目录
一.Coco标注数据介绍
1. Json detection标签文件解读
coco数据集的所有标注信息包含在一个json文件中,json文件中以字典格式保存信息. 总的json文件中有五类信息: info. licenses. images. annotations. categories .
我们主要关注后三类信息, 即图片的基本信息(name, height,width) ,每张图片的标注bbox和bbox的类别(category_id),以及总的类别id对应名称.
{ #image:图片信息 annotations:标注数据,categories:类别信息
#---------------------------------------------------
"info":info,
"licenses": [licenses],
"images":["file_name": "000000037777.jpg",
"height": 230,"width": 352,
"id": 37777]
"annotations":["image_id":289343,
#[xmin,ymin,width,height]
"bbox": [473.07,395.93,38.65,28.67],
"category_id": 18,"id": 1768],
"categories":[{"person","id": 1},
{"id": 17,"name": "cat"},
{"id": 18,"name": "dog"}]
}
2.代码读取json文件:
import json
annotate_path = "/home/wtj/Data/Coco2017/annotations/instances_train2017.json"
annos = json.loads(open(annotate_path).read())
print(type(annos))
print(len(annos))
print(annos.keys())
#print(annos["info"])
#print(annos["licenses"])
print(annos["images"][0]["file_name"],
annos["images"][0]["width"],annos["images"][0]["height"],
annos["images"][0]["id"])
print(annos["annotations"][0]["image_id"],
annos["annotations"][0]["bbox"],
annos["annotations"][0]["category_id"],
annos["annotations"][0]["id"])
x = annos["annotations"][0]["category_id"]
print(annos["categories"][x]["name"]) 
二. Voc 标注数据介绍
1. xml文件解读:
如框:即标注对应的图片名称,图片的shape,以及标注的目标的类别和位置.
2. 代码读取xml文件
import xml.etree.ElementTree as ET
xml_path = '/home/wtj/Data/Coco2017_pet/annotations/train2017/000000000042.xml'
tree = ET.ElementTree(file = xml_path)
root = tree.getroot() #获取跟节点
print(root)
name = root.find("filename").text
print(name)
for size in root.findall("size"):
width = size.find("width").text
height = size.find("height").text
depth = size.find("depth").text
print(width, height, depth)
for x in root.findall("object"):
cate = x.find("name").text
xmin = x.find("bndbox")[0].text
ymin = x.find("bndbox")[1].text
xmax = x.find("bndbox")[2].text
ymax = x.find("bndbox")[3].text
print(name, cate, xmin, ymin, xmax, ymax)
三.Coco和Voc 数据相互转换
1. json ---> xml
未更新完
2. xml ---> json
import xml.etree.ElementTree as ET
import os
import json
coco = dict()
coco['info'] = {"description": "COCO pet Dataset","version": "1.0","year": 2022,"date_created": "2022/3/18"}
coco['licenses']=[{"None":"good good study,day day up @-@"}]
coco['images'] = []
coco['annotations'] = []
coco['categories'] = []
category_set = dict()
image_set = set()
category_item_id = 0
image_id = 000000
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 parseXmlFiles(xml_path):
for f in os.listdir(xml_path):
if not f.endswith('.xml'): #判断字符串是否以指定字符串后缀结尾
continue #跳过当前循环,继续进入下一轮循环
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) #每一个xml地址
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(float(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(float(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 )
if __name__ == '__main__':
xml_path = '/home/wtj/Data/Coco2017_pet/annotations/val2017'
json_file = './val.json'
parseXmlFiles(xml_path)
json_path = open(json_file, 'w')
json.dump(coco, json_path)
json_path.close()
