记录一下

["person","bicycle","car","motorcycle","airplane","bus","train","truck","boat","traffic light","fire hydrant","stop sign","parking meter","bench","bird","cat","dog","horse","sheep","cow","elephant","bear","zebra","giraffe","backpack","umbrella","handbag","tie","suitcase","frisbee","skis","snowboard","sports ball","kite","baseball bat","baseball glove","skateboard","surfboard","tennis racket","bottle","wine glass","cup","fork","knife","spoon","bowl","banana","apple","sandwich","orange","broccoli","carrot","hot dog","pizza","donut","cake","chair","couch","potted plant","bed","dining table","toilet","tv","laptop","mouse","remote","keyboard","cell phone","microwave","oven","toaster","sink","refrigerator","book","clock","vase","scissors","teddy bear","hair drier","toothbrush",]

coco.names

person
bicycle
car
motorbike
aeroplane
bus
train
truck
boat
traffic light
fire hydrant
stop sign
parking meter
bench
bird
cat
dog
horse
sheep
cow
elephant
bear
zebra
giraffe
backpack
umbrella
handbag
tie
suitcase
frisbee
skis
snowboard
sports ball
kite
baseball bat
baseball glove
skateboard
surfboard
tennis racket
bottle
wine glass
cup
fork
knife
spoon
bowl
banana
apple
sandwich
orange
broccoli
carrot
hot dog
pizza
donut
cake
chair
sofa
pottedplant
bed
diningtable
toilet
tvmonitor
laptop
mouse
remote
keyboard
cell phone
microwave
oven
toaster
sink
refrigerator
book
clock
vase
scissors
teddy bear
hair drier
toothbrush

将json文件转变成xml文件

import os
import time
import json
import pandas as pd
from tqdm import tqdm
from pycocotools.coco import COCOdef trans_id(category_id):names = []namesid = []for i in range(0, len(cats)):names.append(cats[i]['name'])namesid.append(cats[i]['id'])#print('id:{1}\t {0}'.format(names[i], namesid[i]))index = namesid.index(category_id)return indexanno  = "./person/coco/instances_train2017.json"
xml_dir = 'coco2017/Annotations'coco = COCO(anno)  # 读文件
cats = coco.loadCats(coco.getCatIds())  # 这里loadCats就是coco提供的接口，获取类别# Create anno dir
dttm = time.strftime("%Y%m%d%H%M%S", time.localtime())
if os.path.exists(xml_dir):os.rename(xml_dir, xml_dir + dttm)
os.mkdir(xml_dir)with open(anno, 'r') as load_f:f = json.load(load_f)imgs = f['images']df_cate = pd.DataFrame(f['categories'])
df_cate_sort = df_cate.sort_values(["id"], ascending=True)
categories = list(df_cate_sort['name'])
print('categories = ',categories)
df_anno = pd.DataFrame(f['annotations'])for i in tqdm(range(len(imgs))):xml_content = []file_name = imgs[i]['file_name']height = imgs[i]['height']img_id = imgs[i]['id']width = imgs[i]['width']xml_content.append("<annotation>")xml_content.append("	<folder>VOC2007</folder>")xml_content.append("	<filename>" + file_name + "</filename>")xml_content.append("	<size>")xml_content.append("		<width>" + str(width) + "</width>")xml_content.append("		<height>" + str(height) + "</height>")xml_content.append("	</size>")xml_content.append("	<segmented>0</segmented>")# 通过img_id找到annotationsannos = df_anno[df_anno["image_id"].isin([img_id])]for index, row in annos.iterrows():bbox = row["bbox"]category_id = row["category_id"]cate_name = categories[trans_id(category_id)]# add new objectxml_content.append("	<object>")xml_content.append("		<name>" + cate_name + "</name>")xml_content.append("		<pose>Unspecified</pose>")xml_content.append("		<truncated>0</truncated>")xml_content.append("		<difficult>0</difficult>")xml_content.append("		<bndbox>")xml_content.append("			<xmin>" + str(int(bbox[0])) + "</xmin>")xml_content.append("			<ymin>" + str(int(bbox[1])) + "</ymin>")xml_content.append("			<xmax>" + str(int(bbox[0] + bbox[2])) + "</xmax>")xml_content.append("			<ymax>" + str(int(bbox[1] + bbox[3])) + "</ymax>")xml_content.append("		</bndbox>")xml_content.append("	</object>")xml_content.append("</annotation>")x = xml_contentxml_content = [x[i] for i in range(0, len(x)) if x[i] != "\n"]### list存入文件xml_path = os.path.join(xml_dir, file_name.replace('.jpg', '.xml'))with open(xml_path, 'w+', encoding="utf8") as f:f.write('\n'.join(xml_content))xml_content[:] = []

