代码1
coco数据集过大，希望从里面挑选特定的类别，来构成测试集。
以下cocodeal.py文件能够保留coco中指定的类别数据，同时生成.xml文件。具体应用可以见代码注释。
#cocodeal.py
#本文件处理coco数据集，删除指定类别数据。要处理的目录结构如下。最后生成Annotations和images备份文件。
#并且在images_coco文件夹中是我们想要的。
# 如下是必须需要的目录或文件，其中annotations存着.xml文件，images下的train2014和val2014存着.jpg文件，labels下的train2014和val2014存着.txt文件信息
# ├── coco
# │ ├── annotations # 里面是*.xml
# │ ├── images
# │ │ ├── train2014 # 里面是*.jpg
# │ │ └── val2014 # 里面是*.jpg
# │ └── labels
# │ ├── train2014 # 里面是*.txt
# │ └── val2014 # 里面是*.txt
# |—— cocodeal.py # 本文件
#生成annotations_filtered和images_filtered文件夹
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, ImageFile
ImageFile.LOAD_TRUNCATED_IMAGES = True
#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)
###########################修改以下参数适配路径
#the path you want to save your results for coco to voc
savepath="" # 保存的路径
img_dir = savepath+'images_filtered/' # 保存图片的文件夹路径
mkr(img_dir)
anno_dir = savepath+'annotations_filtered/' # 保存xml的文件夹路径
mkr(anno_dir)
datasets_list=['train2014', 'val2014'] # 与 coco/images里的两个文件夹名一致
# datasets_list=['train2014']
# datasets_list = ['val2017']
# 你需要挑出的类的名称
classes_names = ["elephant"] # 要保留的类别list
#Store annotations and train2014/val2014/... in this folder
dataDir = 'coco' # coco数据集所在的位置。本文件与该文件夹在同一级目录下
###############################
headstr = """\
<annotation>
<folder>VOC</folder>
<filename>%s</filename>
<source>
<database>My Database</database>
<annotation>COCO</annotation>
<image>flickr</image>
<flickrid>NULL</flickrid>
</source>
<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>
'''
def id2name(coco):
classes=dict()
for cls in coco.dataset['categories']:
classes[cls['id']]=cls['name']
return classes
def 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)
f.close()
# 根据.jpg文件名，生成对应的.xml文件，并且把.jpg文件复制到dst_imgpath目录下
def save_annotations_and_imgs(coco,dataset,filename,objs):
#eg:COCO_train2014_000000196610.jpg-->COCO_train2014_000000196610.xml
anno_path=anno_dir+filename[:-3]+'xml'
img_path=dataDir+'/images/'+dataset+'/'+filename
# print(img_path)
dst_imgpath=img_dir+dataset+"/"+filename
img=cv2.imread(img_path)
# print(img)
if (img.shape[2] == 1):
print(filename + " not a RGB image")
return
shutil.copy(img_path, dst_imgpath) #复制
head=headstr % (filename, img.shape[1], img.shape[0], img.shape[2])
tail = tailstr
write_xml(anno_path,head, objs, tail)
def showimg(coco,dataset,img,classes,cls_id,show=True):
global dataDir
if show:
I=Image.open('%s/%s/%s/%s'%(dataDir,'images',dataset,img['file_name']))
#Get the annotated information by ID
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)
if show:
draw = ImageDraw.Draw(I)
draw.rectangle([xmin, ymin, xmax, ymax])
if show:
plt.figure()
plt.axis('off')
plt.imshow(I)
plt.show()
return objs
# myfile = open("imageID.txt", "w+")
for dataset in datasets_list:
mkr(img_dir+dataset)
#./COCO/annotations/instances_train2014.json
# .json文件所在的位置
annFile='{}/annotations/instances_{}.json'.format(dataDir,dataset)
#COCO API for initializing annotated data
coco = COCO(annFile)
'''
When the COCO object is created, the following information will be output:
loading annotations into memory...
Done (t=0.81s)
creating index...
index created!
So far, the JSON script has been parsed and the images are associated with the corresponding annotated data.
'''
#show all classes in coco
classes = id2name(coco)
print(classes)
#[1, 2, 3, 4, 6, 8]
classes_ids = coco.getCatIds(catNms=classes_names)
print(classes_ids)
# exit()
for cls in classes_names:
#Get ID number of this class
cls_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):
# print(imgId, file=myfile)
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)
# myfile.close()代码2
通过上面代码能够筛选出想要的种类的数据集。如果觉得数据集过大，或者想要生成这些图片文件的名称（不含.jpg），可以通过以下代码来实现。
#getImageID.py
#本文件将提前取出前selct_n张train图片和val图片，并且提取出对应的annotations里的.xml文件，同时把文件名称（不含.jpg）存于文本文件中
#与cocodeal.py在同一目录，先运行cocodeal.py，再手动检查前selct_n张图片的内容，再运行本文件
#生成的文件存于同目录下的myimages和myannotations文件夹。以及train2014imgid.txt,val2014imgid.txt。
#有需要的话自己手动修改文件夹名称。可以先手动筛过images_filtered里前selct_n张图片再运行本文件。
# .
# ├── annotations_filtered 需要的文件夹
# ├── coco
# ├── cocodeal.py
# ├── getImageID.py 本文件
# ├── images_filtered 需要的文件夹
# ├── myannotations 生成的文件夹
# ├── myimages 生成的文件夹
# ├── train2014imgid.txt 生成的文件
# ├── val2014imgid.txt 生成的文件
import os
import shutil
selct_n = 200 # 挑选出200张jpg图片
#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)
img_src = "images_filtered/" # 从该路径下的train2014文件夹与val2014文件夹里面选出照片
anno_src = "annotations_filtered/"
img_path = "myimages/"
anno_path = "myannotations/"
mkr(img_path) # 挑出来的图片保存在该文件夹下
mkr(anno_path) # 挑出来的.xml文件保存在该文件夹下
sets = ['train2014', 'val2014'] # train的图片存放与myimages/train2014/文件夹下，val放在myimages/val2014/下
for x in sets:
cnt = 0
myfile = open(x+"imgid.txt", "w+") # 覆盖写。存储图片的名称（不含.jpg）
mkr(img_path+x) # myimages/train2014/ 或 myimages/val2014/
for dirpath, dirnames, filenames in os.walk(img_src+x):
# print(filenames)
print(dirnames)
print(dirpath)
for filename in filenames:
cnt+=1
if cnt > selct_n:
break
print(filename[:-4], file=myfile)
shutil.copy(src=dirpath+"/"+filename, dst=img_path+x+"/"+filename)
shutil.copy(src=anno_src+filename[:-4]+".xml", dst=anno_path+filename[:-4]+".xml")
myfile.close()
版权声明：本文为CSDN博主「hh_is_vegetable」的原创文章，遵循CC 4.0 BY-SA版权协议，转载请附上原文出处链接及本声明。
原文链接：https://blog.csdn.net/hh1986170901/article/details/122791169
暂无评论