Tips:COCO原数据集格式为.json格式，需要先转为VOC格式，再转为YOLO所需的.txt格式

一、数据集下载

百度网盘:https://pan.baidu.com/s/1YcxHxXfyoViTn2GH2xrPRA
提取码：38ts

二、COCO转VOC格式

##############（80类别都转化）##############

import argparse, json
import cytoolz
from lxml import etree, objectify
import os, re
 
 
def instance2xml_base(anno):
    E = objectify.ElementMaker(annotate=False)
    anno_tree = E.annotation(
        E.folder('VOC2014_instance/{}'.format(anno['category_id'])),
        E.filename(anno['file_name']),
        E.source(
            E.database('MS COCO 2014'),
            E.annotation('MS COCO 2014'),
            E.image('Flickr'),
            E.url(anno['coco_url'])
        ),
        E.size(
            E.width(anno['width']),
            E.height(anno['height']),
            E.depth(3)
        ),
        E.segmented(0),
    )
    return anno_tree
 
 
def instance2xml_bbox(anno, bbox_type='xyxy'):
    """bbox_type: xyxy (xmin, ymin, xmax, ymax); xywh (xmin, ymin, width, height)"""
    assert bbox_type in ['xyxy', 'xywh']
    if bbox_type == 'xyxy':
        xmin, ymin, w, h = anno['bbox']
        xmax = xmin+w
        ymax = ymin+h
    else:
        xmin, ymin, xmax, ymax = anno['bbox']
    E = objectify.ElementMaker(annotate=False)
    anno_tree = E.object(
        E.name(anno['category_id']),
        E.bndbox(
            E.xmin(xmin),
            E.ymin(ymin),
            E.xmax(xmax),
            E.ymax(ymax)
        ),
        E.difficult(anno['iscrowd'])
    )
    return anno_tree
 
 
def parse_instance(content, outdir):
    categories = {d['id']: d['name'] for d in content['categories']}
    # merge images and annotations: id in images vs image_id in annotations
    merged_info_list = list(map(cytoolz.merge, cytoolz.join('id', content['images'], 'image_id', content['annotations'])))
    # convert category id to name
    for instance in merged_info_list:
        instance['category_id'] = categories[instance['category_id']]
    # group by filename to pool all bbox in same file
    for name, groups in cytoolz.groupby('file_name', merged_info_list).items():
        anno_tree = instance2xml_base(groups[0])
        # if one file have multiple different objects, save it in each category sub-directory
        filenames = []
        for group in groups:
            filenames.append(os.path.join(outdir, re.sub(" ", "_", group['category_id']),
                                    os.path.splitext(name)[0] + ".xml"))
            anno_tree.append(instance2xml_bbox(group, bbox_type='xyxy'))
        for filename in filenames:
            etree.ElementTree(anno_tree).write(filename, pretty_print=True)
        print("Formating instance xml file {} done!".format(name))
 
 
def keypoints2xml_base(anno):
    annotation = etree.Element("annotation")
    etree.SubElement(annotation, "folder").text = "VOC2014_keypoints"
    etree.SubElement(annotation, "filename").text = anno['file_name']
    source = etree.SubElement(annotation, "source")
    etree.SubElement(source, "database").text = "MS COCO 2014"
    etree.SubElement(source, "annotation").text = "MS COCO 2014"
    etree.SubElement(source, "image").text = "Flickr"
    etree.SubElement(source, "url").text = anno['coco_url']
    size = etree.SubElement(annotation, "size")
    etree.SubElement(size, "width").text = str(anno["width"])
    etree.SubElement(size, "height").text = str(anno["height"])
    etree.SubElement(size, "depth").text = '3'
    etree.SubElement(annotation, "segmented").text = '0'
    return annotation
 
