deepdoctection 0.39.4__py3-none-any.whl → 0.39.5__py3-none-any.whl

deepdoctection/__init__.py

@@ -25,7 +25,7 @@ from .utils.logger import LoggingRecord, logger
 
 # pylint: enable=wrong-import-position
 
-__version__ = "0.39.4"
+__version__ = "0.39.5"
 
 _IMPORT_STRUCTURE = {
     "analyzer": ["config_sanity_checks", "get_dd_analyzer", "ServiceFactory"],

deepdoctection/datapoint/image.py

@@ -702,11 +702,11 @@ class Image:
         return get_uuid(self.image_id, *container_ids)
 
     def save(
-            self,
-            image_to_json: bool = True,
-            highest_hierarchy_only: bool = False,
-            path: Optional[PathLikeOrStr] = None,
-            dry: bool = False,
+        self,
+        image_to_json: bool = True,
+        highest_hierarchy_only: bool = False,
+        path: Optional[PathLikeOrStr] = None,
+        dry: bool = False,
     ) -> Optional[Union[ImageDict, str]]:
         """
         Export image as dictionary. As numpy array cannot be serialized `image` values will be converted into
@@ -723,7 +723,7 @@ class Image:
         def set_image_keys_to_none(d):  # type: ignore
             if isinstance(d, dict):
                 for key, value in d.items():
-                    if key == '_image':
+                    if key == "_image":
                         d[key] = None
                     else:
                         set_image_keys_to_none(value)

deepdoctection/datapoint/view.py

@@ -430,8 +430,10 @@ class Table(Layout):
             category_names=[LayoutType.CELL, CellType.SPANNING], annotation_ids=all_relation_ids
         )
         column_cells = list(
-            filter(lambda c: column_number in  # type: ignore
-                             (c.column_number, c.column_number + c.column_span - 1), all_cells)  # type: ignore
+            filter(
+                lambda c: column_number in (c.column_number, c.column_number + c.column_span - 1),  # type: ignore
+                all_cells,
+            )  # type: ignore
         )
         column_cells.sort(key=lambda c: c.row_number)  # type: ignore
         return column_cells  # type: ignore

deepdoctection/datasets/base.py

@@ -394,6 +394,7 @@ class CustomDataset(DatasetBase):
         dataflow_builder: Type[DataFlowBaseBuilder],
         init_sub_categories: Optional[Mapping[ObjectTypes, Mapping[ObjectTypes, Sequence[ObjectTypes]]]] = None,
         annotation_files: Optional[Mapping[str, Union[str, Sequence[str]]]] = None,
+        description: Optional[str] = None,
     ):
         """
         :param name: Name of the dataset. It will not be used in the code, however it might be helpful, if several
@@ -422,6 +423,7 @@ class CustomDataset(DatasetBase):
         :param annotation_files: A mapping to one or more annotation files, e.g.
 
                                        annotation_file = {"train": "train_file.json", "test": "test_file.json"}
+        :param description: A description of the dataset.
         """
 
         self.name = name
@@ -439,10 +441,18 @@ class CustomDataset(DatasetBase):
                 "annotation_files: Optional[Mapping[str, Union[str, Sequence[str]]]] = None):`"
             )
         self.dataflow_builder = dataflow_builder(self.location, self.annotation_files)
+        self.description = description
         super().__init__()
 
     def _info(self) -> DatasetInfo:  # type: ignore  # pylint: disable=W0221
-        return DatasetInfo(name=self.name, type=self.type, description="", license="", url="", splits={})
+        return DatasetInfo(
+            name=self.name,
+            type=self.type,
+            description=self.description if self.description is not None else "",
+            license="",
+            url="",
+            splits={},
+        )
 
     def _categories(self) -> DatasetCategories:
         return DatasetCategories(init_categories=self.init_categories, init_sub_categories=self.init_sub_categories)

deepdoctection/datasets/info.py

@@ -85,6 +85,7 @@ class DatasetInfo:
     """
 
     name: str
+    short_description: str = field(default="")
     description: str = field(default="")
     license: str = field(default="")
     url: Union[str, Sequence[str]] = field(default="")

deepdoctection/datasets/instances/doclaynet.py

@@ -45,6 +45,7 @@ from ..info import DatasetCategories, DatasetInfo
 from ..registry import dataset_registry
 
 _NAME = "doclaynet"
+_SHORT_DESCRIPTION = "DocLayNet is a human-annotated document layout segmentation dataset containing 80863 pages."
 _DESCRIPTION = (
     "DocLayNet is a human-annotated document layout segmentation dataset containing 80863 pages from a broad "
     "variety of document sources. \n"
@@ -105,7 +106,15 @@ class DocLayNet(DatasetBase):
 
