文章目錄
1 MSCOCO數據集簡介
1.1 概要
現今最流行的公開數據集是啥？COCO，Common Objects in Context。現如今最先進的視覺檢測模型都是在COCO上評測了。
相較於上一代的Pascal VOC，COCO擁有更多的圖片–330K，更多的標註–1.5 million，更多的物體類別–80類，更復雜的場景，更多的小的物體，總之就是更大更復雜更具挑戰性，也更具說服力。想了解更多，移步COCO官網
1.2 數據集格式
COCO一共有5種不同任務分類，分別是目標檢測、關鍵點檢測、語義分割、場景分割和圖像描述。COCO數據集的標註文件以JSON格式保存，官方的註釋文件有仨 captions_type.json instances_type.json person_keypoints_type.json，其中的type是 train/val/test+year，比如captions_train2017.json instances_train2017.json person_keypoints_train2017.json,其中目標檢測的註釋放在instances_xxx.json裏。
公共格式
{
//公共格式，三個json文件開頭都是他們
"info" : info, //數據集的信息，
"images" : [image],//數據集中所有圖片的信息，詳細見下方
"annotations" : [annotation], //數據集中註釋的信息
"licenses" : [license],//這個是證書信息，跑模型時不用理會
}
info{
"year" : int, //數據集年份 2014,2015,2017。
"version" : str, //剩下信息不必理會
"description" : str,
"contributor" : str,
"url" : str,
"date_created" : datetime,
}
image{//對每一張圖片
"id" : int, //可唯一標識圖片的 圖片id
"width" : int,//圖片的 寬、高，，，，沒有提到圖片的depth
"height" : int,
"file_name" : str, //文件名稱 ，"xxx.jpg"
"license" : int,
"flickr_url" : str,
"coco_url" : str,
"date_captured" : datetime,
}
license{
"id" : int,
"name" : str,
"url" : str,
}
特有格式-目標檢測類
//注意：COCO中的每個annotation是獨立的，有自己的id。比如說目標檢測，一張圖片中的每個object是單獨存在的，都有自己的一個annotation實例。
annotation{
"id" : int, //object id
"image_id" : int,//這個object在哪個圖片中
"category_id" : int, //object的類別
"segmentation" : RLE or [polygon],//分割用，
"area" : float,
"bbox" : [x,y,width,height],//劃重點，bbox,以左上角爲原點，是實際座標！！
"iscrowd" : 0 or 1,
}
categories[//這個是所有類別的一個總的集合，python.list,比如COCO一共有80類，那它的大小就是80。其中的每一個類別又有如下的結構
{
"id" : int,//類別id
"name" : str, //類名
"supercategory" : str,//父 類名，通常不用管
}
]
2 動手製作
僅以目標檢測爲例！！！
自己製作時只需要image,annotation,categories就足夠了。
2.1 數據集框架準備
找個位置，新建文件夾coco，進入coco，新建兩個文件夾images,annotations，最終形成的目錄結構應該是
- coco/
- images/
- annotations/
2.1 製作xml格式的annotation文件
參考【筆記】從零開始製作自己的Pascal VOC數據集的2.1小節。
2.2 xml2coco
把剛纔用到的圖片直接拷貝到 coco/images。
運行如下腳本：
注意：腳本文件來自腳本地址，只做了一點修改使得結果更符合強迫症患者
# -*- coding: utf-8 -*-
# @Time : 2019/7/8 16:10
# @Author : lazerliu
# @File : voc2coco.py
# just for object detection
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 = 0
image_id = 0
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.')
img_id = "%04d" % image_id
image_id += 1
image_item = dict()
image_item['id'] = int(img_id)
# 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'):
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)
if __name__ == '__main__':
#修改這裏的兩個地址，一個是xml文件的父目錄；一個是生成的json文件的絕對路徑
xml_path = 'xxx/VOCdevkit/VOC2007/Annotations/'
json_file = 'xxx/coco/annotations/instances.json'
parseXmlFiles(xml_path)
json.dump(coco, open(json_file, 'w'))
至此，自制的coco數據集完成。
3 測試
測試製作的coco數據集能否被cocoapi識別。
3.1 安裝cocoapi
git clone https://github.com/cocodataset/cocoapi.git
cd cocoapi/PythonAPI
make
3.2 實測
# -*- coding: utf-8 -*-
# @Time : 2019/7/8 14:32
# @Author : lazerliu
# @File : CocoForm_Learn.py
import sys
import json
sys.path.append("/xxx/cocoapi/PythonAPI")#把cocoapi的絕對路徑加上
from pycocotools.coco import COCO
ann_file = "xxx/coco/annotations/instances.json"# json文件的絕對路徑
coco = COCO(annotation_file=ann_file)
print("coco\nimages.size [%05d]\tannotations.size [%05d]\t category.size [%05d]\ndone!"
%(len(coco.imgs),len(coco.anns),len(coco.cats)))