 
def keypoints2xml_object(anno, xmltree, keypoints_dict, bbox_type='xyxy'):
    assert bbox_type in ['xyxy', 'xywh']
    if bbox_type == 'xyxy':
        xmin, ymin, w, h = anno['bbox']
        xmax = xmin+w
        ymax = ymin+h
    else:
        xmin, ymin, xmax, ymax = anno['bbox']
    key_object = etree.SubElement(xmltree, "object")
    etree.SubElement(key_object, "name").text = anno['category_id']
    bndbox = etree.SubElement(key_object, "bndbox")
    etree.SubElement(bndbox, "xmin").text = str(xmin)
    etree.SubElement(bndbox, "ymin").text = str(ymin)
    etree.SubElement(bndbox, "xmax").text = str(xmax)
    etree.SubElement(bndbox, "ymax").text = str(ymax)
    etree.SubElement(key_object, "difficult").text = '0'
    keypoints = etree.SubElement(key_object, "keypoints")
    for i in range(0, len(keypoints_dict)):
        keypoint = etree.SubElement(keypoints, keypoints_dict[i+1])
        etree.SubElement(keypoint, "x").text = str(anno['keypoints'][i*3])
        etree.SubElement(keypoint, "y").text = str(anno['keypoints'][i*3+1])
        etree.SubElement(keypoint, "v").text = str(anno['keypoints'][i*3+2])
    return xmltree
 
 
def parse_keypoints(content, outdir):
    keypoints = dict(zip(range(1, len(content['categories'][0]['keypoints'])+1), content['categories'][0]['keypoints']))
    # merge images and annotations: id in images vs image_id in annotations
    merged_info_list = map(cytoolz.merge, cytoolz.join('id', content['images'], 'image_id', content['annotations']))
    # convert category name to person
    for keypoint in merged_info_list:
        keypoint['category_id'] = "person"
    # group by filename to pool all bbox and keypoint in same file
    for name, groups in cytoolz.groupby('file_name', merged_info_list).items():
        filename = os.path.join(outdir, os.path.splitext(name)[0]+".xml")
        anno_tree = keypoints2xml_base(groups[0])
        for group in groups:
            anno_tree = keypoints2xml_object(group, anno_tree, keypoints, bbox_type="xyxy")
        doc = etree.ElementTree(anno_tree)
        doc.write(open(filename, "w"), pretty_print=True)
        print("Formating keypoints xml file {} done!".format(name))
 
 
def main(args):
    if not os.path.exists(args.output_dir):
        os.makedirs(args.output_dir)
    content = json.load(open(args.anno_file, 'r'))
    if args.type == 'instance':
        # make subdirectories
        sub_dirs = [re.sub(" ", "_", cate['name']) for cate in content['categories']]
        for sub_dir in sub_dirs:
            sub_dir = os.path.join(args.output_dir, str(sub_dir))
            if not os.path.exists(sub_dir):
                os.makedirs(sub_dir)
        parse_instance(content, args.output_dir)
    elif args.type == 'keypoint':
        parse_keypoints(content, args.output_dir)
 
 
if __name__ == "__main__":
    parser = argparse.ArgumentParser()
    parser.add_argument("--anno_file", default = '这里填写COCO的标签路径例如：/Path/to/instances_train2014.json', help="annotation file for object instance/keypoint")
    parser.add_argument("--type", default = 'instance',type=str, help="object instance or keypoint", choices=['instance', 'keypoint'])
    parser.add_argument("--output_dir", default = '这里填写生成VOC标签的保存路径', help="output directory for voc annotation xml file")
    args = parser.parse_args()
    main(args)

##############（选择某个类别转化，只需要修改64行代码）##############

import argparse, json
import cytoolz
from lxml import etree, objectify
import os, re
 
 
def instance2xml_base(anno):
    E = objectify.ElementMaker(annotate=False)
    anno_tree = E.annotation(
        E.folder('VOC2014_instance/{}'.format(anno['category_id'])),
        E.filename(anno['file_name']),
        E.source(
            E.database('MS COCO 2014'),
            E.annotation('MS COCO 2014'),
            E.image('Flickr'),
            E.url(anno['coco_url'])
        ),
        E.size(
            E.width(anno['width']),
            E.height(anno['height']),
            E.depth(3)
        ),
        E.segmented(0),
    )
    return anno_tree
 
