Open Images数据集解析----下载Open Images V4指定的类别数据

本文主要是介绍Open Images数据集解析----下载Open Images V4指定的类别数据，希望对大家解决编程问题提供一定的参考价值，需要的开发者们随着小编来一起学习吧！

1.下载Open Images的注释文件

注释文件如下：

Class Names:

           class-descriptions-boxable.csv      数据集内部使用的类名到人类可理解名称的对应

Boxes:

          train-annotations-bbox.csv              训练图像中对象实例的边框注释
          validation-annotations-bbox.csv     验证图像中对象实例的边框注释
        test-annotations-bbox.csv                测试图像中对象实例的边框注释

下载地址：

wget https://storage.googleapis.com/openimages/2018_04/class-descriptions-boxable.csv

wget https://storage.googleapis.com/openimages/2018_04/train/train-annotations-bbox.csv

wget https://storage.googleapis.com/openimages/2018_04/validation/validation-annotations-bbox.csv

wget https://storage.googleapis.com/openimages/2018_04/test/test-annotations-bbox.csv

2.需要的包

管理AWS服务的统一工具

sudo pip3 install awscli

sudo pip3 install tqdm

3.运行脚本

python3 downloadOI.py --classes 'Bicycle' --mode train

可选的参数

parser.add_argument("--mode", help="Dataset category - train, validation or test", required=True)
parser.add_argument("--classes", help="Names of object classes to be downloaded", required=True)
parser.add_argument("--nthreads", help="Number of threads to use", required=False, type=int, default=cpu_count*2)
parser.add_argument("--occluded", help="Include occluded images", required=False, type=int, default=1)
parser.add_argument("--truncated", help="Include truncated images", required=False, type=int, default=1)
parser.add_argument("--groupOf", help="Include groupOf images", required=False, type=int, default=1)
parser.add_argument("--depiction", help="Include depiction images", required=False, type=int, default=1)
parser.add_argument("--inside", help="Include inside images", required=False, type=int, default=1)

4.downloadOI.py

#Author : Sunita Nayak, Big Vision LLC#### Usage example: python3 downloadOI.py --classes 'Ice_cream,Cookie' --mode trainimport argparse
import csv
import subprocess
import os
from tqdm import tqdm
import multiprocessing
from multiprocessing import Pool as thread_poolcpu_count = multiprocessing.cpu_count()parser = argparse.ArgumentParser(description='Download Class specific images from OpenImagesV4')
parser.add_argument("--mode", help="Dataset category - train, validation or test", required=True)
parser.add_argument("--classes", help="Names of object classes to be downloaded", required=True)
parser.add_argument("--nthreads", help="Number of threads to use", required=False, type=int, default=cpu_count*2)
parser.add_argument("--occluded", help="Include occluded images", required=False, type=int, default=1)
parser.add_argument("--truncated", help="Include truncated images", required=False, type=int, default=1)
parser.add_argument("--groupOf", help="Include groupOf images", required=False, type=int, default=1)
parser.add_argument("--depiction", help="Include depiction images", required=False, type=int, default=1)
parser.add_argument("--inside", help="Include inside images", required=False, type=int, default=1)args = parser.parse_args()run_mode = args.modethreads = args.nthreadsclasses = []
for class_name in args.classes.split(','):classes.append(class_name)with open('./class-descriptions-boxable.csv', mode='r') as infile:reader = csv.reader(infile)dict_list = {rows[1]:rows[0] for rows in reader}subprocess.run(['rm', '-rf', 'labels'])
subprocess.run([ 'mkdir', 'labels'])subprocess.run(['rm', '-rf', 'JPEGImages'])
subprocess.run([ 'mkdir', 'JPEGImages'])pool = thread_pool(threads)
commands = []
cnt = 0for ind in range(0, len(classes)):class_name = classes[ind]print("Class "+str(ind) + " : " + class_name)subprocess.run([ 'mkdir', run_mode+'/'+class_name])command = "grep "+dict_list[class_name.replace('_', ' ')] + " ./" + run_mode + "-annotations-bbox.csv"class_annotations = subprocess.run(command.split(), stdout=subprocess.PIPE).stdout.decode('utf-8')class_annotations = class_annotations.splitlines()for line in class_annotations:line_parts = line.split(',')#IsOccluded,IsTruncated,IsGroupOf,IsDepiction,IsInsideif (args.occluded==0 and int(line_parts[8])>0):print("Skipped %s",line_parts[0])continueif (args.truncated==0 and int(line_parts[9])>0):print("Skipped %s",line_parts[0])continueif (args.groupOf==0 and int(line_parts[10])>0):print("Skipped %s",line_parts[0])continueif (args.depiction==0 and int(line_parts[11])>0):print("Skipped %s",line_parts[0])continueif (args.inside==0 and int(line_parts[12])>0):print("Skipped %s",line_parts[0])continuecnt = cnt + 1command = 'aws s3 --no-sign-request --only-show-errors cp s3://open-images-dataset/'+run_mode+'/'+line_parts[0]+'.jpg '+ 'JPEGImages'+'/'+class_name+'/'+line_parts[0]+'.jpg'commands.append(command)with open('labels/%s.txt'%(line_parts[0]),'a') as f:f.write(' '.join([str(ind), str((float(line_parts[5]) + float(line_parts[4]))/2), str((float(line_parts[7]) + float(line_parts[6]))/2), str(float(line_parts[5])-float(line_parts[4])), str(float(line_parts[7])-float(line_parts[6]))])+'\n')print("Annotation Count : "+str(cnt))
commands = list(set(commands))
print("Number of images to be downloaded : "+str(len(commands)))list(tqdm(pool.imap(os.system, commands), total = len(commands) ))pool.close()
pool.join()

下载的对应Bicycle图片