VOC数据集格式转化成COCO数据集格式

                  VOC数据集格式转化成COCO数据集格式

一、唠叨

     之前写过一篇关于coco数据集转化成VOC格式的博客COCO2VOC，最近读到CenterNet的官方代码，实现上则是将voc转化成coco数据格式，这样的操作我个人感觉很不习惯，也觉得有些奇葩，可能是每个人习惯不一样吧，我们知道有时候我们会采用labelImg标注数据，标注出来的格式就是voc，如果直接训练就可以用来训练是不是更加友好。

     为了不大规模修改原始训练代码（虽然自己修改了一个版本的voc数据集就能直接训练centernet ）,同时也看到网上很多大佬也做了将VOC数据格式转化成COCO用于其训练，这里我自己做一个精细一点的，作为笔记。

二、转化过程

   数据格式的转换实际是annotation标注文件的转化，voc的数据标注文件为以.xml结尾的文件，而且每张图片均有一个对应的同名标注文件；COCO则是将所有的标注信息写在一个json文件中。VOC数据集目录如下：

    在之前的coco2voc博客中做了详细的介绍，现在直接开始转化，目标就是将Annotations中的所有标注文件中的bbox标注信息转化为json文件，根据训练集和测试集，则主要转化为四个json文件，分别是test.json、train.json、val.json和trainval.json .这里我根据ImageSets中的train.txt val.txt trainval.txt生成后三个json文件，当然也可以直接从Annotations文件夹生成。

VOC2COCO.py

import xml.etree.ElementTree as ET
import os
import json

coco = dict()
coco['images'] = []
coco['type'] = 'instances'
coco['annotations'] = []
coco['categories'] = []

category_set = dict()
image_set = set()

category_item_id = -1
image_id = 20180000000
annotation_id = 0

def 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_id

def 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_id

def 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 _read_image_ids(image_sets_file):
    ids = []
    with open(image_sets_file) as f:
        for line in f:
            ids.append(line.rstrip())
    return ids

"""通过txt文件生成"""
#split ='train' 'va' 'trainval' 'test'
def parseXmlFiles_by_txt(data_dir,json_save_path,split='train'):
    print("hello")
    labelfile=split+".txt"
    image_sets_file = data_dir + "/ImageSets/Main/"+labelfile
    ids=_read_image_ids(image_sets_file)

    for _id in ids:
        xml_file=data_dir + f"/Annotations/{_id}.xml"

        bndbox = dict()
        size = dict()
        current_image_id = None
        current_category_id = None
        file_name = None
        size['width'] = None
        size['height'] = None
        size['depth'] = None

        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 , , ,