 
def instance2xml_bbox(anno, bbox_type='xyxy'):
    """bbox_type: xyxy (xmin, ymin, xmax, ymax); xywh (xmin, ymin, width, height)"""
    assert bbox_type in ['xyxy', 'xywh']
    if bbox_type == 'xyxy':
        xmin, ymin, w, h = anno['bbox']
        xmax = xmin+w
        ymax = ymin+h
    else:
        xmin, ymin, xmax, ymax = anno['bbox']
    E = objectify.ElementMaker(annotate=False)
    anno_tree = E.object(
        E.name(anno['category_id']),
        E.bndbox(
            E.xmin(xmin),
            E.ymin(ymin),
            E.xmax(xmax),
            E.ymax(ymax)
        ),
        E.difficult(anno['iscrowd'])
    )
    return anno_tree
 
 
def parse_instance(content, outdir):
    categories = {d['id']: d['name'] for d in content['categories']}
    # merge images and annotations: id in images vs image_id in annotations
    merged_info_list = list(map(cytoolz.merge, cytoolz.join('id', content['images'], 'image_id', content['annotations'])))
    # convert category id to name
    for instance in merged_info_list:
        instance['category_id'] = categories[instance['category_id']]
    # group by filename to pool all bbox in same file
    for name, groups in cytoolz.groupby('file_name', merged_info_list).items():
        anno_tree = instance2xml_base(groups[0])
        # if one file have multiple different objects, save it in each category sub-directory
        filenames = []
        for group in groups:
            if group['category_id']=='person':   #这里可以修改为COCO的其他类别，就可以输出相应的VOC格式文件
                filenames.append(os.path.join(outdir, re.sub(" ", "_", group['category_id']),
                                        os.path.splitext(name)[0] + ".xml"))
                anno_tree.append(instance2xml_bbox(group, bbox_type='xyxy'))
        for filename in filenames:
            etree.ElementTree(anno_tree).write(filename, pretty_print=True)
        print("Formating instance xml file {} done!".format(name))
 
 
def keypoints2xml_base(anno):
    annotation = etree.Element("annotation")
    etree.SubElement(annotation, "folder").text = "VOC2014_keypoints"
    etree.SubElement(annotation, "filename").text = anno['file_name']
    source = etree.SubElement(annotation, "source")
    etree.SubElement(source, "database").text = "MS COCO 2014"
    etree.SubElement(source, "annotation").text = "MS COCO 2014"
    etree.SubElement(source, "image").text = "Flickr"
    etree.SubElement(source, "url").text = anno['coco_url']
    size = etree.SubElement(annotation, "size")
    etree.SubElement(size, "width").text = str(anno["width"])
    etree.SubElement(size, "height").text = str(anno["height"])
    etree.SubElement(size, "depth").text = '3'
    etree.SubElement(annotation, "segmented").text = '0'
    return annotation
 
 
def keypoints2xml_object(anno, xmltree, keypoints_dict, bbox_type='xyxy'):
    assert bbox_type in ['xyxy', 'xywh']
    if bbox_type == 'xyxy':
        xmin, ymin, w, h = anno['bbox']
        xmax = xmin+w
        ymax = ymin+h
    else:
        xmin, ymin, xmax, ymax = anno['bbox']
    key_object = etree.SubElement(xmltree, "object")
    etree.SubElement(key_object, "name").text = anno['category_id']
    bndbox = etree.SubElement(key_object, "bndbox")
    etree.SubElement(bndbox, "xmin").text = str(xmin)
    etree.SubElement(bndbox, "ymin").text = str(ymin)
    etree.SubElement(bndbox, "xmax").text = str(xmax)
    etree.SubElement(bndbox, "ymax").text = str(ymax)
    etree.SubElement(key_object, "difficult").text = '0'
    keypoints = etree.SubElement(key_object, "keypoints")
    for i in range(0, len(keypoints_dict)):
        keypoint = etree.SubElement(keypoints, keypoints_dict[i+1])
        etree.SubElement(keypoint, "x").text = str(anno['keypoints'][i*3])
        etree.SubElement(keypoint, "y").text = str(anno['keypoints'][i*3+1])
        etree.SubElement(keypoint, "v").text = str(anno['keypoints'][i*3+2])
    return xmltree
 
