mirrors/mmocr
1
0
Fork 0
mirror of https://github.com/open-mmlab/mmocr.git synced 2025-06-03 21:54:47 +08:00
Code Issues Projects Releases Wiki Activity

[Fix] Fix Data Converter Issues (#955)

Browse Source 
* fix naf mask issue; fix lv path issue

* fix path

* fix ic13, ic11 path issue; fix cocotextv2 mask issue

* fix funsd format
This commit is contained in:
Xinyu Wang 2022-05-05 14:09:05 +08:00 committed by GitHub
parent ae1cf42503
commit b4678eb657
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23
6 changed files with 13 additions and 9 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
tools/data/textdet/cocotext_converter.py
View File

@ -92,6 +92,8 @@ def collect_cocotext_info(root_path, split, print_every=1000):
w, h = math.ceil(w), math.ceil(h)
bbox = [x, y, w, h]
segmentation = [max(0, int(x)) for x in ann['mask']]
if len(segmentation) < 8 or len(segmentation) % 2 != 0:
segmentation = [x, y, x + w, y, x + w, y + h, x, y + h]
anno = dict(
iscrowd=iscrowd,
category_id=1,

3
tools/data/textdet/lv_converter.py
View File

@ -83,9 +83,10 @@ def load_img_info(files):
'.')[0]
# read imgs while ignoring orientations
img = mmcv.imread(img_file, 'unchanged')
img_file = img_file.split('data/lv/')[1]
img_info = dict(
file_name=osp.join(osp.basename(img_file)),
file_name=img_file,
height=img.shape[0],
width=img.shape[1],
segm_file=osp.join(osp.basename(gt_file)))

5
tools/data/textdet/naf_converter.py
View File

@ -139,14 +139,15 @@ def load_json_info(gt_file, img_info):
if anno['type'] == 'blank':
continue
xs, ys = [], []
xs, ys, segmentation = [], [], []
for p in anno['poly_points']:
xs.append(p[0])
ys.append(p[1])
segmentation.append(p[0])
segmentation.append(p[1])
x, y = max(0, min(xs)), max(0, min(ys))
w, h = max(xs) - x, max(ys) - y
bbox = [x, y, w, h]
segmentation = anno['poly_points']
anno = dict(
iscrowd=0,

4
tools/data/textrecog/funsd_converter.py
View File

@ -140,9 +140,9 @@ def generate_ann(root_path, split, image_infos, preserve_vertical, format):
dst_image_root = osp.join(root_path, 'dst_imgs', split)
if split == 'training':
dst_label_file = osp.join(root_path, 'train_label.txt')
dst_label_file = osp.join(root_path, f'train_label.{format}')
elif split == 'test':
dst_label_file = osp.join(root_path, 'test_label.txt')
dst_label_file = osp.join(root_path, f'test_label.{format}')
os.makedirs(dst_image_root, exist_ok=True)
lines = []

4
tools/data/textrecog/ic11_converter.py
View File

@ -39,7 +39,7 @@ def convert_annotations(root_path, split, format):
'r',
encoding='"utf-8-sig') as f:
annos = f.readlines()
dst_image_root = osp.join(root_path, split)
dst_image_root = osp.join(root_path, split.lower())
for anno in annos:
# text may contain comma ','
dst_img_name, word = anno.split(', "')
@ -58,7 +58,7 @@ def convert_annotations(root_path, split, format):
else:
raise NotImplementedError
list_to_file(osp.join(root_path, f'{split}_label.{format}'), lines)
list_to_file(osp.join(root_path, f'{split.lower()}_label.{format}'), lines)
def parse_args():

4
tools/data/textrecog/ic13_converter.py
View File

@ -39,7 +39,7 @@ def convert_annotations(root_path, split, format):
'r',
encoding='"utf-8-sig') as f:
annos = f.readlines()
dst_image_root = osp.join(root_path, split)
dst_image_root = osp.join(root_path, split.lower())
for anno in annos:
# text may contain comma ','
dst_img_name, word = anno.split(', "')
@ -58,7 +58,7 @@ def convert_annotations(root_path, split, format):
else:
raise NotImplementedError
list_to_file(osp.join(root_path, f'{split}_label.{format}'), lines)
list_to_file(osp.join(root_path, f'{split.lower()}_label.{format}'), lines)
def parse_args():