原文鏈接:https://blog.csdn.net/weixin_42419002/article/details/100161294
1. 轉換前的 .json 格式文件的內容:
json 是一個字典,具體內容看下面這個鏈接:
https://blog.csdn.net/weixin_42419002/article/details/100159408
2. 轉換後的 .xml 格式文件的內容:
<annotation>
<folder>VOC2012</folder> # 這些值訓練的時候不會被用到
<filename>2007_000661.jpg</filename>
<source>
<database>The VOC2007 Database</database>
<annotation>PASCAL VOC2007</annotation>
<image>flickr</image>
</source>
<size>
<width>500</width> # 這個值需要改變
<height>375</height> # 這個值需要改變
<depth>3</depth>
</size>
<segmented>0</segmented>
<object>
<name>sofa</name> # 這個值需要改變
<pose>Unspecified</pose>
<truncated>1</truncated>
<difficult>0</difficult>
<bndbox>
<xmin>119</xmin> # 這個值需要改變
<ymin>177</ymin> # 這個值需要改變
<xmax>331</xmax> # 這個值需要改變
<ymax>278</ymax> # 這個值需要改變
</bndbox>
</object>
<object>
<name>chair</name> # 這個值需要改變
<pose>Unspecified</pose>
<truncated>1</truncated>
<difficult>0</difficult>
<bndbox>
<xmin>133</xmin> # 這個值需要改變
<ymin>159</ymin> # 這個值需要改變
<xmax>179</xmax> # 這個值需要改變
<ymax>197</ymax> # 這個值需要改變
</bndbox>
</object>
</annotation>
3. 將 .json 轉換成 .xml 格式代碼:
import os
import json
from lxml import etree as ET
from xml.dom import minidom
def edit_xml(objects, id, dir):
save_xml_path = os.path.join(dir, "%s.xml" % id) # xml
root = ET.Element("annotation")
# root.set("version", "1.0")
folder = ET.SubElement(root, "folder")
folder.text = "none"
filename = ET.SubElement(root, "filename")
filename.text = "none"
source = ET.SubElement(root, "source")
source.text = "201908"
owner = ET.SubElement(root, "owner")
owner.text = "YZN"
size = ET.SubElement(root, "size")
width = ET.SubElement(size, "width")
width.text = str(2048)
height = ET.SubElement(size, "height")
height.text = str(2048)
depth = ET.SubElement(size, "depth")
depth.text = "3"
segmented = ET.SubElement(root, "segmented")
segmented.text = "0"
for obj in objects: #
object = ET.SubElement(root, "object")
name = ET.SubElement(object, "name") # number
name.text = obj["category"]
# meaning = ET.SubElement(object, "meaning") # name
# meaning.text = inf_value[0]
pose = ET.SubElement(object, "pose")
pose.text = "Unspecified"
truncated = ET.SubElement(object, "truncated")
truncated.text = "0"
difficult = ET.SubElement(object, "difficult")
difficult.text = "0"
bndbox = ET.SubElement(object, "bndbox")
xmin = ET.SubElement(bndbox, "xmin")
xmin.text = str(int(obj["bbox"]["xmin"]))
ymin = ET.SubElement(bndbox, "ymin")
ymin.text = str(int(obj["bbox"]["ymin"]))
xmax = ET.SubElement(bndbox, "xmax")
xmax.text = str(int(obj["bbox"]["xmax"]))
ymax = ET.SubElement(bndbox, "ymax")
ymax.text = str(int(obj["bbox"]["ymax"]))
tree = ET.ElementTree(root)
tree.write(save_xml_path, encoding="UTF-8", xml_declaration=True)
root = ET.parse(save_xml_path)
file_lines = minidom.parseString(ET.tostring(root, encoding="Utf-8")).toprettyxml(
indent="\t")
file_line = open(save_xml_path, "w", encoding="utf-8")
file_line.write(file_lines)
file_line.close()
def getDirId(dir): # get the id list of id.png
names = os.listdir(dir)
ids = []
for name in names:
# path = os.path.join(dir, name)
# img = cv2.imread(path)
# w, h, c = img.shape
# if name.endswith(".jpg") or name.endswith(".png"):
# ids["%s" % name.split(".")[0]] = [w, h, c]
ids.append(name.split(".")[0])
return ids
filedir = "annotations.json"
annos = json.loads(open(filedir).read())
trainIds = getDirId("Tinghua100K/images/train/")
testIds = getDirId("Tinghua100K/images/test/")
ids = annos["imgs"].keys() # all img ids in .json
for id in ids:
# json 中的ID圖片有待檢測目標,且該id圖片在 train文件夾中
if len(annos["imgs"][id]["objects"]) > 0 and (id in trainIds) and :
objects = annos["imgs"][id]["objects"]
edit_xml(objects, id, dir = "xmlLabel/train")
elif len(annos["imgs"][id]["objects"]) > 0 and (id in testIds):
objects = annos["imgs"][id]["objects"]
edit_xml(objects, id, dir = "xmlLabel/test")