Spaces:
Sleeping
Sleeping
File size: 5,014 Bytes
9bf4bd7 |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 |
# Copyright (c) OpenMMLab. All rights reserved.
import argparse
import os
import os.path as osp
import mmcv
import mmengine
from mmocr.utils import dump_ocr_data
def collect_files(img_dir, gt_dir):
"""Collect all images and their corresponding groundtruth files.
Args:
img_dir (str): The image directory
gt_dir (str): The groundtruth directory
Returns:
files (list): The list of tuples (img_file, groundtruth_file)
"""
assert isinstance(img_dir, str)
assert img_dir
assert isinstance(gt_dir, str)
assert gt_dir
ann_list, imgs_list = [], []
for img_file in os.listdir(img_dir):
ann_file = 'gt_' + str(int(img_file[2:6])) + '.txt'
ann_list.append(osp.join(gt_dir, ann_file))
imgs_list.append(osp.join(img_dir, img_file))
files = list(zip(imgs_list, ann_list))
assert len(files), f'No images found in {img_dir}'
print(f'Loaded {len(files)} images from {img_dir}')
return files
def collect_annotations(files, nproc=1):
"""Collect the annotation information.
Args:
files (list): The list of tuples (image_file, groundtruth_file)
nproc (int): The number of process to collect annotations
Returns:
images (list): The list of image information dicts
"""
assert isinstance(files, list)
assert isinstance(nproc, int)
if nproc > 1:
images = mmengine.track_parallel_progress(
load_img_info, files, nproc=nproc)
else:
images = mmengine.track_progress(load_img_info, files)
return images
def load_img_info(files):
"""Load the information of one image.
Args:
files (tuple): The tuple of (img_file, groundtruth_file)
Returns:
img_info (dict): The dict of the img and annotation information
"""
assert isinstance(files, tuple)
img_file, gt_file = files
assert int(osp.basename(gt_file)[3:-4]) == int(
osp.basename(img_file)[2:-4])
# read imgs while ignoring orientations
img = mmcv.imread(img_file, 'unchanged')
img_info = dict(
file_name=osp.basename(img_file),
height=img.shape[0],
width=img.shape[1],
segm_file=osp.basename(gt_file))
if osp.splitext(gt_file)[1] == '.txt':
img_info = load_txt_info(gt_file, img_info)
else:
raise NotImplementedError
return img_info
def load_txt_info(gt_file, img_info):
"""Collect the annotation information.
The annotation format is as the following:
x1,y1,x2,y2,x3,y3,x4,y4,text
118,15,147,15,148,46,118,46,LƯỢNG
149,9,165,9,165,43,150,43,TỐT
167,9,180,9,179,43,167,42,ĐỂ
181,12,193,12,193,43,181,43,CÓ
195,13,215,14,215,46,196,46,VIỆC
217,13,237,14,239,47,217,46,LÀM,
Args:
gt_file (str): The path to ground-truth
img_info (dict): The dict of the img and annotation information
Returns:
img_info (dict): The dict of the img and annotation information
"""
with open(gt_file, encoding='utf-8') as f:
anno_info = []
for line in f:
line = line.strip('\n')
ann = line.split(',')
bbox = ann[0:8]
word = line[len(','.join(bbox)) + 1:]
bbox = [int(coord) for coord in bbox]
segmentation = bbox
x_min = min(bbox[0], bbox[2], bbox[4], bbox[6])
x_max = max(bbox[0], bbox[2], bbox[4], bbox[6])
y_min = min(bbox[1], bbox[3], bbox[5], bbox[7])
y_max = max(bbox[1], bbox[3], bbox[5], bbox[7])
w = x_max - x_min
h = y_max - y_min
bbox = [x_min, y_min, w, h]
iscrowd = 1 if word == '###' else 0
anno = dict(
iscrowd=iscrowd,
category_id=1,
bbox=bbox,
area=w * h,
segmentation=[segmentation])
anno_info.append(anno)
img_info.update(anno_info=anno_info)
return img_info
def parse_args():
parser = argparse.ArgumentParser(
description='Generate training and test set of VinText ')
parser.add_argument('root_path', help='Root dir path of VinText')
parser.add_argument(
'--nproc', default=1, type=int, help='Number of processes')
args = parser.parse_args()
return args
def main():
args = parse_args()
root_path = args.root_path
for split in ['training', 'test', 'unseen_test']:
print(f'Processing {split} set...')
with mmengine.Timer(
print_tmpl='It takes {}s to convert VinText annotation'):
files = collect_files(
osp.join(root_path, 'imgs', split),
osp.join(root_path, 'annotations'))
image_infos = collect_annotations(files, nproc=args.nproc)
dump_ocr_data(image_infos,
osp.join(root_path, 'instances_' + split + '.json'),
'textdet')
if __name__ == '__main__':
main()
|