mirrors
/
mmocr
mirror of https://github.com/open-mmlab/mmocr.git
1
0
Fork 0
Code Issues Projects Releases Wiki Activity

[Feature] Add ReCTS Data Converter (#892)

pull/901/head
Xinyu Wang 2022-03-30 15:24:37 +08:00 committed by GitHub
parent 6ef3ecd300
commit bea8587f3f
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23
2 changed files with 476 additions and 0 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

205
tools/data/textdet/rects_converter.py 100644
View File

@ -0,0 +1,205 @@
# Copyright (c) OpenMMLab. All rights reserved.
import argparse
import math
import os
import os.path as osp
import mmcv
from mmocr.utils import convert_annotations
def collect_files(img_dir, gt_dir, ratio):
"""Collect all images and their corresponding groundtruth files.
Args:
img_dir (str): The image directory
gt_dir (str): The groundtruth directory
ratio (float): Split ratio for val set
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
assert isinstance(ratio, float)
assert ratio < 1.0, 'val_ratio should be a float between 0.0 to 1.0'
ann_list, imgs_list = [], []
for ann_file in os.listdir(gt_dir):
ann_list.append(osp.join(gt_dir, ann_file))
imgs_list.append(osp.join(img_dir, ann_file.replace('json', 'jpg')))
all_files = list(zip(imgs_list, ann_list))
assert len(all_files), f'No images found in {img_dir}'
print(f'Loaded {len(all_files)} images from {img_dir}')
trn_files, val_files = [], []
if ratio > 0:
for i, file in enumerate(all_files):
if i % math.floor(1 / ratio):
trn_files.append(file)
else:
val_files.append(file)
else:
trn_files, val_files = all_files, []
print(f'training #{len(trn_files)}, val #{len(val_files)}')
return trn_files, val_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 = mmcv.track_parallel_progress(
load_img_info, files, nproc=nproc)
else:
images = mmcv.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 osp.basename(gt_file).split('.')[0] == osp.basename(img_file).split(
'.')[0]
# read imgs while ignoring orientations
img = mmcv.imread(img_file)
img_info = dict(
file_name=osp.join(osp.basename(img_file)),
height=img.shape[0],
width=img.shape[1],
segm_file=osp.join(osp.basename(gt_file)))
if osp.splitext(gt_file)[1] == '.json':
img_info = load_json_info(gt_file, img_info)
else:
raise NotImplementedError
return img_info
def load_json_info(gt_file, img_info):
"""Collect the annotation information.
The annotation format is as the following:
{
"chars": [
{
"ignore": 0,
"transcription": "H",
"points": [25, 175, 112, 175, 112, 286, 25, 286]
},
{
"ignore": 0,
"transcription": "O",
"points": [102, 182, 210, 182, 210, 273, 102, 273]
}, ...
]
"lines": [
{
"ignore": 0,
"transcription": "HOKI",
"points": [23, 173, 327, 180, 327, 290, 23, 283]
},
{
"ignore": 0,
"transcription": "TEA",
"points": [368, 180, 621, 180, 621, 294, 368, 294]
}, ...
]
}
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
"""
annotation = mmcv.load(gt_file)
anno_info = []
for line in annotation['lines']:
segmentation = line['points']
x = max(0, min(segmentation[0::2]))
y = max(0, min(segmentation[1::2]))
w = abs(max(segmentation[0::2]) - x)
h = abs(max(segmentation[1::2]) - y)
bbox = [x, y, w, h]
anno = dict(
iscrowd=line['ignore'],
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 val set of ReCTS.')
parser.add_argument('root_path', help='Root dir path of ReCTS')
parser.add_argument(
'--val-ratio', help='Split ratio for val set', default=0.0, type=float)
parser.add_argument(
'--nproc', default=1, type=int, help='Number of process')
args = parser.parse_args()
return args
def main():
args = parse_args()
root_path = args.root_path
ratio = args.val_ratio
trn_files, val_files = collect_files(
osp.join(root_path, 'imgs'), osp.join(root_path, 'annotations'), ratio)
# Train set
trn_infos = collect_annotations(trn_files, nproc=args.nproc)
with mmcv.Timer(
print_tmpl='It takes {}s to convert ReCTS Training annotation'):
convert_annotations(trn_infos,
osp.join(root_path, 'instances_training.json'))
# Val set
if len(val_files) > 0:
val_infos = collect_annotations(val_files, nproc=args.nproc)
with mmcv.Timer(
print_tmpl='It takes {}s to convert ReCTS Val annotation'):
convert_annotations(val_infos,
osp.join(root_path, 'instances_val.json'))
if __name__ == '__main__':
main()

