将COCO数据集转成YOLO格式数据集，可提取单独的类别分离出来。

最新推荐文章于 2024-07-05 09:30:53 发布
最新推荐文章于 2024-07-05 09:30:53 发布
阅读量1.1k 收藏 7
点赞数
文章标签： YOLO
版权声明：本文为博主原创文章，遵循 CC 4.0 BY-SA 版权协议，转载请附上原文出处链接和本声明。
本文链接：https://blog.csdn.net/lafsca5/article/details/130547063
版权

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

Huang3stone
关注
  • 0
    点赞
  • 踩
  • 7
    收藏
    觉得还不错? 一键收藏
  • 1
    评论
coco数据集转yolo
qq_41413211的博客
04-26 361
yolov5自己有标注，下载之后可以看到，train的json文件，train,val的图片文件是缺少的，直接从yolov5里把缺少的拖过去就能用了。问题描述：yolo怎么跑coco数据集？bash get_coco.sh在window中不能使用怎么办？方法一：自己转换（不推荐）这个可能有自带数据集。
coco格式数据集 json转换成yolo格式数据集txt
最新发布
07-18
coco格式数据集 json转换成yolo格式数据集txt
coco数据集格式转yolo数据格式
小张的技术分享博客
01-11 2747
COCO（Common Objects in Context）是一个广泛使用的目标检测和分割数据集，而YOLO（You Only Look Once）是一种流行的实时目标检测算法。首先，导入了必要的库，包括json和os。然后，定义了一个名为的函数，用于将COCO数据转换为YOLO格式。该函数接受一个COCO数据的字典作为输入，并返回转换后的YOLO数据和类别字典。在函数内部，提取了COCO数据中的图像列表、注释和类别信息。然后，创建了一个空的YOLO数据列表和一个用于存储类别名和序号映射关系的字典。
COCO目标检测标签转YOLO格式+按需实现标签筛选
qq_40387714的博客
07-05 555
COCO标签转YOLO：将下载的训练集标签instances_train2017.json和验证集标签instances_val2017.json转成YOLO格式。
将coco格式数据集转换为yolo格式数据集
Li_yan的博客
10-13 5067
将coco格式的数据集转换成yolo格式
coco数据集转yolo数据集（简单易懂）
qq_43471945的博客
12-03 8554
coco数据集转yolo数据集
COCO格式转YOLO
11-18 8826
环境window 10 64bitcoco yolo前言前文 MS COCO数据集 介绍过了 COCO 数据集，COCO 是将所有图片对应的标注信息写在了一个 json 文件里，如下coc...
yolo格式手势识别数据集-1+ 1万多数据
02-24
1、yolo格式手势识别数据集1，使用lableimg标注软件，标注好的真实场景的高质量图片数据，图片格式为jpg，标签yolo格式，txt文件，可以直接用于YOLO、Faster-RCNN等算法手机识别，数据场景丰富，包含图像，标注文件...
手势识别数据集VOC+YOLO格式270张3类别.zip
01-02
数据集格式：Pascal VOC格式+YOLO格式(不包含分割路径的txt文件，仅仅包含jpg图片以及对应的VOC格式xml文件和yolo格式txt文件) 图片数量(jpg文件个数)：270 标注数量(xml文件个数)：270 标注数量(txt文件个数)：270 ...
玩手机检测数据集VOC+YOLO格式8201张1类别
01-08
数据集格式：Pascal VOC格式+YOLO格式(不包含分割路径的txt文件，仅仅包含jpg图片以及对应的VOC格式xml文件和yolo格式txt文件) 图片数量(jpg文件个数)：8201 标注数量(xml文件个数)：8201 标注数量(txt文件个数)：...
印章检测数据集VOC+YOLO格式210张1类别
01-04
数据集格式：Pascal VOC格式+YOLO格式(不包含分割路径的txt文件，仅仅包含jpg图片以及对应的VOC格式xml文件和yolo格式txt文件) 图片数量(jpg文件个数)：210 标注数量(xml文件个数)：210 标注数量(txt文件个数)：210 ...
Python将COCO格式实例分割数据集转换为YOLO格式实例分割数据集
FriendshipTang的博客
07-28 2294
Python、COCO、YOLO、Json、实例分割
coco格式数据集 json转换成yolo格式数据集txt（python代码）
qq_53821866的博客
09-08 1053
import os# os.path.splitext(image['file_name'])将图像文件名（例如："image001.jpg"）分为两部分：文件名（不包括扩展名）和扩展名。# 这个函数返回一个包含两个元素的元组，第一个元素是文件名（不包括扩展名），第二个元素是扩展名。# 首先，检查所有轮廓线信息是否属于相同的物体类别# 然后，遍历所有轮廓线信息并进行归一化处理# 最后，将归一化后的信息写入文件中。
【目标检测】COCO格式数据集转换为YOLO格式
ericdiii的博客
05-25 275
目标检测COCO格式数据集转换为YOLO格式
3.keypoint关键点检测-COCO格式转为YOLO格式
Snakewood的博客
05-25 1225
网上没找到有关 关键点检测-COCO格式转为YOLO格式的相关代码，就自己参考其他人基于目标检测的进行了改写，话不多说，直接上代码。
目标检测和实例分割:COCO格式json直接转换成yolo格式txt
Guet142021的博客
01-17 1576
如果想使用yolo训练类似coco标注格式的数据集需要进行格式转换,将json格式转换为yolo的txt格式。
coco2017数据集COCO格式转YOLO格式
帅的发光发亮的博客
10-27 2612
【代码】coco2017数据集COCO格式转YOLO格式。
详细！正确！COCO数据集（.json）训练格式转换成YOLO格式（.txt）
热门推荐
qq_42012888的博客
09-13 1万+
自己从网上找了好久，都是各种错误，或者写的不清晰，忙活了两个小时，现在准备写到博客上，利人利己。 在coco数据集中，coco2017train或coco2017val数据集中标注的目标(类别)位置在 Annotations 文件中以 (x, y, width, height) 来进行表示，x，y表示bbox左上角位置，width, height表示bbox的宽和高。而在YOLO训练或者进行验证的时候读取的标注格式是以 (xmin, ymin, xmax, ymax) 来进行表示，xmin, ymin表示b
coco数据集转换成yolo数据集
05-14
