import os
import random
import shutil
import sys
import json
import glob
from time import sleep
import xml.etree.ElementTree as ET
# os.chdir(sys.path[0])
from tqdm import tqdm # 进度条
import logging
logger = logging.getLogger(__name__)
# critical > error > waring > info > debug
logger.setLevel(logging.DEBUG)
# 创建一个handler,用于输出到控制台
console_handler = logging.StreamHandler()
console_handler.setLevel(logging.DEBUG) # 输出到控制台的log等级的开关
# 创建该handler的formatter
console_handler.setFormatter(
logging.Formatter(
fmt='%(asctime)s - %(levelname)s: %(message)s',
datefmt='%Y-%m-%d %H:%M:%S')
)
logger.addHandler(console_handler)
"""
You only need to set the following three parts
1.val_files_num : num of validation samples from your all samples
2.test_files_num = num of test samples from your all samples
3.voc_annotations : path to your VOC dataset Annotations
"""
val_files_num = 20
test_files_num = 30
voc_annotations = './VOC2012/Annotations' #remember to modify the path
main_path = os.path.dirname(os.path.dirname(voc_annotations))
coco_name = 'VOC2012'
coco_path = os.path.join(main_path, coco_name+'_COCO')
coco_images = os.path.join(main_path, coco_name+'_COCO', 'images')
coco_json_annotations = os.path.join(main_path, coco_name+'_COCO','annotations')
xml_val = os.path.join(main_path, 'xml', 'xml_val')
xml_test = os.path.join(main_path, 'xml', 'xml_test')
xml_train = os.path.join(main_path, 'xml', 'xml_train')
voc_images = os.path.join(main_path, coco_name, 'JPEGImages')
#from https://www.php.cn/python-tutorials-424348.html
def mkdir(path):
path=path.strip()
path=path.rstrip("\\")
isExists=os.path.exists(path)
if not isExists:
os.makedirs(path)
logger.info('Folder already exists')
return True
logger.warning('Folder already exists')
return False
#foler to make, please enter full path
# map(mkdir,[coco_path, coco_images, coco_json_annotations, xml_val, xml_test, xml_train])
mkdir(coco_path)
mkdir(coco_images)
mkdir(coco_json_annotations)
mkdir(xml_val)
mkdir(xml_test)
mkdir(xml_train)
tbar = tqdm(list(zip(os.listdir(voc_images), os.listdir(voc_annotations))))
for idx, (img_name, xml_name) in enumerate(tbar):
img_src = os.path.join(voc_images, img_name)
xml_src = os.path.join(voc_annotations, xml_name)
# voc images copy to coco images
shutil.copy(img_src, coco_images)
# voc xml annotations copy to path 'xml_train'
shutil.copy(xml_src, xml_train)
tbar.set_description('COPYING |')
logger.info("%s files copied to %s" % (val_files_num, xml_val))
# split xmls xmls_test to xml_vla and xml_train
allxml = os.listdir(xml_train)
if len(allxml) > 0 or len(allxml) < val_files_num + test_files_num:
flist = random.sample(allxml, val_files_num + test_files_num)
val_list, test_list = flist[:val_files_num], flist[val_files_num:]
for val_fname, test_fname in zip(val_list, test_list):
src_val = os.path.join(xml_train, val_fname)
shutil.move(src_val, xml_val)
src_test = os.path.join(xml_train, test_fname)
shutil.move(src_test, xml_test)
else:
logger.fatal('The xmls folders are empty or Not enough to split into val and test, please make sure there are enough %d files to move' % (val_files_num))
logger.info("*" * 27 + "[Xmls segmentation Done ! Go check your file ]" + "*" * 28)
# # !/usr/bin/python
# pip install lxml
START_BOUNDING_BOX_ID = 1
PRE_DEFINE_CATEGORIES = None
# If necessary, pre-define category and its id
# PRE_DEFINE_CATEGORIES = {"aeroplane": 1, "bicycle": 2, "bird": 3, "boat": 4,
# "bottle":5, "bus": 6, "car": 7, "cat": 8, "chair": 9,
# "cow": 10, "diningtable": 11, "dog": 12, "horse": 13,
# "motorbike": 14, "person": 15, "pottedplant": 16,
# "sheep": 17, "sofa": 18, "train": 19, "tvmonitor": 20}
"""
main code below are from
https://github.com/Tony607/voc2coco
"""
def get(root, name):
vars = root.findall(name)
return vars
def get_and_check(root, name, length):
vars = root.findall(name)
if len(vars) == 0:
raise ValueError("Can not find %s in %s." % (name, root.tag))
if length > 0 and len(vars) != length:
raise ValueError(
"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 get_filename_as_int(filename):
try:
filename = filename.replace("_", "")
filename = os.path.splitext(os.path.basename(filename))[0]
return int(filename)
except:
raise ValueError("Filename %s is supposed to be an integer." % (filename))
def get_categories(xml_files):
"""Generate category name to id mapping from a list of xml files.
Arguments:
xml_files {list} -- A list of xml file paths.
Returns:
dict -- category name to id mapping.
"""
classes_names = []
for xml_file in xml_files:
tree = ET.parse(xml_file)
root = tree.getroot()
for member in root.findall("object"):
classes_names.append(member[0].text)
classes_names = list(set(classes_names))
classes_names.sort()
return {name: i for i, name in enumerate(classes_names)}
def convert(xml_files, json_file, split='unknown'):
json_dict = {"images": [], "type": "instances", "annotations": [], "categories": []}
if PRE_DEFINE_CATEGORIES is not None:
categories = PRE_DEFINE_CATEGORIES
else:
categories = get_categories(xml_files)
bnd_id = START_BOUNDING_BOX_ID
tbar = tqdm(xml_files)
for xml_file in tbar:
tree = ET.parse(xml_file)
root = tree.getroot()
path = get(root, "path")
if len(path) == 1:
filename = os.path.basename(path[0].text)
elif len(path) == 0:
filename = get_and_check(root, "filename", 1).text
else:
raise ValueError("%d paths found in %s" % (len(path), xml_file))
## The filename must be a number
image_id = get_filename_as_int(filename)
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 not in categories:
new_id = len(categories)
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)) - 1
ymin = int(float(get_and_check(bndbox, "ymin", 1).text)) - 1
xmax = int(float(get_and_check(bndbox, "xmax", 1).text))
ymax = int(float(get_and_check(bndbox, "ymax", 1).text))
assert xmax > xmin
assert ymax > ymin
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
tbar.set_description('SPLIT:{}'.format(split))
for cate, cid in categories.items():
cat = {"supercategory": "none", "id": cid, "name": cate}
json_dict["categories"].append(cat)
os.makedirs(os.path.dirname(json_file), exist_ok=True)
json_fp = open(json_file, "w")
json_str = json.dumps(json_dict)
json_fp.write(json_str)
json_fp.close()
xml_val_files = glob.glob(os.path.join(xml_val, "*.xml"))
xml_test_files = glob.glob(os.path.join(xml_test, "*.xml"))
xml_train_files = glob.glob(os.path.join(xml_train, "*.xml"))
convert(xml_val_files, coco_json_annotations + 'val2017.json', split='val')
convert(xml_test_files, coco_json_annotations+'test2017.json', split='test')
convert(xml_train_files, coco_json_annotations + 'train2017.json', split='train')
VOC格式数据转COCO(For Object Detection)
最新推荐文章于 2024-05-16 22:29:32 发布