一、安裝pycocotools方法1，直接GitHub原始碼安裝： pip install git+https://github.com/philferriere/cocoapi.git #subdirectory=PythonAPI 1方法2，安裝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版本為3.5，編譯時改為自己對應版本

如果在安裝過程中出現：“pycocotools/_mask.c: No such file or directory” 錯誤，可參考: 解決編譯 COCOAPI時出現的 “pycocotools/_mask.c: No such file or directory”錯誤

提取程式碼：

from pycocotools.coco import COCOimport osimport shutilfrom tqdm import tqdmimport skimage.io as ioimport matplotlib.pyplot as pltimport cv2from PIL import Image, ImageDraw # 需要設定的路徑savepath="/path/to/generate/COCO/" dir=savepath+'images/'anno_dir=savepath+'annotations/'datasets_list=['train2017', 'val2017']#coco有80類，這裡寫要提取類的名字，以person為例 classes_names = ['person'] #包含所有類別的原coco資料集路徑'''目錄格式如下：$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>''' # 檢查目錄是否存在，如果存在，先刪除再建立，否則，直接建立def mkr(path):    if os.path.exists(path):        shutil.rmtree(path)        os.makedirs(path)  # 可以建立多級目錄    else:        os.makedirs(path)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):    #將圖片轉為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'    path=dataDir+dataset+'/'+filename    print("img_path: ", 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']))    #透過id，得到註釋的資訊    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用來初始化註釋資料    coco = COCO(annFile)     #獲取COCO資料集中的所有類別    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:        #獲取該類的id        cls_id=coco.getCatIds(catNms=[cls])        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)

該指令碼執行完後會獲得需要提取的特定類別的圖片及其對應VOC格式的標註檔案.xml。下面還需將生成的.xml檔案轉化為COCO格式的.json檔案。

轉換程式碼如下：

import xml.etree.ElementTree as ETimport osimport jsoncoco = dict()coco['images'] = []coco['type'] = 'instances'coco['annotations'] = []coco['categories'] = []category_set = dict()image_set = set()category_item_id = 0image_id = 20180000000annotation_id = 0def 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_iddef 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_iddef 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__':    # 需要自己設定的地址，一個是已生成的是xml檔案的父目錄；一個是要生成的json檔案的目錄    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'))

原參考指令碼不支援劃分訓練集和測試集，只能單個檔案進行轉換，本指令碼對此進行了簡單完善。獲得特定類別的影象和對應json檔案後，即可使用新獲取的資料集對特定目標檢測網路進行訓練。