提取COCO 数据集的部分类

1.python提取COCO数据集中特定的类

安装pycocotools github地址:https://github.com/philferriere/cocoapi

pip install git+https://github.com/philferriere/cocoapi.git#subdirectory=PythonAPI

若报错,pip install git+https://github.com/philferriere/cocoapi.git#subdirectory=PythonAPI

换成

pip install git+git://github.com/philferriere/cocoapi.git#subdirectory=PythonAPI

实在不行的话,手动下载

python 复制代码
git clone https://github.com/pdollar/coco.git
cd coco/PythonAPI
python setup.py build_ext --inplace #安装到本地
python setup.py build_ext install # 安装到Python环境中

没有的库自己pip

注意skimage用pip install scikit-image -i https://pypi.tuna.tsinghua.edu.cn/simple

提取特定的类别如下:

python 复制代码
# conding='utf-8'
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="/opt/10T/home/asc005/YangMingxiang/DenseCLIP_/data/COCO/"  #save_path
img_dir=savepath+'images/'
anno_dir=savepath+'Annotations/'
# datasets_list=['train2014', 'val2014']
datasets_list=['train2017', 'val2017']
 
classes_names = ['sheep']  #coco
#Store annotations and train2014/val2014/... in this folder
dataDir= '/opt/10T/home/asc005/YangMingxiang/DenseCLIP_/data/coco/'  #origin coco
 
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 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)
 
 
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+dataset+'/'+filename
    print(img_path)
    dst_imgpath=img_dir+filename
 
    img=cv2.imread(img_path)
    #if (img.shape[2] == 1):
    #    print(filename + " not a RGB image")
     #   return
    shutil.copy(img_path, dst_imgpath)
 
    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
    I=Image.open('%s/%s/%s'%(dataDir,dataset,img['file_name']))
    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 objs
 
for dataset in datasets_list:
    #./COCO/annotations/instances_train2014.json
    annFile='{}/annotations/instances_{}.json'.format(dataDir,dataset)
 
    #COCO API for initializing annotated data
    coco = COCO(annFile)

    #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)
    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):
            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)

然后就可以了

2. 将上面获取的数据集划分为训练集和测试集
python 复制代码
#conding='utf-8'
import os
import random
from shutil import copy2
 
# origin
image_original_path = "/opt/10T/home/asc005/YangMingxiang/DenseCLIP_/data/COCO/images"
label_original_path = "/opt/10T/home/asc005/YangMingxiang/DenseCLIP_/data/COCO/Annotations"

# parent_path = os.path.dirname(os.getcwd())
# parent_path = "D:\\AI_Find"
# train_image_path = os.path.join(parent_path, "image_data/seed/train/images/")
# train_label_path = os.path.join(parent_path, "image_data/seed/train/labels/")
train_image_path = os.path.join("/opt/10T/home/asc005/YangMingxiang/DenseCLIP_/data/COCO/train2017")
train_label_path = os.path.join("/opt/10T/home/asc005/YangMingxiang/DenseCLIP_/data/COCO/annotations/train2017")
test_image_path = os.path.join("/opt/10T/home/asc005/YangMingxiang/DenseCLIP_/data/COCO/val2017")
test_label_path = os.path.join("/opt/10T/home/asc005/YangMingxiang/DenseCLIP_/data/COCO/annotations/val2017")
 
 
# test_image_path = os.path.join(parent_path, 'image_data/seed/val/images/')
# test_label_path = os.path.join(parent_path, 'image_data/seed/val/labels/')
 
 
def mkdir():
    if not os.path.exists(train_image_path):
        os.makedirs(train_image_path)
    if not os.path.exists(train_label_path):
        os.makedirs(train_label_path)
 
    if not os.path.exists(test_image_path):
        os.makedirs(test_image_path)
    if not os.path.exists(test_label_path):
        os.makedirs(test_label_path)
 
 
def main():
    mkdir()
    all_image = os.listdir(image_original_path)
    for i in range(len(all_image)):
        num = random.randint(1,5)
        if num != 2:
            copy2(os.path.join(image_original_path, all_image[i]), train_image_path)
            train_index.append(i)
        else:
            copy2(os.path.join(image_original_path, all_image[i]), test_image_path)
            val_index.append(i)
 
    all_label = os.listdir(label_original_path)
    for i in train_index:
            copy2(os.path.join(label_original_path, all_label[i]), train_label_path)
    for i in val_index:
            copy2(os.path.join(label_original_path, all_label[i]), test_label_path)
 
 
if __name__ == '__main__':
    train_index = []
    val_index = []
    main()
3.将上一步提取的COCO 某一类 xml转为COCO标准的json文件:
python 复制代码
# -*- coding: utf-8 -*-
# @Time    : 2019/8/27 10:48
# @Author  :Rock
# @File    : voc2coco.py
# just for object detection
import xml.etree.ElementTree as ET
import os
import json

coco = dict()
coco['images'] = []
coco['type'] = 'instances'
coco['annotations'] = []
coco['categories'] = []

category_set = dict()
image_set = set()

category_item_id = 0
image_id = 0
annotation_id = 0


def addCatItem(name):
    global category_item_id
    category_item = dict()
    category_item['supercategory'] = 'none'
    category_item_id += 1
    category_item['id'] = category_item_id
    category_item['name'] = name
    coco['categories'].append(category_item)
    category_set[name] = category_item_id
    return category_item_id


