代碼里面集合了python處理xml的精髓

import xml.etree.ElementTree as ET import os import jsoncoco = dict() coco['images'] = [] coco['type'] = 'instances' coco['annotations'] = [] coco['categories'] = []category_set = dict() image_set = set()category_item_id = 0 image_id = 20180000000 annotation_id = 0def addCatItem(name):global category_item_idcategory_item = dict()category_item['supercategory'] = 'none'category_item_id += 1category_item['id'] = category_item_idcategory_item['name'] = namecoco['categories'].append(category_item)category_set[name] = category_item_idreturn category_item_iddef addImgItem(file_name, size):global image_idif 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 += 1image_item = dict()image_item['id'] = image_idimage_item['file_name'] = file_nameimage_item['width'] = size['width']image_item['height'] = size['height']coco['images'].append(image_item)image_set.add(file_name)return image_iddef addAnnoItem(object_name, image_id, category_id, bbox):global annotation_idannotation_item = dict()annotation_item['segmentation'] = []seg = []#bbox[] is x,y,w,h#left_topseg.append(bbox[0])seg.append(bbox[1])#left_bottomseg.append(bbox[0])seg.append(bbox[1] + bbox[3])#right_bottomseg.append(bbox[0] + bbox[2])seg.append(bbox[1] + bbox[3])#right_topseg.append(bbox[0] + bbox[2])seg.append(bbox[1])annotation_item['segmentation'].append(seg)annotation_item['area'] = bbox[2] * bbox[3]annotation_item['iscrowd'] = 0annotation_item['ignore'] = 0annotation_item['image_id'] = image_idannotation_item['bbox'] = bboxannotation_item['category_id'] = category_idannotation_id += 1annotation_item['id'] = annotation_idcoco['annotations'].append(annotation_item)def parseXmlFiles(xml_path): for f in os.listdir(xml_path):if not f.endswith('.xml'):continuebndbox = dict()size = dict()current_image_id = Nonecurrent_category_id = Nonefile_name = Nonesize['width'] = Nonesize['height'] = Nonesize['depth'] = Nonexml_file = os.path.join(xml_path, f)print(xml_file)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 <folder>, <filename>, <size>, <object>for elem in root:current_parent = elem.tagcurrent_sub = Noneobject_name = Noneif elem.tag == 'folder':continueif elem.tag == 'filename':file_name = elem.textif file_name in category_set:raise Exception('file_name duplicated')#add img item only after parse <size> tagelif current_image_id is None and file_name is not None and size['width'] is not None:if file_name not in image_set:current_image_id = addImgItem(file_name, size)print('add image with {} and {}'.format(file_name, size))else:raise Exception('duplicated image: {}'.format(file_name)) #subelem is <width>, <height>, <depth>, <name>, <bndbox>for subelem in elem:bndbox ['xmin'] = Nonebndbox ['xmax'] = Nonebndbox ['ymin'] = Nonebndbox ['ymax'] = Nonecurrent_sub = subelem.tagif current_parent == 'object' and subelem.tag == 'name':object_name = subelem.textif object_name not in category_set:current_category_id = addCatItem(object_name)else:current_category_id = category_set[object_name]elif current_parent == 'size':if size[subelem.tag] is not None:raise Exception('xml structure broken at size tag.')size[subelem.tag] = int(subelem.text)#option is <xmin>, <ymin>, <xmax>, <ymax>, when subelem is <bndbox>for option in subelem:if current_sub == 'bndbox':if bndbox[option.tag] is not None:raise Exception('xml structure corrupted at bndbox tag.')bndbox[option.tag] = int(option.text)#only after parse the <object> tagif bndbox['xmin'] is not None:if object_name is None:raise Exception('xml structure broken at bndbox tag')if current_image_id is None:raise Exception('xml structure broken at bndbox tag')if current_category_id is None:raise Exception('xml structure broken at bndbox tag')bbox = []#xbbox.append(bndbox['xmin'])#ybbox.append(bndbox['ymin'])#wbbox.append(bndbox['xmax'] - bndbox['xmin'])#hbbox.append(bndbox['ymax'] - bndbox['ymin'])print('add annotation with {},{},{},{}'.format(object_name, current_image_id, current_category_id, bbox))addAnnoItem(object_name, current_image_id, current_category_id, bbox )if __name__ == '__main__':xml_path = '/media/data_2/everyday/0709/maskrcnn/data/ret/xml_test'json_file = './instances_test.json'parseXmlFiles(xml_path)json.dump(coco, open(json_file, 'w'))

