voc转coco步骤
1、整理需要的voc文件,包括下述内容
其中annotations中存放的是xml注解,images存放的是图片
存放xml文件
存放图片文件
2、将voc转化为coco的代码,一步到位
import xml.etree.ElementTree as ET
import os
import json
# 初始化了一个名为 coco 的字典,用于构建一个COCO(Common Objects in Context)数据结构
coco = dict()
#用于存储图像信息的列表。
coco['images'] = []
# 被设置为 'instances',表明这是一个实例分割任务的数据集。
coco['type'] = 'instances'
# 用于存储标注信息的列表。
coco['annotations'] = []
# 用于存储类别信息的列表。
coco['categories'] = []
category_set = dict({'car':1})#是一个字典,包含一个类别'car',对应值为1
image_set = set()#集合,用于存储图像文件名
category_item_id = 0#整数变量,用于标识类别项ID
image_id = 20180000000#用于表示图像ID
annotation_id = 0#用于标识注释ID
# 用于向COCO数据集中添加类别项
def addCatItem(name):#name类别项名称
global category_item_id#全局变量,表示类别项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
# 用于向某个数据结构(可能是COCO数据集)中添加图像项的函数。这段代码的作用是根据传入的文件名和大小信息,创建一个包含图像信息的字典,并将其添加到COCO数据结构中。
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
# 这段代码定义了一个函数 addAnnoItem,用于向COCO数据结构中添加标注项。函数的参数包括目标对象的名称 (object_name)、图像的ID (image_id)、类别的ID (category_id) 以及边界框的坐标信息 (bbox)。
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)
# 这段代码定义了一个名为 _read_image_ids 的函数,用于从一个文件中读取图像的ID。具体来说,函数的作用是:
# 打开指定的图像集文件 image_sets_file。
# 逐行读取文件内容,将每行去除末尾的换行符后的结果添加到列表 ids 中。
# 返回包含所有图像ID的列表 ids。
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
def parseXmlFiles(xml_path, json_save_path):#xml_path=ann_path=annotations
for f in os.listdir(xml_path):#筛选出annotations以.xml结尾的文件
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)#打印出需要处理的文件名
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
file_name = f[:-3] + '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:
# elif current_image_id is None and file_name is None and size['width'] is 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)
bndbox[option.tag] = float(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,object_name is none')
if current_image_id is None:
raise Exception('xml structure broken at bndbox tag,current_image_id is None')
if current_category_id is None:
raise Exception('xml structure broken at bndbox tag,current_category_id is None')
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__':
dataset_dir = "./detr/train_daysunny/images"#存放voc数据集图片的路径
ann_path = "./detr/train_daysunny/annotations"#存放voc数据集xml文件的路径
json_save_path = "./COCO/annotations/coco.json"#转化之后coco.json文件的路径。PS:coco.json文件需要自己手动提前创建成功。
parseXmlFiles(ann_path, json_save_path)
print("生成完成。")
3、根据xml文件里的格式不同,适当调整上述代码
1、第一种情况
如果xml文件里的格式是这种的话,那就可以直接使用上述代码,不需要调整。
因为如图所示:
代码本身要找的xml文件中的元素就是folder,filename,size,object与上述xml文件中的格式是对应的,所以可以直接转化。(PS:如果碰到其他小问题自己解决)
2、第二种情况
xml文件中的格式与第一种情况稍微有些不同,比如说没有folder,filename改为name等等。这个时候就需要调整我们的代码。
调整之后的代码如下:
import xml.etree.ElementTree as ET
import os
import json
# 初始化了一个名为 coco 的字典,用于构建一个COCO(Common Objects in Context)数据结构
coco = dict()
#用于存储图像信息的列表。
coco['images'] = []
# 被设置为 'instances',表明这是一个实例分割任务的数据集。
coco['type'] = 'instances'
# 用于存储标注信息的列表。
coco['annotations'] = []
# 用于存储类别信息的列表。
coco['categories'] = []
category_set = dict({'car':1})#是一个字典,包含一个类别'car',对应值为1
image_set = set()#集合,用于存储图像文件名
category_item_id = 0#整数变量,用于标识类别项ID
image_id = 20180000000#用于表示图像ID
annotation_id = 0#用于标识注释ID
# 用于向COCO数据集中添加类别项
def addCatItem(name):#name类别项名称
global category_item_id#全局变量,表示类别项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
# 用于向某个数据结构(可能是COCO数据集)中添加图像项的函数。这段代码的作用是根据传入的文件名和大小信息,创建一个包含图像信息的字典,并将其添加到COCO数据结构中。
def addImgItem(file_name):
global image_id
if file_name is None:
raise Exception('Could not find filename tag in xml file.')
image_id += 1
image_item = dict()
image_item['id'] = image_id
image_item['file_name'] = file_name
coco['images'].append(image_item)
image_set.add(file_name)
return image_id
# 这段代码定义了一个函数 addAnnoItem,用于向COCO数据结构中添加标注项。函数的参数包括目标对象的名称 (object_name)、图像的ID (image_id)、类别的ID (category_id) 以及边界框的坐标信息 (bbox)。
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)
# 这段代码定义了一个名为 _read_image_ids 的函数,用于从一个文件中读取图像的ID。具体来说,函数的作用是:
# 打开指定的图像集文件 image_sets_file。
# 逐行读取文件内容,将每行去除末尾的换行符后的结果添加到列表 ids 中。
# 返回包含所有图像ID的列表 ids。
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
def parseXmlFiles(xml_path, json_save_path):#xml_path=ann_path=annotations
for f in os.listdir(xml_path):#筛选出annotations以.xml结尾的文件
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)#打印出需要处理的文件名
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))
print(xml_file)
# 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 == 'name':
# file_name = elem.text
file_name = f[:-3] + 'jpg'
print("111")
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:
# elif current_image_id is None and file_name is None and size['width'] is None:
if file_name not in image_set:
current_image_id = addImgItem(file_name)
print('add image with {} '.format(file_name))
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)
bndbox[option.tag] = float(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,object_name is none')
if current_image_id is None:
raise Exception('xml structure broken at bndbox tag,current_image_id is None')
if current_category_id is None:
raise Exception('xml structure broken at bndbox tag,current_category_id is None')
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__':
dataset_dir = "./detr/train_daysunny/images"#存放voc数据集图片的路径
ann_path = "./detr/train_daysunny/annotations"#存放voc数据集xml文件的路径
json_save_path = "./COCO/annotations/coco.json"#转化之后coco.json文件的路径。PS:coco.json文件需要自己手动提前创建成功。
parseXmlFiles(ann_path, json_save_path)
print("生成完成。")
3、其他情况
剩下的情况,具体问题具体分析了。
4、批量修改文件名的代码
# 批量修改文件名,默认操作为将图片按1,2,3,,,顺序重命名
import os
path_in = "./detr/train_daysunny/images" # 待批量重命名的文件夹
class_name = ".jpg" # 重命名后的文件名后缀
file_in = os.listdir(path_in) # 返回文件夹包含的所有文件名
num_file_in = len(file_in) # 获取文件数目
print(file_in, num_file_in) # 输出修改前的文件名
for i in range(0, num_file_in):
t = str(i + 1)
new_name = os.rename(path_in + "/" + file_in[i], path_in + "/" + t + class_name) # 重命名文件名
file_out = os.listdir(path_in)
print(file_out) # 输出修改后的结果