1、根据ImageSets文件中的trainval.txt和test.txt文件将相应的图片、xml文件、labels文件夹中的txt提取出来,如下:
import os
import shutil
test_path = 'D:/BaiduNetdiskDownload/GDUT-HWD/ImageSets/Main/test.txt'
anno_path = 'D:/BaiduNetdiskDownload/GDUT-HWD/Annotations/'
img_path = 'D:/BaiduNetdiskDownload/GDUT-HWD/JPEGImages/'
label_path = 'D:/BaiduNetdiskDownload/GDUT-HWD/labels/'
anno_new_path = 'D:/BaiduNetdiskDownload/GDUT-HWD/my/val/xml/'
label_new_path = 'D:/BaiduNetdiskDownload/GDUT-HWD/my/val/labels/'
img_new_path = 'D:/BaiduNetdiskDownload/GDUT-HWD/my/val/images/'
def _main():
fp = open(test_path, 'r')
xml_list = fp.readlines()
fp.close()
i = 0
for file in xml_list:
xml_file = file.replace('\n', '')
shutil.copyfile(anno_path + xml_file+'.xml', anno_new_path + xml_file+'.xml')
shutil.copyfile(label_path + xml_file+'.txt', label_new_path + xml_file+'.txt')
shutil.copyfile(img_path + xml_file+'.jpg', img_new_path + xml_file+'.jpg')
#os.remove(anno_path + xml_file+'.xml')
i =+ 1
print( xml_file+'.xml')
print(i)
if __name__ == '__main__':
_main()
2、根据xml文件转换为coco格式,参考https://github.com/Tony607/voc2coco
代码如下:
#!/usr/bin/python
# pip install lxml
import sys
import os
import json
import xml.etree.ElementTree as ET
import glob
START_BOUNDING_BOX_ID = 1
PRE_DEFINE_CATEGORIES = {"blue": 1, "yellow": 2, "white": 3, "red": 4, "none":5}
#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}
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):
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
for xml_file in xml_files:
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(get_and_check(bndbox, "xmin", 1).text) - 1
ymin = int(get_and_check(bndbox, "ymin", 1).text) - 1
xmax = int(get_and_check(bndbox, "xmax", 1).text)
ymax = int(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
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()
if __name__ == "__main__":
import argparse
parser = argparse.ArgumentParser(
description="Convert Pascal VOC annotation to COCO format."
)
parser.add_argument("xml_dir", help="Directory path to xml files.", type=str)
parser.add_argument("json_file", help="Output COCO format json file.", type=str)
args = parser.parse_args()
xml_files = glob.glob(os.path.join(args.xml_dir, "*.xml"))
# If you want to do train/test split, you can pass a subset of xml files to convert function.
print("Number of xml files: {}".format(len(xml_files)))
convert(xml_files, args.json_file)
print("Success: {}".format(args.json_file))
用法
python voc2coco.py ./data/VOC/Annotations ./data/coco/output.json
最后就可以计算APs等等了
https://zhuanlan.zhihu.com/p/461488682
该链接中给出的voc转coco方法,最后计算APs时会报错