我自己xml數(shù)據(jù)示例：

<annotation><folder>VOC2007</folder><filename>mingpai_104.jpg</filename><source><database>The VOC2007 Database</database><annotation>PASCAL VOC2007</annotation><image>flickr</image><flickrid>329145082</flickrid></source><owner>><flickrid>hiromori2</flickrid><name>Hiroyuki Mori</name></owner>><size><width>997</width><height>1000</height><depth>3</depth></size><segmented>0</segmented><object><name>ZhiZaoNianYue</name><pose>Unspecified</pose><truncated>0</truncated><difficult>0</difficult><bndbox><xmin>444</xmin><ymin>679</ymin><xmax>575</xmax><ymax>720</ymax></bndbox></object><object><name>FDJ_PaiL</name><pose>Unspecified</pose><truncated>0</truncated><difficult>0</difficult><bndbox><xmin>747</xmin><ymin>545</ymin><xmax>806</xmax><ymax>586</ymax></bndbox></object><object><name>FDJ_Hao</name><pose>Unspecified</pose><truncated>0</truncated><difficult>0</difficult><bndbox><xmin>448</xmin><ymin>536</ymin><xmax>562</xmax><ymax>576</ymax></bndbox></object><object><name>CJHao</name><pose>Unspecified</pose><truncated>0</truncated><difficult>0</difficult><bndbox><xmin>445</xmin><ymin>364</ymin><xmax>724</xmax><ymax>432</ymax></bndbox></object> </annotation>

生成的coco json格式示例：

{"images": [{"file_name": "mingpai_1083.jpg","height": 747,"id": 20180000001,"width": 843},{"file_name": "mingpai_1079.jpg","height": 544,"id": 20180000002,"width": 826}],"type": "instances","annotations": [{"segmentation": [[526,315,526,356,701,356,701,315]],"area": 7175,"iscrowd": 0,"ignore": 0,"image_id": 20180000001,"bbox": [526,315,175,41],"category_id": 1,"id": 1},{"segmentation": [[580,286,580,320,702,320,702,286]],"area": 4148,"iscrowd": 0,"ignore": 0,"image_id": 20180000001,"bbox": [580,286,122,34],"category_id": 2,"id": 2},{"segmentation": [[299,292,299,331,384,331,384,292]],"area": 3315,"iscrowd": 0,"ignore": 0,"image_id": 20180000001,"bbox": [299,292,85,39],"category_id": 3,"id": 3},{"segmentation": [[292,256,292,292,683,292,683,256]],"area": 14076,"iscrowd": 0,"ignore": 0,"image_id": 20180000001,"bbox": [292,256,391,36],"category_id": 4,"id": 4},{"segmentation": [[171,335,171,377,318,377,318,335]],"area": 6174,"iscrowd": 0,"ignore": 0,"image_id": 20180000002,"bbox": [171,335,147,42],"category_id": 1,"id": 5},{"segmentation": [[622,400,622,444,733,444,733,400]],"area": 4884,"iscrowd": 0,"ignore": 0,"image_id": 20180000002,"bbox": [622,400,111,44],"category_id": 2,"id": 6},{"segmentation": [[188,385,188,418,273,418,273,385]],"area": 2805,"iscrowd": 0,"ignore": 0,"image_id": 20180000002,"bbox": [188,385,85,33],"category_id": 3,"id": 7},{"segmentation": [[196,258,196,327,725,327,725,258]],"area": 36501,"iscrowd": 0,"ignore": 0,"image_id": 20180000002,"bbox": [196,258,529,69],"category_id": 4,"id": 8}],"categories": [{"supercategory": "none","id": 1,"name": "ZhiZaoNianYue"},{"supercategory": "none","id": 2,"name": "FDJ_PaiL"},{"supercategory": "none","id": 3,"name": "FDJ_Hao"},{"supercategory": "none","id": 4,"name": "CJHao"}] }

轉(zhuǎn)載于:https://www.cnblogs.com/yanghailin/p/11189871.html

與50位技術專家面對面20年技術見證，附贈技術全景圖

總結(jié)

以上是生活随笔為你收集整理的voc定位数据xml转coco数据集格式json的全部內(nèi)容，希望文章能夠幫你解決所遇到的問題。

如果覺得生活随笔網(wǎng)站內(nèi)容還不錯，歡迎將生活随笔推薦給好友。