     @classmethod
     def _info(cls) -> DatasetInfo:
-        return DatasetInfo(name=_NAME, description=_DESCRIPTION, license=_LICENSE, splits=_SPLITS, type=_TYPE, url=_URL)
+        return DatasetInfo(
+            name=_NAME,
+            short_description=_SHORT_DESCRIPTION,
+            description=_DESCRIPTION,
+            license=_LICENSE,
+            splits=_SPLITS,
+            type=_TYPE,
+            url=_URL,
+        )
 
     def _categories(self) -> DatasetCategories:
         return DatasetCategories(init_categories=_INIT_CATEGORIES, init_sub_categories=_SUB_CATEGORIES)

deepdoctection/datasets/instances/fintabnet.py

@@ -54,6 +54,7 @@ from ..info import DatasetCategories, DatasetInfo
 from ..registry import dataset_registry
 
 _NAME = "fintabnet"
+_SHORT_DESCRIPTION = "FinTabNet dataset contains complex tables from the annual reports of S&P 500 companies."
 _DESCRIPTION = (
     "FinTabNet dataset contains complex tables from the annual reports of S&P 500 companies with detailed \n"
     " table structure annotations to help train and test structure recognition. \n"
@@ -129,7 +130,15 @@ class Fintabnet(_BuiltInDataset):
 
     @classmethod
     def _info(cls) -> DatasetInfo:
-        return DatasetInfo(name=_NAME, description=_DESCRIPTION, license=_LICENSE, url=_URL, splits=_SPLITS, type=_TYPE)
+        return DatasetInfo(
+            name=_NAME,
+            short_description=_SHORT_DESCRIPTION,
+            description=_DESCRIPTION,
+            license=_LICENSE,
+            url=_URL,
+            splits=_SPLITS,
+            type=_TYPE,
+        )
 
     def _categories(self) -> DatasetCategories:
         return DatasetCategories(init_categories=_INIT_CATEGORIES, init_sub_categories=_SUB_CATEGORIES)

deepdoctection/datasets/instances/funsd.py

@@ -66,6 +66,7 @@ def load_file(path_ann: PathLikeOrStr) -> FunsdDict:
 
 
 _NAME = "funsd"
+_SHORT_DESCRIPTION = "FUNSD: Form Understanding in Noisy Scanned Documents."
 _DESCRIPTION = (
     "FUNSD: Form Understanding in Noisy Scanned Documents. A dataset for Text Detection, Optical Character \n"
     " Recognition, Spatial Layout Analysis and Form Understanding."
@@ -116,7 +117,15 @@ class Funsd(_BuiltInDataset):
 
     @classmethod
     def _info(cls) -> DatasetInfo:
-        return DatasetInfo(name=_NAME, description=_DESCRIPTION, license=_LICENSE, url=_URL, splits=_SPLITS, type=_TYPE)
+        return DatasetInfo(
+            name=_NAME,
+            short_description=_SHORT_DESCRIPTION,
+            description=_DESCRIPTION,
+            license=_LICENSE,
+            url=_URL,
+            splits=_SPLITS,
+            type=_TYPE,
+        )
 
     def _categories(self) -> DatasetCategories:
         return DatasetCategories(init_categories=_INIT_CATEGORIES, init_sub_categories=_SUB_CATEGORIES)

deepdoctection/datasets/instances/iiitar13k.py

@@ -60,7 +60,7 @@ with try_import() as import_guard:
     from lxml import etree
 
 _NAME = "iiitar13k"
-
+_SHORT_DESCRIPTION = "IIIT-AR-13K: A New Dataset for Graphical Object Detection in Documents"
 _DESCRIPTION = (
     "[excerpt from Ajoy Mondal et. all. IIIT-AR-13K: A New Dataset for Graphical Object Detection in \n"
     "Documents] ...This dataset, IIIT-AR-13K, is created by manually annotating the bounding boxes of \n"
@@ -97,7 +97,15 @@ class IIITar13K(_BuiltInDataset):
 
     @classmethod
     def _info(cls) -> DatasetInfo:
-        return DatasetInfo(name=_NAME, description=_DESCRIPTION, license=_LICENSE, url=_URL, splits=_SPLITS, type=_TYPE)
+        return DatasetInfo(
+            name=_NAME,
+            short_description=_SHORT_DESCRIPTION,
+            description=_DESCRIPTION,
+            license=_LICENSE,
+            url=_URL,
+            splits=_SPLITS,
+            type=_TYPE,
+        )
 
     def _categories(self) -> DatasetCategories:
         return DatasetCategories(init_categories=_INIT_CATEGORIES)

deepdoctection/datasets/instances/layouttest.py

@@ -73,7 +73,14 @@ class LayoutTest(_BuiltInDataset):
 
