代码里面集合了python处理xml的精髓
1. voc定位数据xml转coco数据集格式json
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 = 0
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 parseXmlFiles(xml_path):
for f in os.listdir(xml_path):
if not f.endswith('.xml'):
continue
bndbox = dict()
size = dict()
current_image_id = None
current_category_id = None
file_name = None
size['width'] = None
size['height'] = None
size['depth'] = None
xml_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.tag
current_sub = None
object_name = None
if elem.tag == 'folder':
continue
if elem.tag == 'filename':
file_name = elem.text
if file_name in category_set:
raise Exception('file_name duplicated')
#add img item only after parse <size> tag
elif 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'] = None
bndbox ['xmax'] = None
bndbox ['ymin'] = None
bndbox ['ymax'] = None
current_sub = subelem.tag
if current_parent == 'object' and subelem.tag == 'name':
object_name = subelem.text
if 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> tag
if 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 = []
#x
bbox.append(bndbox['xmin'])
#y
bbox.append(bndbox['ymin'])
#w
bbox.append(bndbox['xmax'] - bndbox['xmin'])
#h
bbox.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数据示例：
<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"
}
]
}
2.抽取voc里面的坐标信息到txt
import xml.etree.ElementTree as ET
import os
import json
xml_dir = "/media/data_1/bigdata_tmp/20190820chejiahao/deal/1_xml/"
def xml2txt(txt_dir,xml_name):
xml_file = xml_dir + xml_name
tree = ET.parse(xml_file)
root = tree.getroot() #annotation
print (root.tag)
bndbox = dict()
bndbox['xmin'] = None
bndbox['xmax'] = None
bndbox['ymin'] = None
bndbox['ymax'] = None
for elem in root: #folder filename source owner size segmented object
if "object" == elem.tag:
for sub_elem in elem:
if 'bndbox' == sub_elem.tag:
for x_y_sub_elem in sub_elem:
bndbox[x_y_sub_elem.tag] = int(x_y_sub_elem.text)
tl_x = bndbox['xmin']
tl_y = bndbox['ymin']
tr_x = bndbox['xmax']
tr_y = bndbox['ymin']
bl_x = bndbox['xmin']
bl_y = bndbox['ymax']
br_x = bndbox['xmax']
br_y = bndbox['ymax']
with open(txt_dir + xml_name.replace('.xml','.txt'),'w') as f:
f.write(str(tl_x))
f.write(',')
f.write(str(tl_y))
f.write(',')
f.write(str(tr_x))
f.write(',')
f.write(str(tr_y))
f.write(',')
f.write(str(br_x))
f.write(',')
f.write(str(br_y))
f.write(',')
f.write(str(bl_x))
f.write(',')
f.write(str(bl_y))
f.write('
')
txt_dir = os.path.dirname(os.path.dirname(xml_dir)) + '/txt/'
if not os.path.exists(txt_dir):
os.makedirs(txt_dir)
list_xml = os.listdir(xml_dir)
for cnt,xml_name in enumerate(list_xml):
print("cnt=%d,xml=%s"%(cnt,xml_name))
xml2txt(txt_dir, xml_name)