COCO数据集简介与处理
1、标准的coco数据标注的格式与下载
Dataset - COCO Dataset 数据特点
COCO数据集标注格式详解----object instances
Dataset之COCO数据集：COCO数据集的简介、下载、使用方法之详细攻略
COCO/VOC 数据集加速下载
{
"images": [
{
"height": 682,
"width": 1024,
"id": 1,
"file_name": "terrain2.png"
}
],
"categories": [
{
"supercategory": "car",
"id": 1,
"name": "car"
}
],
"annotations": [
{
"iscrowd": 0,
"image_id": 1,
"bbox": [
218.0,
448.0,
222.0,
161.0
],
"segmentation": [
[
218.0,
448.0,
440.0,
448.0,
440.0,
609.0,
218.0,
609.0
]
],
"category_id": 1,
"id": 1,
"area": 698368
},
{
"iscrowd": 0,
"image_id": 1,
"bbox": [
501.0,
451.0,
121.0,
92.0
],
"segmentation": [
[
501.0,
451.0,
622.0,
451.0,
622.0,
543.0,
501.0,
543.0
]
],
"category_id": 1,
"id": 2,
"area": 698368
},
{
"iscrowd": 0,
"image_id": 1,
"bbox": [
634.0,
437.0,
81.0,
56.0
],
"segmentation": [
[
634.0,
437.0,
715.0,
437.0,
715.0,
493.0,
634.0,
493.0
]
],
"category_id": 1,
"id": 3,
"area": 698368
},
{
"iscrowd": 0,
"image_id": 1,
"bbox": [
725.0,
423.0,
70.0,
51.0
],
"segmentation": [
[
725.0,
423.0,
795.0,
423.0,
795.0,
474.0,
725.0,
474.0
]
],
"category_id": 1,
"id": 4,
"area": 698368
},
{
"iscrowd": 0,
"image_id": 1,
"bbox": [
791.0,
404.0,
40.0,
47.0
],
"segmentation": [
[
791.0,
404.0,
831.0,
404.0,
831.0,
451.0,
791.0,
451.0
]
],
"category_id": 1,
"id": 5,
"area": 698368
}
]
}
1.1、COCO数据基本结构
这3种类型共享下面所列的基本类型，包括info、image、license，而annotation类型则呈现出了多态，会根据不同的任务具有不同的数据标注形式。
{
"info" : info,
"images" : [image],
"annotations" : [annotation],
"licenses" : [license],
}info{
"year" : int,
"version" : str,
"description" : str,
"contributor" : str,
"url" : str,
"date_created" : datetime,
}image{
"id" : int,
"width" : int,
"height" : int,
"file_name" : str,
"license" : int,
"flickr_url" : str,
"coco_url" : str,
"date_captured" : datetime,
}license{
"id" : int,
"name" : str,
"url" : str,
}
除了Annotation数据之外的数据类型举例如下：
1）info类型，比如一个info类型的实例：
"info":{
"description":"This is stable 1.0 version of the 2014 MS COCO dataset.",
"url":"http:\/\/mscoco.org",
"version":"1.0","year":2014,
"contributor":"Microsoft COCO group",
"date_created":"2015-01-27 09:11:52.357475"
}
2）Images类型，Images是包含多个image实例的数组，对于一个image类型的实例：{
"license":3,
"file_name":"COCO_val2014_000000391895.jpg",
"coco_url":"http:\/\/mscoco.org\/images\/391895",
"height":360,"width":640,"date_captured":"2013-11-14 11:18:45",
"flickr_url":"http:\/\/farm9.staticflickr.com\/8186\/8119368305_4e622c8349_z.jpg",
"id":391895
}
3）licenses类型，licenses是包含多个license实例的数组，对于一个license类型的实例：{
"url":"http:\/\/creativecommons.org\/licenses\/by-nc-sa\/2.0\/",
"id":1,
"name":"Attribution-NonCommercial-ShareAlike License"
1.2、COCO数据基本结构（Object Instance 类型的标注格式）
1）整体JSON文件格式
Object Instance这种格式的文件从头至尾按照顺序分为以下段落：
{
"info": info,
"licenses": [license],
"images": [image],
"annotations": [annotation],
"categories": [category]
}
