def main():
args = parse_args()
root_path = args.root_path
print('Processing training set...')
training_infos = collect_textocr_info(root_path, 'TextOCR_0.1_train.json')
convert_annotations(training_infos,
osp.join(root_path, 'instances_training.json'))
print('Processing validation set...')
val_infos = collect_textocr_info(root_path, 'TextOCR_0.1_val.json')
convert_annotations(val_infos, osp.join(root_path, 'instances_val.json'))
print('Finish')
def main():
args = parse_args()
root_path = args.root_path
print('Processing training set...')
training_infos = collect_hiertext_info(root_path, args.level, 'train')
convert_annotations(training_infos,
osp.join(root_path, 'instances_training.json'))
print('Processing validation set...')
val_infos = collect_hiertext_info(root_path, args.level, 'val')
convert_annotations(val_infos, osp.join(root_path, 'instances_val.json'))
print('Finish')
def main():
args = parse_args()
root_path = args.root_path
for split in ['train', 'val', 'test']:
print(f'Processing {split} set...')
with mmcv.Timer(print_tmpl='It takes {}s to convert IMGUR annotation'):
anno_infos = collect_imgur_info(
root_path, f'imgur5k_annotations_{split}.json')
convert_annotations(anno_infos,
osp.join(root_path, f'instances_{split}.json'))
def main():
args = parse_args()
root_path = args.root_path
for split in ['train', 'val', 'test']:
print(f'Processing {split} set...')
with mmcv.Timer(print_tmpl='It takes {}s to convert LV annotation'):
files = collect_files(osp.join(root_path, 'imgs', split))
image_infos = collect_annotations(files, nproc=args.nproc)
convert_annotations(
image_infos, osp.join(root_path,
'instances_' + split + '.json'))
def main():
args = parse_args()
root_path = args.root_path
with mmcv.Timer(print_tmpl='It takes {}s to convert BID annotation'):
files = collect_files(osp.join(root_path, 'imgs'),
osp.join(root_path, 'annotations'))
image_infos = collect_annotations(files, nproc=args.nproc)
if args.val_ratio:
image_infos = split_train_val_list(image_infos, args.val_ratio)
splits = ['training', 'val']
else:
image_infos = [image_infos]
splits = ['training']
for i, split in enumerate(splits):
convert_annotations(
image_infos[i],
osp.join(root_path, 'instances_' + split + '.json'))
def main():
args = parse_args()
root_path = args.root_path
split_info = mmcv.load(
osp.join(root_path, 'annotations', 'train_valid_test_split.json'))
split_info['training'] = split_info.pop('train')
split_info['val'] = split_info.pop('valid')
for split in ['training', 'val', 'test']:
print(f'Processing {split} set...')
with mmcv.Timer(print_tmpl='It takes {}s to convert NAF annotation'):
files = collect_files(osp.join(root_path, 'imgs'),
osp.join(root_path, 'annotations'),
split_info[split])
image_infos = collect_annotations(files, nproc=args.nproc)
convert_annotations(
image_infos, osp.join(root_path,
'instances_' + split + '.json'))
def main():
args = parse_args()
root_path = args.root_path
img_dir = osp.join(root_path, 'imgs')
gt_dir = osp.join(root_path, 'annotations')
set_name = {}
for split in ['training', 'test']:
set_name.update({split: 'instances_' + split + '.json'})
assert osp.exists(osp.join(img_dir, split))
for split, json_name in set_name.items():
print(f'Converting {split} into {json_name}')
with mmcv.Timer(
print_tmpl='It takes {}s to convert totaltext annotation'):
files = collect_files(osp.join(img_dir, split),
osp.join(gt_dir, split))
image_infos = collect_annotations(files, nproc=args.nproc)
convert_annotations(image_infos, osp.join(root_path, json_name))
def main():
args = parse_args()
root_path = args.root_path
out_dir = args.out_dir if args.out_dir else root_path
mmcv.mkdir_or_exist(out_dir)
img_dir = osp.join(root_path, 'imgs')
gt_dir = osp.join(root_path, 'annotations')
set_name = {}
for split in args.split_list:
set_name.update({split: 'instances_' + split + '.json'})
assert osp.exists(osp.join(img_dir, split))
for split, json_name in set_name.items():
print(f'Converting {split} into {json_name}')
with mmcv.Timer(print_tmpl='It takes {}s to convert icdar annotation'):
files = collect_files(osp.join(img_dir, split),
osp.join(gt_dir, split), split)
image_infos = collect_annotations(files, split, nproc=args.nproc)
convert_annotations(image_infos, osp.join(out_dir, json_name))
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 KAIST 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 KAIST Val annotation'):
convert_annotations(val_infos,
osp.join(root_path, 'instances_val.json'))
