convert_voc_to_coco.py

#!/usr/bin/env python
# -*- coding: utf-8 -*-

"""
Convert PASCAL VOC to COCO.

License_info:
# ==============================================================================
# ISC License (ISC)
# Copyright 2020 Christian Doppler Laboratory for Embedded Machine Learning
#
# Permission to use, copy, modify, and/or distribute this software for any
# purpose with or without fee is hereby granted, provided that the above
# copyright notice and this permission notice appear in all copies.
#
# THE SOFTWARE IS PROVIDED "AS IS" AND THE AUTHOR DISCLAIMS ALL WARRANTIES WITH
# REGARD TO THIS SOFTWARE INCLUDING ALL IMPLIED WARRANTIES OF MERCHANTABILITY AND
# FITNESS. IN NO EVENT SHALL THE AUTHOR BE LIABLE FOR ANY SPECIAL, DIRECT,
# INDIRECT, OR CONSEQUENTIAL DAMAGES OR ANY DAMAGES WHATSOEVER RESULTING FROM
# LOSS OF USE, DATA OR PROFITS, WHETHER IN AN ACTION OF CONTRACT, NEGLIGENCE
# OR OTHER TORTIOUS ACTION, ARISING OUT OF OR IN CONNECTION WITH THE USE OR
# PERFORMANCE OF THIS SOFTWARE.
# ==============================================================================

# The following script uses several method fragments the following script. We modified the execution with argparse to
# generalize the script.
# Source: https://github.com/yukkyo/voc2coco

"""

# Futures
from __future__ import print_function

# Built-in/Generic Imports
import glob
import os
import json
import re

# Libs
import argparse
import xml.etree.ElementTree as ET
from typing import Dict, List
from tqdm import tqdm

# Own modules

__author__ = 'Alexander Wendt'
__copyright__ = 'Copyright 2020, Christian Doppler Laboratory for ' \
                'Embedded Machine Learning'
__credits__ = ['Y. fujimoto']
__license__ = 'ISC'
__version__ = '0.2.0'
__maintainer__ = 'Alexander Wendt'
__email__ = 'alexander.wendt@tuwien.ac.at'
__status__ = 'Experiental'

parser = argparse.ArgumentParser(
        description='This script support converting voc format xmls to coco format json')
parser.add_argument('--ann_dir', type=str, default=None,
                    help='path to annotation files directory. It is not need when use --ann_paths_list')
parser.add_argument('--ann_ids', type=str, default=None,
                    help='path to annotation files ids list. It is not need when use --ann_paths_list.'
                         'If --ann_ids is not provided, all xmls in the --ann_dir will be used.')
parser.add_argument('--ann_paths_list', type=str, default=None,
                    help='path of annotation paths list. It is not need when use --ann_dir and --ann_ids')
parser.add_argument('--labels', type=str, default=None,
                    help='path to label list.')
parser.add_argument('--output', type=str, default='output.json', help='path to output json file')
parser.add_argument('--ext', type=str, default='', help='additional extension of annotation file')
parser.add_argument('--extract_num_from_imgid', action="store_true",
                    help='Extract image number from the image filename')
args = parser.parse_args()

def get_label2id(labels_path: str) -> Dict[str, int]:
    """id is 1 start"""
    with open(labels_path, 'r') as f:
        labels_str = f.read().split()
    labels_ids = list(range(1, len(labels_str)+1))
    return dict(zip(labels_str, labels_ids))


def get_annpaths(ann_dir_path: str = None,
                 ann_ids_path: str = None,
                 ext: str = '',
                 annpaths_list_path: str = None) -> List[str]:
    # If use annotation paths list
    if annpaths_list_path is not None:
        with open(annpaths_list_path, 'r') as f:
            ann_paths = f.read().split()
        return ann_paths

