一、安装pycocotools

1. 方法1，直接GitHub源码安装：

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

2. 方法2，安装COCOAPI【Linux版】:

   # COCOAPI=/path/to/clone/cocoapi
   git clone https://github.com/cocodataset/cocoapi.git $COCOAPI
   cd $COCOAPI/PythonAPI
   make
   python3.5 setup.py install --user  # 博主的Python版本为3.5，编译时改为自己对应版本
   

   如果在安装过程中出现：“pycocotools/_mask.c: No such file or directory” 错误，可参考: 解决编译 COCOAPI时出现的 “pycocotools/_mask.c: No such file or directory”错误

二、提取特定的类别

提取代码：

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="/path/to/generate/COCO/" 
img_dir=savepath+'images/'
anno_dir=savepath+'annotations/'
datasets_list=['train2017', 'val2017']

#coco有80类，这里写要提取类的名字，以person为例 
classes_names = ['person'] 
#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= '/path/to/coco_orgi/' 
 
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>
'''
 
# 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)

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。

三、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 <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__':
    # 需要自己设定的地址，一个是已生成的是xml文件的父目录；一个是要生成的json文件的目录
    xml_dir = r'/path/to/generate/COCO/annotations'
    json_dir = r'/path/to/save/COCO/annotations'
    dataset_lists = ['train2017', 'val2017']
    for dataset in dataset_lists:
        xml_path = os.path.join(xml_dir, dataset)
        json_file = json_dir + '/instances_{}.json'.format(dataset)
        parseXmlFiles(xml_path)
        json.dump(coco, open(json_file, 'w'))

原参考脚本不支持划分训练集和测试集，只能单个文件进行转换，本脚本对此进行了简单完善。获得特定类别的图像和对应json文件后，即可使用新获取的数据集对特定目标检测网络进行训练。

参考文献：

• python实现提取COCO,VOC数据集中特定的类
• 把voc格式的标注文件.xml转为coco格式的.json文件
• https://github.com/CivilNet/Gemfield/blob/master/src/python/pascal_voc_xml2json/pascal_voc_xml2json.py