CoCo转Voc后，提取person类。

CoCo数据格式转Yolo格，并从Yolo格式中提取相应类别

本篇博文为转载大佬文章，因自己网上踩坑无数，为了帮助大家可以看到此优质文章特此转载（侵权删）
链接为：https://www.cnblogs.com/shuimuqingyang/p/13651038.html

1. 创建一个转换格式的环境

   git clone https://github.com/cocodataset/cocoapi.git cd
   cocoapi/PythonAPI
   make

2. 创建一个 person.py 用于专门从coco数据中提取person类。

   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="/home/coco80/Voc/voc_person/"    #数据保存地址 下述图片和xml文件
   img_dir=savepath+'JPEGImages/'
   anno_dir=savepath+'Annotations/'
   # datasets_list=['train2014', 'val2014']      
   datasets_list=['train2017']
   
   classes_names = ['person']
   dataDir= '/home/yd/code/duchangchun/coco80/CoCo/'   #官网下载的COCO2017（无标签）数据集
   
   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']))
       #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_train2014.json
       annFile='{}/annotations/instances_{}.json'.format(dataDir,dataset)
   
       #COCO API for initializing annotated data
       coco = COCO(annFile)
       '''
       COCO 对象创建完毕后会输出如下信息:
       loading annotations into memory...
       Done (t=0.81s)
       creating index...
       index created!
       至此, json 脚本解析完毕, 并且将图片和对应的标注数据关联起来.
       '''
       #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)
   

3. 运行后如果报错：

   ModuleNotFoundError: No module named ‘skimage’

   终端输入：
   pip install scikit-image -i http://pypi.douban.com/simple

4. 安装成功后再次运行 person.py