <name>, <bndbox>
for subelem in elem:
bndbox['xmin'] = None
bndbox['xmax'] = None
bndbox['ymin'] = None
bndbox['ymax'] = None
current_sub = subelem.tag
if current_parent == 'object' and subelem.tag == 'name':
object_name = subelem.text
if object_name not in category_set:
current_category_id = addCatItem(object_name)
else:
current_category_id = category_set[object_name]
elif current_parent == 'size':
if size[subelem.tag] is not None:
raise Exception('xml structure broken at size tag.')
size[subelem.tag] = int(subelem.text)
# option is <xmin>, <ymin>, <xmax>, <ymax>, when subelem is <bndbox>
for option in subelem:
if current_sub == 'bndbox':
if bndbox[option.tag] is not None:
raise Exception('xml structure corrupted at bndbox tag.')
bndbox[option.tag] = int(option.text)
# only after parse the <object> tag
if bndbox['xmin'] is not None:
if object_name is None:
raise Exception('xml structure broken at bndbox tag')
if current_image_id is None:
raise Exception('xml structure broken at bndbox tag')
if current_category_id is None:
raise Exception('xml structure broken at bndbox tag')
bbox = []
# x
bbox.append(bndbox['xmin'])
# y
bbox.append(bndbox['ymin'])
# w
bbox.append(bndbox['xmax'] - bndbox['xmin'])
# h
bbox.append(bndbox['ymax'] - bndbox['ymin'])
print('add annotation with {},{},{},{}'.format(object_name, current_image_id, current_category_id,
bbox))
addAnnoItem(object_name, current_image_id, current_category_id, bbox)
json.dump(coco, open(json_save_path, 'w'))
"""直接从xml文件夹中生成"""
def parseXmlFiles(xml_path, json_save_path):
for f in os.listdir(xml_path):
if not f.endswith('.xml'):
continue
bndbox = dict()
size = dict()
current_image_id = None
current_category_id = None
file_name = None
size['width'] = None
size['height'] = None
size['depth'] = None
xml_file = os.path.join(xml_path, f)
print(xml_file)
tree = ET.parse(xml_file)
root = tree.getroot()
if root.tag != 'annotation':
raise Exception('pascal voc xml root element should be annotation, rather than {}'.format(root.tag))
# elem is <folder>, <filename>, <size>, <object>
for elem in root:
current_parent = elem.tag
current_sub = None
object_name = None
if elem.tag == 'folder':
continue
if elem.tag == 'filename':
file_name = elem.text
if file_name in category_set:
raise Exception('file_name duplicated')
# add img item only after parse <size> tag
elif current_image_id is None and file_name is not None and size['width'] is not None:
if file_name not in image_set:
current_image_id = addImgItem(file_name, size)
print('add image with {} and {}'.format(file_name, size))
else:
raise Exception('duplicated image: {}'.format(file_name))
# subelem is <width>, <height>, <depth>, <name>, <bndbox>
for subelem in elem:
bndbox['xmin'] = None
bndbox['xmax'] = None
bndbox['ymin'] = None
bndbox['ymax'] = None
current_sub = subelem.tag
if current_parent == 'object' and subelem.tag == 'name':
object_name = subelem.text
if object_name not in category_set:
current_category_id = addCatItem(object_name)
else:
current_category_id = category_set[object_name]
elif current_parent == 'size':
if size[subelem.tag] is not None:
raise Exception('xml structure broken at size tag.')
size[subelem.tag] = int(subelem.text)
# option is <xmin>, <ymin>, <xmax>, <ymax>, when subelem is <bndbox>
for option in subelem:
if current_sub == 'bndbox':
if bndbox[option.tag] is not None:
raise Exception('xml structure corrupted at bndbox tag.')