是的，你打开这两个文件，虽然内容很多，但从文件开始到结尾按照顺序就是这5段。其中，info、licenses、images这三个结构体/类型 在上一节中已经说了，在不同的JSON文件中这三个类型是一样的，定义是共享的。不共享的是annotation和category这两种结构体，他们在不同类型的JSON文件中是不一样的。
PS，mages数组、annotations数组、categories数组的元素数量是相等的，等于图片的数量。
2）annotations字段
annotations字段是包含多个annotation实例的一个数组，annotation类型本身又包含了一系列的字段，如这个目标的category id和segmentation mask。segmentation格式取决于这个实例是一个单个的对象（即iscrowd=0，将使用polygons格式）还是一组对象（即iscrowd=1，将使用RLE格式）。如下所示：
annotation{
"id": int,
"image_id": int,
"category_id": int,
"segmentation": RLE or [polygon],
"area": float,
"bbox": [x,y,width,height],
"iscrowd": 0 or 1,
}
注意，单个的对象（iscrowd=0)可能需要多个polygon来表示，比如这个对象在图像中被挡住了。而iscrowd=1时（将标注一组对象，比如一群人）的segmentation使用的就是RLE格式。
另外，每个对象（不管是iscrowd=0还是iscrowd=1）都会有一个矩形框bbox ，矩形框左上角的坐标和矩形框的长宽会以数组的形式提供，数组第一个元素就是左上角的横坐标值。
其中，area是框的面积（area of encoded masks）。
3）categories字段
annotation结构中的categories字段存储的是当前对象所属的category的id，以及所属的supercategory的name。
categories是一个包含多个category实例的数组，而category结构体描述如下：
{
"id": int,
"name": str,
"supercategory": str,
}
从instances_val2017.json文件中摘出的2个category实例如下所示：
{
"supercategory": "person",
"id": 1,
"name": "person"
},
{
"supercategory": "vehicle",
"id": 2,
"name": "bicycle"
},
......
2、Create your own COCO-style datasets（构造自己格式的COCO数据）
Create your own COCO-style datasets，这个页面讲述了能够构造的COCO数据类型的详情信息，标注coco的Annotation工具，通过COCO的支持实现深度学习。
我们所要做的就是循环遍历每个图像jpeg及其对应的注释png，并让pycococreator生成正确格式的项。第90和91行创建图像条目，而第112-114行处理注释。
#!/usr/bin/env python3
import datetime
import json
import os
import re
import fnmatch
from PIL import Image
import numpy as np
from pycococreatortools import pycococreatortools
ROOT_DIR = 'train'
IMAGE_DIR = os.path.join(ROOT_DIR, "shapes_train2018")
ANNOTATION_DIR = os.path.join(ROOT_DIR, "annotations")
INFO = {
"description": "Example Dataset",
"url": "https://github.com/waspinator/pycococreator",
"version": "0.1.0",
"year": 2018,
"contributor": "waspinator",
"date_created": datetime.datetime.utcnow().isoformat(' ')
}
LICENSES = [
{
"id": 1,
"name": "Attribution-NonCommercial-ShareAlike License",
"url": "http://creativecommons.org/licenses/by-nc-sa/2.0/"
}
]
CATEGORIES = [
{
'id': 1,
'name': 'square',
'supercategory': 'shape',
},
{
'id': 2,
'name': 'circle',
'supercategory': 'shape',
},
{
'id': 3,
'name': 'triangle',
'supercategory': 'shape',
},
]
def filter_for_jpeg(root, files):
file_types = ['*.jpeg', '*.jpg']
file_types = r'|'.join([fnmatch.translate(x) for x in file_types])
files = [os.path.join(root, f) for f in files]
files = [f for f in files if re.match(file_types, f)]
return files
def filter_for_annotations(root, files, image_filename):
file_types = ['*.png']
file_types = r'|'.join([fnmatch.translate(x) for x in file_types])
basename_no_extension = os.path.splitext(os.path.basename(image_filename))[0]
file_name_prefix = basename_no_extension + '.*'
files = [os.path.join(root, f) for f in files]
files = [f for f in files if re.match(file_types, f)]
files = [f for f in files if re.match(file_name_prefix, os.path.splitext(os.path.basename(f))[0])]
