scripts for coco to pascal then to yolo,extract_person convert coco data to pascal,then voc_label convert that pascal data to yolo

customize_extract_person.py

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="./coco/cow/train/"
img_dir=savepath+'images/'
anno_dir=savepath+'Annotations/'
# datasets_list=['train2014', 'val2014']
datasets_list=['train2014']

classes_names = ['cow']
#Store annotations and train2014/val2014/... in this folder
dataDir= 'data/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']))
    #Get the annotated information by ID
    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)
    '''
    When the COCO object is created, the following information will be output:
    loading annotations into memory...
    Done (t=0.81s)
    creating index...
    index created!
    So far, the JSON script has been parsed and the images are associated with the corresponding annotated data.
    '''
    #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)

customize_voc_label.py

import xml.etree.ElementTree as ET
import pickle
import os
from os import listdir, getcwd
from os.path import join

sets=[('2014', 'train')]

classes = ["cow"]


def convert(size, box):
    dw = 1./(size[0])
    dh = 1./(size[1])
    x = (box[0] + box[1])/2.0 - 1
    y = (box[2] + box[3])/2.0 - 1
    w = box[1] - box[0]
    h = box[3] - box[2]
    x = x*dw
    w = w*dw
    y = y*dh
    h = h*dh
    return (x,y,w,h)

def convert_annotation(image_id):

    #in_file = open('VOCdevkit/VOC%s/Annotations/%s.xml'%(year, image_id))
    in_file = open('coco/cow/train/Annotations/%s.xml' % (image_id))
    out_file = open('coco/cow/train/labels/%s.txt'%(image_id), 'w')
    tree=ET.parse(in_file)
    root = tree.getroot()
    size = root.find('size')
    w = int(size.find('width').text)
    h = int(size.find('height').text)

    for obj in root.iter('object'):
        difficult = obj.find('difficult').text
        cls = obj.find('name').text
        if cls not in classes or int(difficult)==1:
            continue
        cls_id = classes.index(cls)
        xmlbox = obj.find('bndbox')
        b = (float(xmlbox.find('xmin').text), float(xmlbox.find('xmax').text), float(xmlbox.find('ymin').text), float(xmlbox.find('ymax').text))
        bb = convert((w,h), b)
        out_file.write(str(cls_id) + " " + " ".join([str(a) for a in bb]) + '\n')

wd = getcwd()

for image_set in sets:
    if not os.path.exists('coco/cow/train/labels/'):
        os.makedirs('coco/cow/train/labels/')
   # image_ids = open('VOCdevkit/VOC%s/ImageSets/Main/%s.txt'%(year, image_set)).read().strip().split()
    path = 'coco/cow/train/images/'
    for filename in os.listdir(path):
     image_ids = (filename).strip('.jpg').split()
     list_file = open('%s_%s.txt'%(image_set), 'w')

     for image_id in image_ids:
            list_file.write('/images/%s.jpg\n'%(image_id))
            convert_annotation(image_id)
list_file.close()

#os.system("cat 2007_train.txt 2012_train.txt > train.txt")

directory info
output should be as(below image)

input should be as(below image)

Note: match directories in scripts