bndbox[option.tag] = int(option.text)
# only after parse the <object> tag
if bndbox['xmin'] is not None:
if object_name is None:
raise Exception('xml structure broken at bndbox tag')
if current_image_id is None:
raise Exception('xml structure broken at bndbox tag')
if current_category_id is None:
raise Exception('xml structure broken at bndbox tag')
bbox = []
# x
bbox.append(bndbox['xmin'])
# y
bbox.append(bndbox['ymin'])
# w
bbox.append(bndbox['xmax'] - bndbox['xmin'])
# h
bbox.append(bndbox['ymax'] - bndbox['ymin'])
print('add annotation with {},{},{},{}'.format(object_name, current_image_id, current_category_id,
bbox))
addAnnoItem(object_name, current_image_id, current_category_id, bbox)
json.dump(coco, open(json_save_path, 'w'))
if __name__ == '__main__':
# 通过txt文件生成
voc_data_dir="../VOCData/"
json_save_path="../VOCData_COCO2/voc2007val.json"
parseXmlFiles_by_txt(voc_data_dir,json_save_path,"val")
# # 通过文件夹生成
# ann_path = "../VOCData/Annotations/"
# json_save_path = "../VOCData_COCO2/test.json"
# parseXmlFiles(ann_path, json_save_path)
VOC转COCO demo2:
import os
import random
import shutil
import sys
import json
import glob
import xml.etree.ElementTree as ET
"""
You only need to set the following three parts
1.val_files_num : num of validation samples from your all samples
2.test_files_num = num of test samples from your all samples
3.voc_annotations : path to your VOC dataset Annotations
"""
# 只需要该下边四个值即可
val_files_num = 170
test_files_num = 170
voc_annotations = '../VOCData/Annotations/' # remember to modify the path
main_path = '../'
split = voc_annotations.split('/')
coco_name = split[-3]
del split[-3]
del split[-2]
del split[-1]
del split[0]
# print(split)
for i in split:
main_path += '/' + i
main_path = main_path + '/'
# print(main_path)
coco_path = os.path.join(main_path, coco_name + '_COCO/')
coco_images = os.path.join(main_path, coco_name + '_COCO/images')
coco_json_annotations = os.path.join(main_path, coco_name + '_COCO/annotations/')
xml_val = os.path.join(main_path, 'xml', 'xml_val/')
xml_test = os.path.join(main_path, 'xml/', 'xml_test/')
xml_train = os.path.join(main_path, 'xml/', 'xml_train/')
voc_images = os.path.join(main_path, coco_name, 'JPEGImages/')
# from https://www.php.cn/python-tutorials-424348.html
def mkdir(path):
path = path.strip()
path = path.rstrip("\\")
isExists = os.path.exists(path)
if not isExists:
os.makedirs(path)
print(path + ' ----- folder created')
return True
else:
print(path + ' ----- folder existed')
return False
# foler to make, please enter full path
mkdir(coco_path)
mkdir(coco_images)
mkdir(coco_json_annotations)
mkdir(xml_val)
mkdir(xml_test)
mkdir(xml_train)
# voc images copy to coco images
for i in os.listdir(voc_images):
img_path = os.path.join(voc_images + i)
shutil.copy(img_path, coco_images)
# voc images copy to coco images
for i in os.listdir(voc_annotations):
img_path = os.path.join(voc_annotations + i)
shutil.copy(img_path, xml_train)
print("\n\n %s files copied to %s" % (val_files_num, xml_val))
for i in range(val_files_num):
if len(os.listdir(xml_train)) > 0:
random_file = random.choice(os.listdir(xml_train))
# print("%d) %s"%(i+1,random_file))
source_file = "%s/%s" % (xml_train, random_file)
if random_file not in os.listdir(xml_val):
shutil.move(source_file, xml_val)
else:
random_file = random.choice(os.listdir(xml_train))
source_file = "%s/%s" % (xml_train, random_file)
shutil.move(source_file, xml_val)
else:
print('The folders are empty, please make sure there are enough %d file to move' % (val_files_num))
break
for i in range(test_files_num):
if len(os.listdir(xml_train)) > 0:
random_file = random.choice(os.listdir(xml_train))
# print("%d) %s"%(i+1,random_file))
source_file = "%s/%s" % (xml_train, random_file)
if random_file not in os.listdir(xml_test):
shutil.move(source_file, xml_test)
else:
random_file = random.choice(os.listdir(xml_train))
source_file = "%s/%s" % (xml_train, random_file)
shutil.move(source_file, xml_test)
else:
print('The folders are empty, please make sure there are enough %d file to move' % (val_files_num))
break
print("\n\n" + "*" * 27 + "[ Done ! Go check your file ]" + "*" * 28)
# !/usr/bin/python
# pip install lxml
START_BOUNDING_BOX_ID = 1
PRE_DEFINE_CATEGORIES = None
# If necessary, pre-define category and its id
# PRE_DEFINE_CATEGORIES = {"aeroplane": 1, "bicycle": 2, "bird": 3, "boat": 4,
# "bottle":5, "bus": 6, "car": 7, "cat": 8, "chair": 9,
# "cow": 10, "diningtable": 11, "dog": 12, "horse": 13,
# "motorbike": 14, "person": 15, "pottedplant": 16,
# "sheep": 17, "sofa": 18, "train": 19, "tvmonitor": 20}
"""
main code below are from
https://github.com/Tony607/voc2coco
"""
def get(root, name):
vars = root.findall(name)
return vars
def get_and_check(root, name, length):
vars = root.findall(name)
if len(vars) == 0:
raise ValueError("Can not find %s in %s." % (name, root.tag))
if length > 0 and len(vars) != length:
raise ValueError(
"The size of %s is supposed to be %d, but is %d."