将COCO数据集转换为YOLO数据集可以通过以下步骤完成： 1. 下载COCO数据集并解压缩。 2. 安装COCO API和OpenCV。 3. 创建一个新的文件夹，用于存储转换后的YOLO数据集。 4. 读取COCO中的图像和注释。 5. 将每个图像转换为YOLO格式（.txt文件）。 6. 将所有的YOLO格式文件和图像放入新的文件夹中。 以下是一个将COCO数据集转换为YOLO数据集的Python代码示例： ```python import os import json import cv2 # COCO类别对应的YOLO类别 class_id = { "person": 0, "bicycle": 1, "car": 2, "motorcycle": 3, "airplane": 4, "bus": 5, "train": 6, "truck": 7, "boat": 8, "traffic light": 9, "fire hydrant": 10, "stop sign": 11, "parking meter": 12, "bench": 13, "bird": 14, "cat": 15, "dog": 16, "horse": 17, "sheep": 18, "cow": 19, "elephant": 20, "bear": 21, "zebra": 22, "giraffe": 23, "backpack": 24, "umbrella": 25, "handbag": 26, "tie": 27, "suitcase": 28, "frisbee": 29, "skis": 30, "snowboard": 31, "sports ball": 32, "kite": 33, "baseball bat": 34, "baseball glove": 35, "skateboard": 36, "surfboard": 37, "tennis racket": 38, "bottle": 39, "wine glass": 40, "cup": 41, "fork": 42, "knife": 43, "spoon": 44, "bowl": 45, "banana": 46, "apple": 47, "sandwich": 48, "orange": 49, "broccoli": 50, "carrot": 51, "hot dog": 52, "pizza": 53, "donut": 54, "cake": 55, "chair": 56, "couch": 57, "potted plant": 58, "bed": 59, "dining table": 60, "toilet": 61, "tv": 62, "laptop": 63, "mouse": 64, "remote": 65, "keyboard": 66, "cell phone": 67, "microwave": 68, "oven": 69, "toaster": 70, "sink": 71, "refrigerator": 72, "book": 73, "clock": 74, "vase": 75, "scissors": 76, "teddy bear": 77, "hair drier": 78, "toothbrush": 79 } # 将COCO注释转换为YOLO格式 def convert_annotation(image_id, coco_annotation, file): for annotation in coco_annotation: x, y, w, h = annotation['bbox'] x_center = x + w / 2 y_center = y + h / 2 x_center /= width y_center /= height w /= width h /= height class_name = coco_classes[annotation["category_id"]] class_num = class_id[class_name] file.write("%s %s %s %s %s\n" % (class_num, x_center, y_center, w, h)) # COCO数据集文件夹路径 coco_folder = "/path/to/coco/folder" # 用于存储YOLO数据集的文件夹路径 yolo_folder = "/path/to/yolo/folder" # COCO数据集注释文件 coco_annotation_file = os.path.join(coco_folder, "annotations/instances_val2017.json") # COCO数据集图像文件夹 coco_image_folder = os.path.join(coco_folder, "val2017") # 创建一个新的文件夹，用于存储转换后的YOLO数据集 if not os.path.exists(yolo_folder): os.makedirs(yolo_folder) # 读取COCO注释文件 with open(coco_annotation_file) as f: coco_data = json.load(f) # COCO类别列表 coco_classes = [] for category in coco_data['categories']: coco_classes.append(category['name']) # 遍历COCO数据集中的每个图像 for image_data in coco_data['images']: # 获取图像文件名和路径 image_name = image_data['file_name'] image_path = os.path.join(coco_image_folder, image_name) # 读取图像 image = cv2.imread(image_path) height, width, channels = image.shape # 创建YOLO格式的注释文件 yolo_annotation_file = os.path.join(yolo_folder, os.path.splitext(image_name)[0] + ".txt") with open(yolo_annotation_file, "w") as f: # 获取图像中的每个注释 for annotation in coco_data['annotations']: # 如果注释属于当前图像，则将其转换为YOLO格式 if annotation['image_id'] == image_data['id']: convert_annotation(image_data['id'], [annotation], f) # 将图像复制到YOLO数据集文件夹中 yolo_image_path = os.path.join(yolo_folder, image_name) cv2.imwrite(yolo_image_path, image) ``` 在运行完上述代码后，YOLO数据集文件夹中应该包括所有转换后的图像和注释文件。
评论 1
添加红包

请填写红包祝福语或标题

个

红包个数最小为10个

元

红包金额最低5元

当前余额3.43元 前往充值 >
需支付：10.00元
成就一亿技术人!
领取后你会自动成为博主和红包主的粉丝 规则
hope_wisdom
发出的红包
实付元
使用余额支付
点击重新获取
扫码支付
钱包余额 0

抵扣说明：

1.余额是钱包充值的虚拟货币，按照1:1的比例进行支付金额的抵扣。
2.余额无法直接购买下载，可以购买VIP、付费专栏及课程。

余额充值