VOC2COCO
方法一
参考自博客
数据格式的转换实际是将VOC的annotation标注文件转化为COCO的json文件
注：下面代码包含通过txt文件生成和通过文件夹生成两种方法
1 通过txt文件生成 ：按照VOC数据集下ImageSets/Main中的已划分好的trian.txt，test.txt，val.txt进行转化，生成对应的3个json文件;
2 通过文件夹生成 ：将annotation文件夹里的xml文件全部转化成一个json文件，一个annotation文件夹转化成一个json文件，要想生成3个trian.json，test.json，val.json文件，需要有3个对应的annotation文件夹（可手动按比例创建3个annotation文件夹，也可写个程序划分annotation文件夹）
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（包含背景的情况）下一句代码需改成category_item_id = 0
category_item_id = -1
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='train'):
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'
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'))
"""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="E:/VOCdevkit/VOC2007"#整个数据集文件夹所在路径
# json_save_path="E:/VOCdevkit/voc2007trainval.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,"trainval")
#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)
方法二
与方法一的区别：可根据需求调节划分训练，测试，验证数据集的比例，通过一个包含全部xml的annotion文件夹，直接生成3个json文件
# coding:utf-8
# 运行前请先做以下工作：
# pip install lxml
# 将所有的图片及xml文件存放到xml_dir指定的文件夹下，并将此文件夹放置到当前目录下
#
import os
import glob
import json
import shutil
import numpy as np
import xml.etree.ElementTree as ET
START_BOUNDING_BOX_ID = 1
save_path = "."
def get(root, name):
return root.findall(name)
def get_and_check(root, name, length):
vars = get(root, name)
if len(vars) == 0:
raise NotImplementedError('Can not find %s in %s.' % (name, root.tag))
if length and len(vars) != length:
raise NotImplementedError('The size of %s is supposed to be %d, but is %d.' % (name, length, len(vars)))
if length == 1:
vars = vars[0]
return vars
def convert(xml_list, json_file):
json_dict = {"images": [], "type": "instances", "annotations": [], "categories": []}
categories = pre_define_categories.copy()
bnd_id = START_BOUNDING_BOX_ID
all_categories = {}
for index, line in enumerate(xml_list):
# print("Processing %s"%(line))
xml_f = line
tree = ET.parse(xml_f)
root = tree.getroot()
filename = os.path.basename(xml_f)[:-4] + ".jpg"
image_id = 20190000001 + index
size = get_and_check(root, 'size', 1)
width = int(get_and_check(size, 'width', 1).text)
height = int(get_and_check(size, 'height', 1).text)
image = {'file_name': filename, 'height': height, 'width': width, 'id': image_id}
json_dict['images'].append(image)
# Currently we do not support segmentation
segmented = get_and_check(root, 'segmented', 1).text
assert segmented == '0'
for obj in get(root, 'object'):
category = get_and_check(obj, 'name', 1).text
if category in all_categories:
all_categories[category] += 1
else:
all_categories[category] = 1
if category not in categories:
if only_care_pre_define_categories:
continue
new_id = len(categories) + 1
print(
"[warning] category '{}' not in 'pre_define_categories'({}), create new id: {} automatically".format(
category, pre_define_categories, new_id))
categories[category] = new_id
category_id = categories[category]
bndbox = get_and_check(obj, 'bndbox', 1)
xmin = int(float(get_and_check(bndbox, 'xmin', 1).text))
ymin = int(float(get_and_check(bndbox, 'ymin', 1).text))
xmax = int(float(get_and_check(bndbox, 'xmax', 1).text))
ymax = int(float(get_and_check(bndbox, 'ymax', 1).text))
assert (xmax > xmin), "xmax <= xmin, {}".format(line)
assert (ymax > ymin), "ymax <= ymin, {}".format(line)
o_width = abs(xmax - xmin)
o_height = abs(ymax - ymin)
ann = {'area': o_width * o_height, 'iscrowd': 0, 'image_id':
