COCO2017数据集-截取某一或多个类-随机截取训练集和验证集-xml格式转json

 从CSDN上找到各种对COCO数据集的操作做一个简单的汇总。

由于coco数据集较大，模型训练时间过长，或者设备不支持如此多的数据进行训练，需要我们对数据集进行截取操作。

首先：classes_names =[ ]输入你想选的类别

该脚本执行完后会获得需要提取的特定类别的图片及其对应VOC格式的标注文件.xml。下面还需将生成的.xml文件转化为COCO格式的.json文件。

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

# 需要设置的路径
savepath = "F:/coco-fan/"
img_dir = savepath + 'images/'
anno_dir = savepath + 'annotations/'
datasets_list = ['train2017']

# coco有80类，这里写要提取类的名字，以person为例
classes_names = ['elephant']
# 包含所有类别的原coco数据集路径
'''
目录格式如下：
$COCO_PATH
----|annotations
----|train2017
----|val2017
----|test2017
'''
dataDir = 'F:/coco/'

headstr = """\

    VOC
    %s
    
        My Database
        COCO
        flickr
        NULL
    
    
        NULL
        company
    
    
        %d
        %d
        %d
    
    0
"""
objstr = """\
    
"""

tailstr = '''\

'''


# 检查目录是否存在，如果存在，先删除再创建，否则，直接创建
def mkr(path):
    if not os.path.exists(path):
        os.makedirs(path)  # 可以创建多级目录


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):
    # 将图片转为xml，例:COCO_train2017_000000196610.jpg-->COCO_train2017_000000196610.xml
    dst_anno_dir = os.path.join(anno_dir, dataset)
    mkr(dst_anno_dir)
    anno_path = dst_anno_dir + '/' + filename[:-3] + 'xml'
    img_path = dataDir + dataset + '/' + filename
    print("img_path: ", img_path)
    dst_img_dir = os.path.join(img_dir, dataset)
    mkr(dst_img_dir)
    dst_imgpath = dst_img_dir + '/' + filename
    print("dst_imgpath: ", dst_imgpath)
    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']))
    # 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 objs


for dataset in datasets_list:
    # ./COCO/annotations/instances_train2017.json
    annFile = '{}/annotations/instances_{}.json'.format(dataDir, dataset)

    # 使用COCO API用来初始化注释数据
    coco = COCO(annFile)

    # 获取COCO数据集中的所有类别
    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:
        # 获取该类的id
        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)

其次，把VOC格式的标注文件.xml转为COCO格式的.json文件

转换代码如下：

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 = 20180000000
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.')
    image_id += 1
    image_item = dict()
    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 , , ,