    # If use annotaion ids list
    ext_with_dot = '.' + ext if ext != '' else ''
    if ann_ids_path:
        with open(ann_ids_path, 'r') as f:
            ann_ids = f.read().split()
    else:
        # No txt wit file names provided, take everything from the folder
        ann_ids = [os.path.splitext(os.path.basename(f))[-2] for f in glob.glob(os.path.join(ann_dir_path, '*.*'))]
    ann_paths = [os.path.join(ann_dir_path, aid+ext_with_dot) for aid in ann_ids]
    return ann_paths


def get_image_info(annotation_root, extract_num_from_imgid=True):
    path = annotation_root.findtext('path')
    if path is None:
        filename = annotation_root.findtext('filename')
    else:
        filename = os.path.basename(path)
    img_name = os.path.basename(filename)
    img_id = os.path.splitext(img_name)[0]
    if extract_num_from_imgid and isinstance(img_id, str):
        img_id = int(re.findall(r'\d+', img_id)[0])

    size = annotation_root.find('size')
    width = int(size.findtext('width'))
    height = int(size.findtext('height'))

    image_info = {
        'file_name': filename,
        'height': height,
        'width': width,
        'id': img_id
    }
    return image_info


def get_coco_annotation_from_obj(obj, label2id):
    label = obj.findtext('name')
    assert label in label2id, f"Error: {label} is not in label2id !"
    category_id = label2id[label]
    bndbox = obj.find('bndbox')
    xmin = int(bndbox.findtext('xmin')) - 1
    ymin = int(bndbox.findtext('ymin')) - 1
    xmax = int(bndbox.findtext('xmax'))
    ymax = int(bndbox.findtext('ymax'))
    assert xmax > xmin and ymax > ymin, f"Box size error !: (xmin, ymin, xmax, ymax): {xmin, ymin, xmax, ymax}"
    o_width = xmax - xmin - 1   #Subtracted -1 to be the same as roboflow's conversion
    o_height = ymax - ymin - 1  #Subtracted -1 to be the same as roboflow's conversion
    ann = {
        'area': o_width * o_height,
        'iscrowd': 0,
        'bbox': [xmin, ymin, o_width, o_height],
        'category_id': category_id,
        'ignore': 0,
        'segmentation': []  # This script is not for segmentation
    }
    return ann


def convert_xmls_to_cocojson(annotation_paths: List[str],
                             label2id: Dict[str, int],
                             output_jsonpath: str,
                             extract_num_from_imgid: bool = True):
    output_json_dict = {
        "images": [],
        "type": "instances",
        "annotations": [],
        "categories": []
    }
    bnd_id = 1  # START_BOUNDING_BOX_ID, TODO input as args ?
    print('Start converting !')
    for a_path in tqdm(annotation_paths):
        # Read annotation xml
        ann_tree = ET.parse(a_path)
        ann_root = ann_tree.getroot()

        img_info = get_image_info(annotation_root=ann_root,
                                  extract_num_from_imgid=extract_num_from_imgid)
        img_id = img_info['id']
        output_json_dict['images'].append(img_info)

        print(img_id)
        for obj in ann_root.findall('object'):
            ann = get_coco_annotation_from_obj(obj=obj, label2id=label2id)
            ann.update({'image_id': img_id, 'id': bnd_id})
            output_json_dict['annotations'].append(ann)
            bnd_id = bnd_id + 1

    for label, label_id in label2id.items():
        category_info = {'supercategory': 'none', 'id': label_id, 'name': label}
        output_json_dict['categories'].append(category_info)

    with open(output_jsonpath, 'w') as outfile:
        json.dump(output_json_dict, outfile, indent=4)

    #with open(output_jsonpath, 'w') as f:
    #    output_json = json.dumps(output_json_dict, indent=4)
    #    f.write(output_json)


def main():
    label2id = get_label2id(labels_path=args.labels)

    ann_paths = get_annpaths(
        ann_dir_path=args.ann_dir,
        ann_ids_path=args.ann_ids,
        ext=args.ext,
        annpaths_list_path=args.ann_paths_list
    )
    convert_xmls_to_cocojson(
        annotation_paths=ann_paths,
        label2id=label2id,
        output_jsonpath=args.output,
        extract_num_from_imgid=args.extract_num_from_imgid
    )


if __name__ == '__main__':
    main()