image_id, 'bbox': [xmin, ymin, o_width, o_height],
'category_id': category_id, 'id': bnd_id, 'ignore': 0,
'segmentation': []}
json_dict['annotations'].append(ann)
bnd_id = bnd_id + 1
for cate, cid in categories.items():
cat = {'supercategory': 'food', 'id': cid, 'name': cate}
json_dict['categories'].append(cat)
json_fp = open(json_file, 'w')
json_str = json.dumps(json_dict)
json_fp.write(json_str)
json_fp.close()
print("------------create {} done--------------".format(json_file))
print("find {} categories: {} -->>> your pre_define_categories {}: {}".format(len(all_categories),
all_categories.keys(),
len(pre_define_categories),
pre_define_categories.keys()))
print("category: id --> {}".format(categories))
print(categories.keys())
print(categories.values())
if __name__ == '__main__':
# 定义你自己的类别
classes = ['aaa', 'bbb', 'ccc', 'ddd', 'eee', 'fff']
pre_define_categories = {}
for i, cls in enumerate(classes):
pre_define_categories[cls] = i + 1
# 这里也可以自定义类别id，把上面的注释掉换成下面这行即可
# pre_define_categories = {'a1': 1, 'a3': 2, 'a6': 3, 'a9': 4, "a10": 5}
only_care_pre_define_categories = True # or False
# 保存的json文件
save_json_train = 'train_food.json'
save_json_val = 'val_food.json'
save_json_test = 'test_food.json'
# 初始文件所在的路径
xml_dir = "./image_and_xml"
xml_list = glob.glob(xml_dir + "/*.xml")
xml_list = np.sort(xml_list)
# 打乱数据集
np.random.seed(100)
np.random.shuffle(xml_list)
# 按比例划分打乱后的数据集
train_ratio = 0.8
val_ratio = 0.1
train_num = int(len(xml_list) * train_ratio)
val_num = int(len(xml_list) * val_ratio)
xml_list_train = xml_list[:train_num]
xml_list_val = xml_list[train_num: train_num+val_num]
xml_list_test = xml_list[train_num+val_num:]
# 将xml文件转为coco文件，在指定目录下生成三个json文件（train/test/food）
convert(xml_list_train, save_json_train)
convert(xml_list_val, save_json_val)
convert(xml_list_test, save_json_test)
# # 将图片按照划分后的结果进行存放
# if os.path.exists(save_path + "/annotations"):
# shutil.rmtree(save_path + "/annotations")
# os.makedirs(save_path + "/annotations")
# if os.path.exists(save_path + "/images_divide/train"):
# shutil.rmtree(save_path + "/images_divide/train")
# os.makedirs(save_path + "/images_divide/train")
# if os.path.exists(save_path + "/images_divide/val"):
# shutil.rmtree(save_path + "/images_divide/val")
# os.makedirs(save_path + "/images_divide/val")
# if os.path.exists(save_path + "/images_divide/test"):
# shutil.rmtree(save_path + "/images_divide/test")
# os.makedirs(save_path + "/images_divide/test")
# # 按需执行，生成3个txt文件，存放相应的文件名称
# f1 = open("./train.txt", "w")
# for xml in xml_list_train:
# img = xml[:-4] + ".jpg"
# f1.write(os.path.basename(xml)[:-4] + "\n")
# shutil.copyfile(img, save_path + "/images_divide/train/" + os.path.basename(img))
#
# f2 = open("val.txt", "w")
# for xml in xml_list_val:
# img = xml[:-4] + ".jpg"
# f2.write(os.path.basename(xml)[:-4] + "\n")
# shutil.copyfile(img, save_path + "/images_divide/val/" + os.path.basename(img))
#
# f3 = open("test.txt", "w")
# for xml in xml_list_val:
# img = xml[:-4] + ".jpg"
# f2.write(os.path.basename(xml)[:-4] + "\n")
# shutil.copyfile(img, save_path + "/images_divide/test/" + os.path.basename(img))
#
# f1.close()
# f2.close()
# f3.close()
print("-" * 50)
print("train number:", len(xml_list_train))
print("val number:", len(xml_list_val))
print("test number:", len(xml_list_val))
COCO2VOC
参考http://blog.csdn.net/ouyangfushu/article/details/79543575
包括对COCO，VOC数据集的简介