 
def parse_keypoints(content, outdir):
    keypoints = dict(zip(range(1, len(content['categories'][0]['keypoints'])+1), content['categories'][0]['keypoints']))
    # merge images and annotations: id in images vs image_id in annotations
    merged_info_list = map(cytoolz.merge, cytoolz.join('id', content['images'], 'image_id', content['annotations']))
    # convert category name to person
    for keypoint in merged_info_list:
        keypoint['category_id'] = "person"
    # group by filename to pool all bbox and keypoint in same file
    for name, groups in cytoolz.groupby('file_name', merged_info_list).items():
        filename = os.path.join(outdir, os.path.splitext(name)[0]+".xml")
        anno_tree = keypoints2xml_base(groups[0])
        for group in groups:
            anno_tree = keypoints2xml_object(group, anno_tree, keypoints, bbox_type="xyxy")
        doc = etree.ElementTree(anno_tree)
        doc.write(open(filename, "w"), pretty_print=True)
        print("Formating keypoints xml file {} done!".format(name))
 
 
def main(args):
    if not os.path.exists(args.output_dir):
        os.makedirs(args.output_dir)
    content = json.load(open(args.anno_file, 'r'))
    if args.type == 'instance':
        # make subdirectories
        sub_dirs = [re.sub(" ", "_", cate['name']) for cate in content['categories']]
        for sub_dir in sub_dirs:
            sub_dir = os.path.join(args.output_dir, str(sub_dir))
            if not os.path.exists(sub_dir):
                os.makedirs(sub_dir)
        parse_instance(content, args.output_dir)
    elif args.type == 'keypoint':
        parse_keypoints(content, args.output_dir)
 
 
if __name__ == "__main__":
    parser = argparse.ArgumentParser()
    parser.add_argument("--anno_file", default = '这里填写COCO的标签路径例如：/Path/to/instances_train2014.json', help="annotation file for object instance/keypoint")
    parser.add_argument("--type", default = 'instance',type=str, help="object instance or keypoint", choices=['instance', 'keypoint'])
    parser.add_argument("--output_dir", default = '这里填写生成VOC标签的保存路径', help="output directory for voc annotation xml file")
    args = parser.parse_args()
    main(args)

三、VOC转YOLO .TXT

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


def convert(size, box):
    # size=(width, height)  b=(xmin, xmax, ymin, ymax)
    # x_center = (xmax+xmin)/2        y_center = (ymax+ymin)/2
    # x = x_center / width            y = y_center / height
    # w = (xmax-xmin) / width         h = (ymax-ymin) / height

    x_center = (box[0] + box[1]) / 2.0
    y_center = (box[2] + box[3]) / 2.0
    x = x_center / size[0]
    y = y_center / size[1]

    w = (box[1] - box[0]) / size[0]
    h = (box[3] - box[2]) / size[1]

    # print(x, y, w, h)
    return (x, y, w, h)


def convert_annotation(xml_files_path, save_txt_files_path, classes):
    xml_files = os.listdir(xml_files_path)
    # print(xml_files)
    for xml_name in xml_files:
        print(xml_name)
        xml_file = os.path.join(xml_files_path, xml_name)
        out_txt_path = os.path.join(save_txt_files_path, xml_name.split('.')[0] + '.txt')
        out_txt_f = open(out_txt_path, 'w')
        tree = ET.parse(xml_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))
            # b=(xmin, xmax, ymin, ymax)
            # print(w, h, b)
            bb = convert((w, h), b)
            out_txt_f.write(str(cls_id) + " " + " ".join([str(a) for a in bb]) + '\n')


if __name__ == "__main__":
    # 把forklift_pallet的voc的xml标签文件转化为yolo的txt标签文件
    # 1、需要转化的类别
    # classes = ['car',  'bus',  'van', 'others']  # 注意：这里根据自己的类别名称及种类自行更改
    classes = ['person']  # 注意：这里根据自己的类别名称及种类自行更改
    # 2、voc格式的xml标签文件路径
    xml_files1 = r'E:\project\py-project\network\dataset\COCO\voc\person'
    # 3、转化为yolo格式的txt标签文件存储路径
    save_txt_files1 = r'E:\project\py-project\network\dataset\COCO\yolo'

    convert_annotation(xml_files1, save_txt_files1, classes)

四、Reference

1、将COCO数据集转成VOC数据集，还可以提取单独的类别分离出来，像行人检测数据集。
2、https://github.com/CasiaFan/Dataset_to_VOC_converter