筛选出固定几类，下面的例子是筛选了person类别

from pycocotools.coco import COCO
import os
import shutil
from tqdm import tqdm
import skimage.io as io
import matplotlib.pyplot as plt
import cv2
from PIL import Image, ImageDraw#the path you want to save your results for coco to voc
savepath="./person/"  #保存提取类的路径,我放在同一路径下
img_dir=savepath+'JPEGImages/'
anno_dir=savepath+'Annotations/'
# datasets_list=['train2014', 'val2014']
# datasets_list=['test2017']
datasets_list=['train2017']classes_names = ['person']  #coco有80类，这里写要提取类的名字，以person为例
#Store annotations and train2014/val2014/... in this folder
# dataDir= '/algdata/xuyy/coco2017/'  #原coco数据集
dataDir= './person/coco/'  #原coco数据集headstr = """\
<annotation><folder>VOC</folder><filename>%s</filename><source><database>My Database</database><annotation>COCO</annotation><image>flickr</image><flickrid>NULL</flickrid></source><owner><flickrid>NULL</flickrid><name>company</name></owner><size><width>%d</width><height>%d</height><depth>%d</depth></size><segmented>0</segmented>
"""
objstr = """\<object><name>%s</name><pose>Unspecified</pose><truncated>0</truncated><difficult>0</difficult><bndbox><xmin>%d</xmin><ymin>%d</ymin><xmax>%d</xmax><ymax>%d</ymax></bndbox></object>
"""tailstr = '''\
</annotation>
'''#if the dir is not exists,make it,else delete it
def mkr(path):if os.path.exists(path):shutil.rmtree(path)os.mkdir(path)else:os.mkdir(path)
mkr(img_dir)
mkr(anno_dir)
def id2name(coco):classes=dict()for cls in coco.dataset['categories']:classes[cls['id']]=cls['name']return classesdef write_xml(anno_path,head, objs, tail):f = open(anno_path, "w")f.write(head)for obj in objs:f.write(objstr%(obj[0],obj[1],obj[2],obj[3],obj[4]))f.write(tail)def save_annotations_and_imgs(coco,dataset,filename,objs):#eg:COCO_train2014_000000196610.jpg-->COCO_train2014_000000196610.xmlanno_path=anno_dir+filename[:-3]+'xml'img_path=dataDir+dataset+'/'+filenameprint(img_path)dst_imgpath=img_dir+filenameimg=cv2.imread(img_path)#if (img.shape[2] == 1):#    print(filename + " not a RGB image")#   returnshutil.copy(img_path, dst_imgpath)head=headstr % (filename, img.shape[1], img.shape[0], img.shape[2])tail = tailstrwrite_xml(anno_path,head, objs, tail)def showimg(coco,dataset,img,classes,cls_id,show=True):global dataDirI=Image.open('%s/%s/%s'%(dataDir,dataset,img['file_name']))#通过id，得到注释的信息annIds = coco.getAnnIds(imgIds=img['id'], catIds=cls_id, iscrowd=None)# print(annIds)anns = coco.loadAnns(annIds)# print(anns)# coco.showAnns(anns)objs = []for ann in anns:class_name=classes[ann['category_id']]if class_name in classes_names:print(class_name)if 'bbox' in ann:bbox=ann['bbox']xmin = int(bbox[0])ymin = int(bbox[1])xmax = int(bbox[2] + bbox[0])ymax = int(bbox[3] + bbox[1])obj = [class_name, xmin, ymin, xmax, ymax]objs.append(obj)draw = ImageDraw.Draw(I)draw.rectangle([xmin, ymin, xmax, ymax])if show:plt.figure()plt.axis('off')plt.imshow(I)plt.show()return objsif __name__ == "__main__":for dataset in datasets_list:#./COCO/annotations/instances_train2014.json# annFile='{}/annotations_trainval2017/annotations/instances_{}.json'.format(dataDir,dataset)annFile='{}/instances_{}.json'.format(dataDir,dataset)#COCO API for initializing annotated datacoco = COCO(annFile)#show all classes in cococlasses = id2name(coco)print(classes)#[1, 2, 3, 4, 6, 8]classes_ids = coco.getCatIds(catNms=classes_names)print(classes_ids)for cls in classes_names:#Get ID number of this classcls_id=coco.getCatIds(catNms=[cls])img_ids=coco.getImgIds(catIds=cls_id)print(cls,len(img_ids))# imgIds=img_ids[0:10]for imgId in tqdm(img_ids):img = coco.loadImgs(imgId)[0]filename = img['file_name']# print(filename)objs=showimg(coco, dataset, img, classes,classes_ids,show=False)print(objs)save_annotations_and_imgs(coco, dataset, filename, objs)

划分数据集

import os
import randomtrainval_percent = 0.95  #可以自己修改
train_percent = 0.95     #可以自己修改
xmlfilepath = 'coco2017/Annotations'
txtsavepath = 'coco2017/ImageSets/Main'
if not os.path.exists(txtsavepath):os.makedirs(txtsavepath)
total_xml = os.listdir(xmlfilepath)num=len(total_xml)
list=range(num)
tv=int(num*trainval_percent)
tr=int(tv*train_percent)
trainval= random.sample(list,tv)
train=random.sample(trainval,tr)ftrainval = open('coco2017/ImageSets/Main/trainval.txt', 'w')
ftest = open('coco2017/ImageSets/Main/test.txt', 'w')
ftrain = open('coco2017/ImageSets/Main/train.txt', 'w')
fval = open('coco2017/ImageSets/Main/val.txt', 'w')for i  in list:name=total_xml[i][:-4]+'\n'if i in trainval:ftrainval.write(name)if i in train:ftrain.write(name)else:fval.write(name)else:ftest.write(name)ftrainval.close()
ftrain.close()
fval.close()
ftest.close()