COCO数据集格式（详解）及COCO标注可视化。json转COCO等代码
coco数据集JSON文件格式分为一下几个字段。
{
"info": info, # dict
"licenses": [license], # list ，内部是dict
"images": [image], # list ，内部是dict
"annotations": [annotation], # list ，内部是dict
"categories": # list ，内部是dict
}注意 ：对于深度学习训练，实际有用的字段，只有以下三个字段。
"images": [image], # list ，内部是dict
"annotations": [annotation], # list ，内部是dict
"categories": # list ，内部是dictinfo字段内的内容
"info":{#数据信息描述
"description":"COCO 2017 Dataset",# 数据描述
"url":"http://*****.org",#下载地址
"version":"1.0",#版本
"year":"2017",#年份
"contributor":"COCO Consortium",#提供者
"data_created":"2017/09/01",#创建日期}这个字段可以忽略，可以为空。
licenses字段
"licenses"：[
{
'url': 'http://creativecommons.org/licenses/by-nc-sa/2.0/',
'id': 1,
'name': 'Attribution-NonCommercial-ShareAlike License'
}
....
....
]这个字段可以忽略，可以为空。
images
"images": [
{
"license":4 #可以忽略
"file_name":000.jpg #可以忽略
"coco_url":"http://****" #可以忽略
"id": 1,
"file_name": "000.tif",
"width": 48.0,
"height": 112.0
"date_captured":"2022-02-02 17:02:02" #可以忽略
"flickl_url":"http://****" #可以忽略
}
...
...
]annotations
这个字段里面都是有用信息
categories
这个里面也是有用的信息
将一个大的json文件生成只有一张图片的json：
from __future__ import print_function
from pycocotools.coco import COCO
import os, sys, zipfile
import urllib.request
import shutil
import numpy as np
import skimage.io as io
import matplotlib.pyplot as plt
import pylab
import json
json_file='/media/fire/d/share_data/datasets/coco/annotations/person_keypoints_val2017.json' #
# Object Instance 类型的标注
# person_keypoints_val2017.json
# Object Keypoint 类型的标注格式
# captions_val2017.json
# Image Caption的标注格式
data=json.load(open(json_file,'r'))
data_2={}
data_2['info']=data['info']
data_2['licenses']=data['licenses']
data_2['images']=[data['images'][0]] # 只提取第一张图片
data_2['categories']=data['categories']
annotation=[] # 通过imgID 找到其所有对象
imgID=data_2['images'][0]['id']
for ann in data['annotations']:
if ann['image_id']==imgID:
annotation.append(ann)
data_2['annotations']=annotation # 保存到新的JSON文件，便于查看数据特点
json.dump(data_2,open('/media/fire/d/share_data/datasets/coco/annotations/test_person_keypoints_val2017.json','w'),indent=4) # indent=4 更加美观显示二、COCO数据集可视化
from __future__ import print_function
from pycocotools.coco import COCO
import os, sys, zipfile
import urllib.request
import shutil
import numpy as np
import skimage.io as io
import matplotlib.pyplot as plt
import pylab
pylab.rcParams['figure.figsize'] = (8.0, 10.0)
annFile='/media/fire/d/share_data/datasets/coco/annotations/person_keypoints_val2017.json'
coco=COCO(annFile) # display COCO categories and supercategories
cats = coco.loadCats(coco.getCatIds())
nms=[cat['name'] for cat in cats]
print('COCO categories: \n{}\n'.format(' '.join(nms)))
nms = set([cat['supercategory'] for cat in cats])
print('COCO supercategories: \n{}'.format(' '.join(nms)))
# imgIds = coco.getImgIds(imgIds = [324158])
imgIds = coco.getImgIds()
img = coco.loadImgs(imgIds[0])[0]
dataDir = '/media/fire/d/share_data/datasets/coco'
dataType = 'val2017'
I = io.imread('%s/%s/%s'%(dataDir,dataType,img['file_name']))
#plt.axis('off')
plt.imshow(I)
plt.show()
显示图片
加载肢体关键点：
catIds=[]
for ann in coco.dataset['annotations']:
if ann['image_id']==imgIds[0]:
catIds.append(ann['category_id'])
plt.imshow(I);
plt.axis('off')
annIds = coco.getAnnIds(imgIds=img['id'], catIds=catIds, iscrowd=None)
anns = coco.loadAnns(annIds)
print(anns)
coco.showAnns(anns)
plt.imshow(I); plt.axis('off'); plt.show()
加载instances mask：
coco = COCO("/media/fire/d/share_data/datasets/coco/annotations/instances_val2017.json")
img_ids = coco.getImgIds()
print(len(img_ids))
cat_ids = []
for ann in coco.dataset["annotations"]:
if ann["image_id"] == img_ids[0]:
cat_ids.append(ann["category_id"])
ann_ids = coco.getAnnIds(imgIds=img_ids[0], catIds = cat_ids)
ann_ids2 = coco.getAnnIds(imgIds=img_ids[0], catIds = cat_ids)
plt.imshow(I)
print(ann_ids)
print(ann_ids2)
anns = coco.loadAnns(ann_ids)
coco.showAnns(anns)
plt.imshow(I)
plt.show()图像效果
三、不同标注数据转换到COCO格式
下面为labelme json格式转到COCO格式。
def image(self,data,num):
image={}
img = utils.img_b64_to_array(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]
self.height=height
self.width=width
return image
def categorie(self,label):
categorie={}
categorie['supercategory'] = label[0]
categorie['id']=len(self.label)+1 # 0 默认为背景
categorie['name'] = label[1]
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['category_id'] = self.getcatid(label)
annotation['id'] = self.annID
return annotation