def addImgItem(file_name, size):
    global image_id
    if file_name is None:
        raise Exception('Could not find filename tag in xml file.')
    if size['width'] is None:
        raise Exception('Could not find width tag in xml file.')
    if size['height'] is None:
        raise Exception('Could not find height tag in xml file.')
    img_id = "%04d" % image_id
    image_id += 1
    image_item = dict()
    image_item['id'] = int(img_id)
    # image_item['id'] = image_id
    image_item['file_name'] = file_name
    image_item['width'] = size['width']
    image_item['height'] = size['height']
    coco['images'].append(image_item)
    image_set.add(file_name)
    return image_id


def addAnnoItem(object_name, image_id, category_id, bbox):
    global annotation_id
    annotation_item = dict()
    annotation_item['segmentation'] = []
    seg = []
    # bbox[] is x,y,w,h
    # left_top
    seg.append(bbox[0])
    seg.append(bbox[1])
    # left_bottom
    seg.append(bbox[0])
    seg.append(bbox[1] + bbox[3])
    # right_bottom
    seg.append(bbox[0] + bbox[2])
    seg.append(bbox[1] + bbox[3])
    # right_top
    seg.append(bbox[0] + bbox[2])
    seg.append(bbox[1])

    annotation_item['segmentation'].append(seg)

    annotation_item['area'] = bbox[2] * bbox[3]
    annotation_item['iscrowd'] = 0
    annotation_item['ignore'] = 0
    annotation_item['image_id'] = image_id
    annotation_item['bbox'] = bbox
    annotation_item['category_id'] = category_id
    annotation_id += 1
    annotation_item['id'] = annotation_id
    coco['annotations'].append(annotation_item)


def parseXmlFiles(xml_path):
    for f in os.listdir(xml_path):
        if not f.endswith('.xml'):
            continue

        bndbox = dict()
        size = dict()
        current_image_id = None
        current_category_id = None
        file_name = None
        size['width'] = None
        size['height'] = None
        size['depth'] = None

        xml_file = os.path.join(xml_path, f)
        # print(xml_file)

        tree = ET.parse(xml_file)
        root = tree.getroot()
        if root.tag != 'annotation':
            raise Exception('pascal voc xml root element should be annotation, rather than {}'.format(root.tag))

        # elem is <folder>, <filename>, <size>, <object>
        for elem in root:
            current_parent = elem.tag
            current_sub = None
            object_name = None

            if elem.tag == 'folder':
                continue

            if elem.tag == 'filename':
                file_name = elem.text
                if file_name in category_set:
                    raise Exception('file_name duplicated')

            # add img item only after parse <size> tag
            elif current_image_id is None and file_name is not None and size['width'] is not None:
                if file_name not in image_set:
                    current_image_id = addImgItem(file_name, size)
                    # print('add image with {} and {}'.format(file_name, size))
                else:
                    raise Exception('duplicated image: {}'.format(file_name))
                    # subelem is <width>, <height>, <depth>, <name>, <bndbox>
            for subelem in elem:
                bndbox['xmin'] = None
                bndbox['xmax'] = None
                bndbox['ymin'] = None
                bndbox['ymax'] = None

                current_sub = subelem.tag
                if current_parent == 'object' and subelem.tag == 'name':
                    object_name = subelem.text
                    if object_name not in category_set:
                        current_category_id = addCatItem(object_name)
                    else:
                        current_category_id = category_set[object_name]

                elif current_parent == 'size':
                    if size[subelem.tag] is not None:
                        raise Exception('xml structure broken at size tag.')
                    size[subelem.tag] = int(subelem.text)

                # option is <xmin>, <ymin>, <xmax>, <ymax>, when subelem is <bndbox>
                for option in subelem:
                    if current_sub == 'bndbox':
                        if bndbox[option.tag] is not None:
                            raise Exception('xml structure corrupted at bndbox tag.')
                        bndbox[option.tag] = int(option.text)

                # only after parse the <object> tag
                if bndbox['xmin'] is not None:
                    if object_name is None:
                        raise Exception('xml structure broken at bndbox tag')
                    if current_image_id is None:
                        raise Exception('xml structure broken at bndbox tag')
                    if current_category_id is None:
                        raise Exception('xml structure broken at bndbox tag')
                    bbox = []
                    # x
                    bbox.append(bndbox['xmin'])
                    # y
                    bbox.append(bndbox['ymin'])
                    # w
                    bbox.append(bndbox['xmax'] - bndbox['xmin'])
                    # h
                    bbox.append(bndbox['ymax'] - bndbox['ymin'])
                    # print('add annotation with {},{},{},{}'.format(object_name, current_image_id, current_category_id,
                    #                                                bbox))
                    addAnnoItem(object_name, current_image_id, current_category_id, bbox)


if __name__ == '__main__':
	#修改这里的两个地址,一个是xml文件的父目录;一个是生成的json文件的绝对路径
    xml_path = r'G:\dataset\COCO\person\coco_val2014\annotations\\'
    json_file = r'G:\dataset\COCO\person\coco_val2014\instances_val2014.json'
    parseXmlFiles(xml_path)
    json.dump(coco, open(json_file, 'w'))
相关推荐
Kkooe1 小时前
GitLab|数据迁移
运维·服务器·git
Beekeeper&&P...2 小时前
git bash是什么,git是什么,git中的暂存区是什么,git中的本地仓库是什么,git中工作目录指的是什么
开发语言·git·bash
Stara05116 小时前
Git推送+拉去+uwsgi+Nginx服务器部署项目
git·python·mysql·nginx·gitee·github·uwsgi
lsswear7 小时前
GIT 操作
git
勋勋勋勋小勋勋7 小时前
git分支合并某一次提交
git
PandaCave8 小时前
git常用命令以及注意事项总结
git
Jurio.11 小时前
Conda 管理项目环境
人工智能·python·深度学习·conda·virtualenv·pip
算你狠 - ZGX12 小时前
Git使用
git
Lojarro18 小时前
【后端】版本控制
git·subversion