271
tools/data/textrecog/rects_converter.py 100644
View File

@ -0,0 +1,271 @@
# Copyright (c) OpenMMLab. All rights reserved.
import argparse
import json
import math
import os
import os.path as osp
import mmcv
from mmocr.datasets.pipelines.crop import crop_img
from mmocr.utils.fileio import list_to_file
def collect_files(img_dir, gt_dir, ratio):
"""Collect all images and their corresponding groundtruth files.
Args:
img_dir (str): The image directory
gt_dir (str): The groundtruth directory
ratio (float): Split ratio for val set
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
assert isinstance(ratio, float)
assert ratio < 1.0, 'val_ratio should be a float between 0.0 to 1.0'
ann_list, imgs_list = [], []
for ann_file in os.listdir(gt_dir):
ann_list.append(osp.join(gt_dir, ann_file))
imgs_list.append(osp.join(img_dir, ann_file.replace('json', 'jpg')))
all_files = list(zip(imgs_list, ann_list))
assert len(all_files), f'No images found in {img_dir}'
print(f'Loaded {len(all_files)} images from {img_dir}')
trn_files, val_files = [], []
if ratio > 0:
for i, file in enumerate(all_files):
if i % math.floor(1 / ratio):
trn_files.append(file)
else:
val_files.append(file)
else:
trn_files, val_files = all_files, []
print(f'training #{len(trn_files)}, val #{len(val_files)}')
return trn_files, val_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 = mmcv.track_parallel_progress(
load_img_info, files, nproc=nproc)
else:
images = mmcv.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 osp.basename(gt_file).split('.')[0] == osp.basename(img_file).split(
'.')[0]
# read imgs while ignoring orientations
img = mmcv.imread(img_file)
img_info = dict(
file_name=osp.join(osp.basename(img_file)),
height=img.shape[0],
width=img.shape[1],
segm_file=osp.join(osp.basename(gt_file)))
if osp.splitext(gt_file)[1] == '.json':
img_info = load_json_info(gt_file, img_info)
else:
raise NotImplementedError
return img_info
def load_json_info(gt_file, img_info):
"""Collect the annotation information.
The annotation format is as the following:
{
"chars": [
{
"ignore": 0,
"transcription": "H",
"points": [25, 175, 112, 175, 112, 286, 25, 286]
},
{
"ignore": 0,
"transcription": "O",
"points": [102, 182, 210, 182, 210, 273, 102, 273]
}, ...
]
"lines": [
{
"ignore": 0,
"transcription": "HOKI",
"points": [23, 173, 327, 180, 327, 290, 23, 283]
},
{
"ignore": 0,
"transcription": "TEA",
"points": [368, 180, 621, 180, 621, 294, 368, 294]
}, ...
]
}
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
"""
annotation = mmcv.load(gt_file)
anno_info = []
for line in annotation['lines']:
if line['ignore'] == 1:
continue
segmentation = line['points']
word = line['transcription']
anno = dict(bbox=segmentation, word=word)
anno_info.append(anno)
img_info.update(anno_info=anno_info)
return img_info
def generate_ann(root_path, split, image_infos, preserve_vertical, format):
"""Generate cropped annotations and label txt file.
Args:
root_path (str): The root path of the dataset
split (str): The split of dataset. Namely: training or test
image_infos (list[dict]): A list of dicts of the img and
annotation information
preserve_vertical (bool): Whether to preserve vertical texts
format (str): Annotation format, whether be txt or jsonl
"""
print('Cropping images...')
dst_image_root = osp.join(root_path, 'crops', split)
ignore_image_root = osp.join(root_path, 'ignores', split)
if split == 'training':
dst_label_file = osp.join(root_path, f'train_label.{format}')
elif split == 'val':
dst_label_file = osp.join(root_path, f'val_label.{format}')
mmcv.mkdir_or_exist(dst_image_root)
mmcv.mkdir_or_exist(ignore_image_root)
lines = []
for image_info in image_infos:
index = 1
src_img_path = osp.join(root_path, 'imgs', image_info['file_name'])
image = mmcv.imread(src_img_path)
src_img_root = image_info['file_name'].split('.')[0]
for anno in image_info['anno_info']:
word = anno['word']
dst_img = crop_img(image, anno['bbox'], 0, 0)
h, w, _ = dst_img.shape
dst_img_name = f'{src_img_root}_{index}.png'
index += 1
# Skip invalid annotations
if min(dst_img.shape) == 0:
continue
# Skip vertical texts
if not preserve_vertical and h / w > 2 and split == 'training':
dst_img_path = osp.join(ignore_image_root, dst_img_name)
else:
dst_img_path = osp.join(dst_image_root, dst_img_name)
mmcv.imwrite(dst_img, dst_img_path)
if format == 'txt':
lines.append(f'{osp.basename(dst_image_root)}/{dst_img_name} '
f'{word}')
elif format == 'jsonl':
lines.append(
json.dumps(
{
'filename':
f'{osp.basename(dst_image_root)}/{dst_img_name}',
'text': word
},
ensure_ascii=False))
else:
raise NotImplementedError
list_to_file(dst_label_file, lines)
def parse_args():
parser = argparse.ArgumentParser(
description='Generate training and val set of ReCTS.')
parser.add_argument('root_path', help='Root dir path of ReCTS')
parser.add_argument(
'--val-ratio', help='Split ratio for val set', default=0.0, type=float)
parser.add_argument(
'--nproc', default=1, type=int, help='Number of process')
parser.add_argument(
'--preserve-vertical',
help='Preserve samples containing vertical texts',
action='store_true')
parser.add_argument(
'--format',
default='jsonl',
help='Use jsonl or string to format annotations',
choices=['jsonl', 'txt'])
args = parser.parse_args()
return args
def main():
args = parse_args()
root_path = args.root_path
ratio = args.val_ratio
trn_files, val_files = collect_files(
osp.join(root_path, 'imgs'), osp.join(root_path, 'annotations'), ratio)
# Train set
trn_infos = collect_annotations(trn_files, nproc=args.nproc)
with mmcv.Timer(
print_tmpl='It takes {}s to convert ReCTS Training annotation'):
generate_ann(root_path, 'training', trn_infos, args.preserve_vertical,
args.format)
# Val set
if len(val_files) > 0:
val_infos = collect_annotations(val_files, nproc=args.nproc)
with mmcv.Timer(
print_tmpl='It takes {}s to convert ReCTS Val annotation'):
generate_ann(root_path, 'val', val_infos, args.preserve_vertical,
args.format)
if __name__ == '__main__':
main()