% (name, length, len(vars))
)
if length == 1:
vars = vars[0]
return vars
def get_filename_as_int(filename):
try:
filename = filename.replace("\\", "/")
filename = os.path.splitext(os.path.basename(filename))[0]
return int(filename)
except:
raise ValueError("Filename %s is supposed to be an integer." % (filename))
def get_categories(xml_files):
"""Generate category name to id mapping from a list of xml files.
Arguments:
xml_files {list} -- A list of xml file paths.
Returns:
dict -- category name to id mapping.
"""
classes_names = []
for xml_file in xml_files:
tree = ET.parse(xml_file)
root = tree.getroot()
for member in root.findall("object"):
classes_names.append(member[0].text)
classes_names = list(set(classes_names))
classes_names.sort()
return {name: i for i, name in enumerate(classes_names)}
def convert(xml_files, json_file):
json_dict = {"images": [], "type": "instances", "annotations": [], "categories": []}
if PRE_DEFINE_CATEGORIES is not None:
categories = PRE_DEFINE_CATEGORIES
else:
categories = get_categories(xml_files)
bnd_id = START_BOUNDING_BOX_ID
for xml_file in xml_files:
tree = ET.parse(xml_file)
root = tree.getroot()
path = get(root, "path")
if len(path) == 1:
filename = os.path.basename(path[0].text)
elif len(path) == 0:
filename = get_and_check(root, "filename", 1).text
else:
raise ValueError("%d paths found in %s" % (len(path), xml_file))
## The filename must be a number
image_id = get_filename_as_int(filename)
size = get_and_check(root, "size", 1)
width = int(get_and_check(size, "width", 1).text)
height = int(get_and_check(size, "height", 1).text)
image = {
"file_name": filename,
"height": height,
"width": width,
"id": image_id,
}
json_dict["images"].append(image)
## Currently we do not support segmentation.
# segmented = get_and_check(root, 'segmented', 1).text
# assert segmented == '0'
for obj in get(root, "object"):
category = get_and_check(obj, "name", 1).text
if category not in categories:
new_id = len(categories)
categories[category] = new_id
category_id = categories[category]
bndbox = get_and_check(obj, "bndbox", 1)
xmin = int(get_and_check(bndbox, "xmin", 1).text) - 1
ymin = int(get_and_check(bndbox, "ymin", 1).text) - 1
xmax = int(get_and_check(bndbox, "xmax", 1).text)
ymax = int(get_and_check(bndbox, "ymax", 1).text)
assert xmax > xmin
assert ymax > ymin
o_width = abs(xmax - xmin)
o_height = abs(ymax - ymin)
ann = {
"area": o_width * o_height,
"iscrowd": 0,
"image_id": image_id,
"bbox": [xmin, ymin, o_width, o_height],
"category_id": category_id,
"id": bnd_id,
"ignore": 0,
"segmentation": [],
}
json_dict["annotations"].append(ann)
bnd_id = bnd_id + 1
for cate, cid in categories.items():
cat = {"supercategory": "none", "id": cid, "name": cate}
json_dict["categories"].append(cat)
os.makedirs(os.path.dirname(json_file), exist_ok=True)
json_fp = open(json_file, "w")
json_str = json.dumps(json_dict)
json_fp.write(json_str)
json_fp.close()
xml_val_files = glob.glob(os.path.join(xml_val, "*.xml"))
xml_test_files = glob.glob(os.path.join(xml_test, "*.xml"))
xml_train_files = glob.glob(os.path.join(xml_train, "*.xml"))
convert(xml_val_files, coco_json_annotations + 'val2017.json')
convert(xml_test_files, coco_json_annotations + 'test2017.json')
convert(xml_train_files, coco_json_annotations + 'train2017.json')
【如果对您有帮助,交个朋友给个一键三连吧,您的肯定是我博客高质量维护的动力!!!】