return files
def main():
coco_output = {
"info": INFO,
"licenses": LICENSES,
"categories": CATEGORIES,
"images": [],
"annotations": []
}
image_id = 1
segmentation_id = 1
# filter for jpeg images
for root, _, files in os.walk(IMAGE_DIR):
image_files = filter_for_jpeg(root, files)
# go through each image
for image_filename in image_files:
image = Image.open(image_filename)
image_info = pycococreatortools.create_image_info(
image_id, os.path.basename(image_filename), image.size)
coco_output["images"].append(image_info)
# filter for associated png annotations
for root, _, files in os.walk(ANNOTATION_DIR):
annotation_files = filter_for_annotations(root, files, image_filename)
# go through each associated annotation
for annotation_filename in annotation_files:
print(annotation_filename)
class_id = [x['id'] for x in CATEGORIES if x['name'] in annotation_filename][0]
category_info = {'id': class_id, 'is_crowd': 'crowd' in image_filename}
binary_mask = np.asarray(Image.open(annotation_filename)
.convert('1')).astype(np.uint8)
annotation_info = pycococreatortools.create_annotation_info(
segmentation_id, image_id, category_info, binary_mask,
image.size, tolerance=2)
if annotation_info is not None:
coco_output["annotations"].append(annotation_info)
segmentation_id = segmentation_id + 1
image_id = image_id + 1
with open('{}/instances_shape_train2018.json'.format(ROOT_DIR), 'w') as output_json_file:
json.dump(coco_output, output_json_file)
if __name__ == "__main__":
main()
3、COCO数据处理工具箱（Pycocotools）
Github链接，visualizing it using the COCO API.
COCO数据评估的案例代码
%matplotlib inline
import matplotlib.pyplot as plt
from pycocotools.coco import COCO
from pycocotools.cocoeval import COCOeval
import numpy as np
import skimage.io as io
import pylab
pylab.rcParams['figure.figsize'] = (10.0, 8.0)
annType = ['segm','bbox','keypoints']
annType = annType[1] #specify type here
prefix = 'person_keypoints' if annType=='keypoints' else 'instances'
print 'Running demo for *%s* results.'%(annType)
#initialize COCO ground truth api
dataDir='../'
dataType='val2014'
annFile = '%s/annotations/%s_%s.json'%(dataDir,prefix,dataType)
cocoGt=COCO(annFile)
#initialize COCO detections api
resFile='%s/results/%s_%s_fake%s100_results.json'
resFile = resFile%(dataDir, prefix, dataType, annType)
cocoDt=cocoGt.loadRes(resFile)
imgIds=sorted(cocoGt.getImgIds())
imgIds=imgIds[0:100]
imgId = imgIds[np.random.randint(100)]
# running evaluation
cocoEval = COCOeval(cocoGt,cocoDt,annType)
cocoEval.params.imgIds = imgIds
cocoEval.evaluate()
cocoEval.accumulate()
cocoEval.summarize()模型结果的评估、可视化
python3 -m venv .venv
. .venv/bin/activate
pip install -r requirements.txt
streamlit run coco_explorer.py -- --coco_train ./coco_data/ground_truth_annotations.json --coco_predictions ./coco_data/predictions.json --images_path ./coco_data/val2017/