     @classmethod
     def _info(cls) -> DatasetInfo:
-        return DatasetInfo(name=_NAME, description=_DESCRIPTION, license=_LICENSE, splits=_SPLITS, type=_TYPE)
+        return DatasetInfo(
+            name=_NAME,
+            short_description=_DESCRIPTION,
+            description=_DESCRIPTION,
+            license=_LICENSE,
+            splits=_SPLITS,
+            type=_TYPE,
+        )
 
     def _categories(self) -> DatasetCategories:
         return DatasetCategories(init_categories=_INIT_CATEGORIES)

deepdoctection/datasets/instances/publaynet.py

@@ -43,6 +43,7 @@ from ..info import DatasetCategories, DatasetInfo
 from ..registry import dataset_registry
 
 _NAME = "publaynet"
+_SHORT_DESCRIPTION = "PubLayNet is a dataset for document layout analysis."
 _DESCRIPTION = (
     "PubLayNet is a dataset for document layout analysis. It contains images of research papers and "
     "articles \n"
@@ -79,7 +80,15 @@ class Publaynet(_BuiltInDataset):
 
     @classmethod
     def _info(cls) -> DatasetInfo:
-        return DatasetInfo(name=_NAME, description=_DESCRIPTION, license=_LICENSE, url=_URL, splits=_SPLITS, type=_TYPE)
+        return DatasetInfo(
+            name=_NAME,
+            short_description=_SHORT_DESCRIPTION,
+            description=_DESCRIPTION,
+            license=_LICENSE,
+            url=_URL,
+            splits=_SPLITS,
+            type=_TYPE,
+        )
 
     def _categories(self) -> DatasetCategories:
         return DatasetCategories(init_categories=_INIT_CATEGORIES)

deepdoctection/datasets/instances/pubtables1m.py

@@ -63,7 +63,7 @@ with try_import() as import_guard:
     from lxml import etree
 
 _NAME = "pubtables1m_det"
-
+_SHORT_DESCRIPTION = "PubTables1M is a dataset for table detection and structure recognition."
 _DESCRIPTION = (
     "[excerpt from Brandon Smock et. all. PubTables-1M: Towards Comprehensive Table Extraction From Unstructured \n"
     "Documents] '...we release PubTables1M, a dataset of nearly one million tables from PubMed Central Open Access \n"
@@ -100,7 +100,15 @@ class Pubtables1MDet(_BuiltInDataset):
 
     @classmethod
     def _info(cls) -> DatasetInfo:
-        return DatasetInfo(name=_NAME, description=_DESCRIPTION, license=_LICENSE, url=_URL, splits=_SPLITS, type=_TYPE)
+        return DatasetInfo(
+            name=_NAME,
+            short_description=_SHORT_DESCRIPTION,
+            description=_DESCRIPTION,
+            license=_LICENSE,
+            url=_URL,
+            splits=_SPLITS,
+            type=_TYPE,
+        )
 
     def _categories(self) -> DatasetCategories:
         return DatasetCategories(init_categories=_INIT_CATEGORIES_DET)

deepdoctection/datasets/instances/pubtabnet.py

@@ -45,6 +45,7 @@ from ..info import DatasetCategories
 from ..registry import dataset_registry
 
 _NAME = "pubtabnet"
+_SHORT_DESCRIPTION = "PubTabNet is a dataset for image-based table recognition."
 _DESCRIPTION = (
     "PubTabNet is a large dataset for image-based table recognition, containing 568k+ images of \n"
     "tabular data annotated with the corresponding HTML representation of the tables. The table images \n"
@@ -115,7 +116,15 @@ class Pubtabnet(_BuiltInDataset):
 
     @classmethod
     def _info(cls) -> DatasetInfo:
-        return DatasetInfo(name=_NAME, description=_DESCRIPTION, license=_LICENSE, url=_URL, splits=_SPLITS, type=_TYPE)
+        return DatasetInfo(
+            name=_NAME,
+            short_description=_SHORT_DESCRIPTION,
+            description=_DESCRIPTION,
+            license=_LICENSE,
+            url=_URL,
+            splits=_SPLITS,
+            type=_TYPE,
+        )
 
     def _categories(self) -> DatasetCategories:
         return DatasetCategories(init_categories=_INIT_CATEGORIES, init_sub_categories=_SUB_CATEGORIES)

deepdoctection/datasets/instances/rvlcdip.py

@@ -48,6 +48,7 @@ from ..info import DatasetCategories, DatasetInfo
 from ..registry import dataset_registry
 
