1、多个xml文件转coco格式
bug已改,已经试过可以用。
只需要修改三个地方:
- 将 xml_folder
- 将 class_name
- 将 json_file
然后按住shift+鼠标右键,选择在此处打开powershell,输入 python xxx.py即可转换成功
import logging
import os
import time
import xml.etree.ElementTree as ET
import json
def get_file_list(path, type=".xml"):
file_names = []
for maindir, subdir, file_name_list in os.walk(path):
for filename in file_name_list:
apath = os.path.join(maindir, filename)
ext = os.path.splitext(apath)[1]
if ext == type:
file_names.append(filename)
return file_names
def xml_to_coco(ann_path, class_names):
"""
convert xml annotations to coco_api
:param ann_path:
:return:
"""
class_name_dict = dict(zip(class_names, range(1, len(class_names)+1)))
print("loading annotations into memory...")
tic = time.time()
ann_file_names = get_file_list(ann_path, type=".xml")
logging.info("Found {} annotation files.".format(len(ann_file_names)))
image_info = []
categories = []
annotations = []
for idx, supercat in enumerate(class_names):
categories.append(
{"supercategory": supercat, "id": idx + 1, "name": supercat}
)
ann_id = 1
for idx, xml_name in enumerate(ann_file_names):
tree = ET.parse(os.path.join(ann_path, xml_name))
root = tree.getroot()
file_name = root.find("filename").text
width = int(root.find("size").find("width").text)
height = int(root.find("size").find("height").text)
info = {
"file_name": file_name,
"height": height,
"width": width,
"id": idx + 1,
}
image_info.append(info)
for _object in root.findall("object"):
category = _object.find("name").text
if category not in class_names:
print(
"WARNING! {} is not in class_names! "
"Pass this box annotation.".format(category)
)
continue
cat_id = class_name_dict[category]
xmin = int(_object.find("bndbox").find("xmin").text)
ymin = int(_object.find("bndbox").find("ymin").text)
xmax = int(_object.find("bndbox").find("xmax").text)
ymax = int(_object.find("bndbox").find("ymax").text)
w = xmax - xmin
h = ymax - ymin
if w < 0 or h < 0:
print(
"WARNING! Find error data in file {}! Box w and "
"h should > 0. Pass this box annotation.".format(xml_name)
)
continue
coco_box = [max(xmin, 0), max(ymin, 0), min(w, width), min(h, height)]
ann = {
"image_id": idx + 1, # 此处的图片序号,从1开始计算,该bbox所在的图片序号
"bbox": coco_box,
"category_id": cat_id,
"iscrowd": 0,
"id": ann_id, # ann_id指的是bbox的序号
"area": coco_box[2] * coco_box[3],
}
annotations.append(ann) # annotation是一个list,包含了所有bbox的相关信息
ann_id += 1
coco_dict = {
"images": image_info,
"categories": categories, # categories,从1开始计算
"annotations": annotations,
}
print("Done (t={:0.2f}s)".format(time.time() - tic))
return coco_dict
xml_folder = r"D:\documents\Learn\_Code\All_dataset\E\Annotations"
class_name = ['dog',
]
coco_dict = xml_to_coco(xml_folder, class_name)
"""
保存为json文件
"""
json_file = r"D:\documents\Learn\DeepLearning_Code\All_dataset\ELinage_All\COCOJson\EL_All.json"
json_fp = open(json_file, 'w')
json_str = json.dumps(coco_dict)
json_fp.write(json_str)
json_fp.close()
2、一个类的coco转VOC格式(xml)
用于一个类的情况
只需要修改6个地方:
- CKimg_dir:生成图片保存的路径
- CKanno_dir:生成标注文件保存的路径
- dataTypes:annotations名称,不带后缀
- base_dir:存放转换后的图片和标注的文件夹
- origin_image_dir:原始的coco的图像存放位置
- origin_anno_dir:原始的coco的标注存放位置
'''
把coco数据集合的所有标注转换到voc格式,不改变图片命名方式,
注意,原来有一些图片是黑白照片,检测出不是 RGB 图像,这样的图像不会被放到新的文件夹中
'''
from pycocotools.coco import COCO
import os, cv2, shutil
