数据集格式转换笔记
voc2coco
-
voc格式
VOC/ ├── Annotations/ # 标注文件（XML格式） ├── JPEGImages/ # 图像文件 ├── ImageSets/ # 图像集（划分为训练、验证和测试集） │ ├── Main/ │ │ ├── train.txt │ │ ├── val.txt │ │ ├── test.txt -
coco格式
COCO/ ├── annotations/ # 标注文件（JSON格式） │ ├── instances_train2017.json │ ├── instances_val2017.json │ ├── instances_test2017.json ├── train2017/ # 训练集图片（JPEG格式） ├── val2017/ # 验证集图片（JPEG格式） ├── test2017/ -
voc2coco转换脚本 参考链接 单个json文件转换无bug，按txt生成json时，
instances_train2017.json,instances_val2017.json,instances_test2017.json中category id不对应，会导致训练时无法正确评估.
# 按照ImageSets/Main生成coco的json文件
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()
# 注意具体应用中，类别索引是从0开始，还是从1开始。
# 若从1开始（数据无背景类别）下一句代码需改成category_item_id = 0,否则-1
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 _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='trainval'):
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 <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':
# 若xml文件名和文件里'filename'标签的内容不一致，而xml文件名是正确的，
# 即，（标注错误），则用xml文件名赋给file_name，即，下面一句代码换成file_name = _id + '.jpg' 否则file_name = elem.text
file_name = _id + '.jpg'
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)
json.dump(coco, open(json_save_path, 'w'))
"""直接从xml文件夹中生成"""
def parseXmlFiles(xml_path, json_save_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)
json.dump(coco, open(json_save_path, 'w'))
if __name__ == '__main__':
# 通过txt文件生成
voc_data_dir = r"/home/zhewang/Project/yolov7_biliii_server/voc_0608_weed_v4_L/VOC2007" # 整个数据集文件夹所在路径
json_save_path = r"/home/zhewang/Project/Dataset/coco_0608_weed_v4_L/utils_voc2coco/annotations/instances_test2017.json" # 生成后的文件存放路径和生成文件的名字
parseXmlFiles_by_txt(voc_data_dir, json_save_path, "test")
# # 通过文件夹生成
# ann_path = "E:/VOCdevkit/VOC2007/Annotations"
# json_save_path = "E:/VOCdevkit/test.json"
# parseXmlFiles(ann_path, json_save_path)
1:指定类别categoryid进行voc2coco格式转换。脚本如下
# 按照ImageSets/Main生成coco的json文件
# 在脚本中提前定义所有类别和其固定的编号
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()
# 注意具体应用中，类别索引是从0开始，还是从1开始。
# 若从1开始（数据无背景类别）下一句代码需改成category_item_id = 0,否则-1
category_item_id = 0
image_id = 20180000000
annotation_id = 0
category_set2 = {'Purslane': 1, 'Crabgrass': 2, 'FatHen': 3, 'other_weeds': 4} # 固定类别与ID映射
def addCatItem(name):
if name in category_set2:
global category_item_id
category_item = dict()
category_item['supercategory'] = 'none'
category_item_id = category_set2[name]
category_item['id'] = category_set2[name]
category_item['name'] = name
coco['categories'].append(category_item)
category_set[name] = category_item_id
return category_item_id
else:
raise ValueError(f"Unknown category {name}, please add it to the category_set.")
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='trainval'):
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 <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':
# 若xml文件名和文件里'filename'标签的内容不一致，而xml文件名是正确的，
# 即，（标注错误），则用xml文件名赋给file_name，即，下面一句代码换成file_name = _id + '.jpg' 否则file_name = elem.text
file_name = _id + '.jpg'
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)
json.dump(coco, open(json_save_path, 'w'))
"""直接从xml文件夹中生成"""
def parseXmlFiles(xml_path, json_save_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)
json.dump(coco, open(json_save_path, 'w'))
if __name__ == '__main__':
# 通过txt文件生成
voc_data_dir = r"/home/zhewang/Project/Dataset/coco_0608_weed_v4_L/utils_voc2coco/tempvoc" # 整个数据集文件夹所在路径
json_save_path = r"/home/zhewang/Project/Dataset/coco_0608_weed_v4_L/utils_voc2coco/annotations/instances_test2017.json" # 生成后的文件存放路径和生成文件的名字
parseXmlFiles_by_txt(voc_data_dir, json_save_path, "test")
# # 通过文件夹生成
# ann_path = "E:/VOCdevkit/VOC2007/Annotations"
# json_save_path = "E:/VOCdevkit/test.json"
# parseXmlFiles(ann_path, json_save_path)
####1.1: 注意生成json文件时最后的categoryid需要按序号排列：少量可手动排列。
- 如下：
"categories": [{"supercategory": "none", "id": 3, "name": "FatHen"}, {"supercategory": "none", "id": 2, "name": "Crabgrass"}, {"supercategory": "none", "id": 1, "name": "Purslane"}, {"supercategory": "none", "id": 4, "name": "other_weeds"}]}
-->
"categories": [{"supercategory": "none", "id": 1, "name": "Purslane"}, {"supercategory": "none", "id": 2, "name": "Crabgrass"}, {"supercategory": "none", "id": 3, "name": "FatHen"}, {"supercategory": "none", "id": 4, "name": "other_weeds"}]}
2: 根据json文件拷贝图像至指定目录
# 以下是一个脚本，它会根据提供的 JSON 文件，从指定目录中拷贝具有相同文件名的图像到另一个目录。
import os
import json
import shutil
def copy_images_from_json(json_file, source_dir, target_dir):
"""
根据 JSON 文件中的图像文件名，从源目录拷贝图像到目标目录。
:param json_file: JSON 文件路径。
:param source_dir: 源目录路径。
:param target_dir: 目标目录路径。
"""
# 确保目标目录存在
if not os.path.exists(target_dir):
os.makedirs(target_dir)
# 读取 JSON 文件
with open(json_file, 'r') as f:
data = json.load(f)
# 获取文件名列表
file_names = [image['file_name'] for image in data['images']]
print(f"Found {len(file_names)} files in JSON.")
# 遍历文件名列表并复制
copied_count = 0
for file_name in file_names:
source_path = os.path.join(source_dir, file_name)
target_path = os.path.join(target_dir, file_name)
if os.path.exists(source_path):
shutil.copy2(source_path, target_path)
copied_count += 1
else:
print(f"File not found: {source_path}")
print(f"Copied {copied_count}/{len(file_names)} files to {target_dir}.")
# 使用示例
if __name__ == "__main__":
json_path = r"/home/zhewang/Project/Dataset/coco_0608_weed_v4_L/annotations/instances_train2017.json" # JSON 文件路径
source_folder = r"/home/zhewang/Project/Dataset/coco_0608_weed_v4_L/JPEGImages" # 源目录路径
target_folder = r"/home/zhewang/Project/Dataset/coco_0608_weed_v4_L/train2017" # 目标目录路径
copy_images_from_json(json_path, source_folder, target_folder)