Spaces:
Sleeping
Sleeping
File size: 3,618 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 |
# Copyright (c) OpenMMLab. All rights reserved.
import os.path as osp
from typing import Dict, List, Tuple
import mmcv
from mmocr.registry import DATA_PACKERS
from mmocr.utils import bbox2poly, poly2bbox
from .base import BasePacker
@DATA_PACKERS.register_module()
class TextSpottingPacker(BasePacker):
"""Text spotting packer. It is used to pack the parsed annotation info to:
.. code-block:: python
{
"metainfo":
{
"dataset_type": "TextDetDataset",
"task_name": "textdet",
"category": [{"id": 0, "name": "text"}]
},
"data_list":
[
{
"img_path": "test_img.jpg",
"height": 640,
"width": 640,
"instances":
[
{
"polygon": [0, 0, 0, 10, 10, 20, 20, 0],
"bbox": [0, 0, 10, 20],
"bbox_label": 0,
"ignore": False,
"text": "mmocr"
},
// ...
]
}
]
}
"""
def pack_instance(self, sample: Tuple, bbox_label: int = 0) -> Dict:
"""Pack the parsed annotation info to an MMOCR format instance.
Args:
sample (Tuple): A tuple of (img_file, ann_file).
- img_path (str): Path to image file.
- instances (Sequence[Dict]): A list of converted annos. Each
element should be a dict with the following keys:
- 'poly' or 'box'
- 'text'
- 'ignore'
- 'bbox_label' (optional)
split (str): The split of the instance.
Returns:
Dict: An MMOCR format instance.
"""
img_path, instances = sample
img = mmcv.imread(img_path)
h, w = img.shape[:2]
packed_instances = list()
for instance in instances:
assert 'text' in instance, 'Text is not found in the instance.'
poly = instance.get('poly', None)
box = instance.get('box', None)
assert box or poly
packed_sample = dict(
polygon=poly if poly else list(
bbox2poly(box).astype('float64')),
bbox=box if box else list(poly2bbox(poly).astype('float64')),
bbox_label=bbox_label,
ignore=instance['ignore'],
text=instance['text'])
packed_instances.append(packed_sample)
packed_instances = dict(
instances=packed_instances,
img_path=osp.relpath(img_path, self.data_root),
height=h,
width=w)
return packed_instances
def add_meta(self, sample: List) -> Dict:
"""Add meta information to the sample.
Args:
sample (List): A list of samples of the dataset.
Returns:
Dict: A dict contains the meta information and samples.
"""
meta = {
'metainfo': {
'dataset_type': 'TextSpottingDataset',
'task_name': 'textspotting',
'category': [{
'id': 0,
'name': 'text'
}]
},
'data_list': sample
}
return meta
|