from lxml import etree, objectify
from tqdm import tqdm
from PIL import Image
# 1、生成图片保存的路径
CKimg_dir = r'faster_rcnn\balloon\VOC\images'
# 2、生成标注文件保存的路径
CKanno_dir = r'faster_rcnn\balloon\VOC\annotations'
# 若模型保存文件夹不存在,创建模型保存文件夹,若存在,删除重建
def mkr(path):
if os.path.exists(path):
shutil.rmtree(path)
os.mkdir(path)
else:
os.mkdir(path)
def save_annotations(filename, objs, filepath):
annopath = CKanno_dir + "/" + filename[:-3] + "xml" # 生成的xml文件保存路径
dst_path = CKimg_dir + "/" + filename
img_path = filepath
img = cv2.imread(img_path)
im = Image.open(img_path)
# if im.mode != "RGB":
# print(filename + " not a RGB image")
# im.close()
# return
im.close()
shutil.copy(img_path, dst_path) # 把原始图像复制到目标文件夹
E = objectify.ElementMaker(annotate=False)
anno_tree = E.annotation(
E.folder('1'),
E.filename(filename),
E.source(
E.database('CKdemo'),
E.annotation('VOC'),
E.image('CK')
),
E.size(
E.width(img.shape[1]),
E.height(img.shape[0]),
E.depth(img.shape[2])
),
E.segmented(0)
)
for obj in objs:
E2 = objectify.ElementMaker(annotate=False)
anno_tree2 = E2.object(
E.name(obj[0]),
E.pose(),
E.truncated("0"),
E.difficult(0),
E.bndbox(
E.xmin(obj[2]),
E.ymin(obj[3]),
E.xmax(obj[4]),
E.ymax(obj[5])
)
)
anno_tree.append(anno_tree2)
etree.ElementTree(anno_tree).write(annopath, pretty_print=True)
def showbycv(coco, img, classes, origin_image_dir, verbose=False):
filename = img['file_name']
filepath = os.path.join(origin_image_dir, filename)
I = cv2.imread(filepath)
annIds = coco.getAnnIds(imgIds=img['id'], iscrowd=None)
anns = coco.loadAnns(annIds)
objs = []
for ann in anns:
name = classes[ann['category_id']]
if 'bbox' in ann:
bbox = ann['bbox']
xmin = (int)(bbox[0])
ymin = (int)(bbox[1])
xmax = (int)(bbox[2] + bbox[0])
ymax = (int)(bbox[3] + bbox[1])
obj = [name, 1.0, xmin, ymin, xmax, ymax]
objs.append(obj)
if verbose:
cv2.rectangle(I, (xmin, ymin), (xmax, ymax), (255, 0, 0))
cv2.putText(I, name, (xmin, ymin), 3, 1, (0, 0, 255))
save_annotations(filename, objs, filepath)
if verbose:
cv2.imshow("img", I)
cv2.waitKey(0)
def catid2name(coco): # 将名字和id号建立一个字典
classes = dict()
for cat in coco.dataset['categories']:
classes[cat['id']] = cat['name']
# print(str(cat['id'])+":"+cat['name'])
return classes
def get_CK5(origin_anno_dir, origin_image_dir, verbose=False):
dataTypes = ['annotation_coco'] # 3、根据你要转化的是训练集还是验证集(annotations名称)
for dataType in dataTypes:
annFile = '{}.json'.format(dataType)
annpath = os.path.join(origin_anno_dir, annFile)
coco = COCO(annpath)
classes = catid2name(coco)
imgIds = coco.getImgIds()
# imgIds=imgIds[0:1000]#测试用,抽取10张图片,看下存储效果
for imgId in tqdm(imgIds):
img = coco.loadImgs(imgId)[0]
#showbycv(coco, dataType, img, classes, origin_image_dir, verbose=False)
showbycv(coco, img, classes, origin_image_dir, verbose=False)
def main():
base_dir = r'D:\documents\faster_rcnn\balloon\VOC' # step1 这里是一个新的文件夹,存放转换后的图片和标注
image_dir = os.path.join(base_dir, 'images') # 在上述文件夹中生成images,annotations两个子文件夹
anno_dir = os.path.join(base_dir, 'annotations')
mkr(image_dir)
mkr(anno_dir)
# 4、
origin_image_dir = 'train' # step 2原始的coco的图像存放位置
# 5、
origin_anno_dir = 'train' # step 3 原始的coco的标注存放位置
print(origin_anno_dir)
verbose = True # 是否需要看下标记是否正确的开关标记,若是true,就会把标记展示到图片上
get_CK5(origin_anno_dir, origin_image_dir, verbose)
if __name__ == "__main__":
main()
2、多个类的coco转VOC格式(xml)
待补充