 _NAME = "rvl-cdip"
+_SHORT_DESCRIPTION = "RVL-CDIP is a dataset for document classification."
 _DESCRIPTION = (
     "The RVL-CDIP (Ryerson Vision Lab Complex Document Information Processing) dataset consists of 400, 000 gray- \n"
     "scale images in 16 classes, with 25, 000 images per class . There are 320, 000 training images, 40, 000  \n"
@@ -98,7 +99,15 @@ class Rvlcdip(_BuiltInDataset):
 
     @classmethod
     def _info(cls) -> DatasetInfo:
-        return DatasetInfo(name=_NAME, description=_DESCRIPTION, license=_LICENSE, url=_URL, splits=_SPLITS, type=_TYPE)
+        return DatasetInfo(
+            name=_NAME,
+            short_description=_SHORT_DESCRIPTION,
+            description=_DESCRIPTION,
+            license=_LICENSE,
+            url=_URL,
+            splits=_SPLITS,
+            type=_TYPE,
+        )
 
     def _categories(self) -> DatasetCategories:
         return DatasetCategories(init_categories=_INIT_CATEGORIES)

deepdoctection/datasets/instances/xfund.py

@@ -45,6 +45,7 @@ from ..info import DatasetCategories
 from ..registry import dataset_registry
 
 _NAME = "xfund"
+_SHORT_DESCRIPTION = "XFUND is a multilingual form understanding benchmark dataset."
 _DESCRIPTION = (
     "XFUND is a multilingual form understanding benchmark dataset that includes human-labeled forms with \n"
     "key-value pairs in 7 languages (Chinese, Japanese, Spanish, French, Italian, German, Portuguese)."
@@ -103,7 +104,15 @@ class Xfund(_BuiltInDataset):
 
     @classmethod
     def _info(cls) -> DatasetInfo:
-        return DatasetInfo(name=_NAME, description=_DESCRIPTION, license=_LICENSE, url=_URL, splits=_SPLITS, type=_TYPE)
+        return DatasetInfo(
+            name=_NAME,
+            short_description=_SHORT_DESCRIPTION,
+            description=_DESCRIPTION,
+            license=_LICENSE,
+            url=_URL,
+            splits=_SPLITS,
+            type=_TYPE,
+        )
 
     def _categories(self) -> DatasetCategories:
         return DatasetCategories(init_categories=_INIT_CATEGORIES, init_sub_categories=_SUB_CATEGORIES)

deepdoctection/datasets/registry.py

@@ -65,18 +65,33 @@ def print_dataset_infos(add_license: bool = True, add_info: bool = True) -> None
     data = dataset_registry.get_all()
     num_columns = min(6, len(data))
     infos = []
+
     for dataset in data.items():
         info = [dataset[0]]
+        ds = dataset[1]()
+        info.append(ds.dataset_info.type)
         if add_license:
-            info.append(dataset[1]._info().license)  # pylint: disable=W0212
+            info.append(ds.dataset_info.license)  # pylint: disable=W0212
         if add_info:
-            info.append(dataset[1]._info().description)  # pylint: disable=W0212
+            info.append(ds.dataset_info.short_description)  # pylint: disable=W0212
+        if ds.dataflow.categories is not None:  # pylint: disable=W0212
+            categories = "\n".join(ds.dataflow.categories.init_categories)  # Format categories as multi-line string
+            sub_categories = "\n".join(
+                f"{key}: {', '.join(values)}" for key, values in ds.dataflow.categories.init_sub_categories.items()
+            )  # Format sub-categories as multi-line string
+            info.append(categories)
+            info.append(sub_categories)
+        else:
+            info.append("")
+            info.append("")
         infos.append(info)
-    header = ["dataset"]
+
+    header = ["dataset", "type"]
     if add_license:
         header.append("license")
     if add_info:
         header.append("description")
+    header.append("categories")
     table = tabulate(
         infos, headers=header * (num_columns // 2), tablefmt="fancy_grid", stralign="left", numalign="left"
     )

deepdoctection/extern/doctrocr.py

@@ -527,8 +527,9 @@ class DocTrRotationTransformer(ImageTransformer):
         return viz_handler.rotate_image(np_img, specification.angle)  # type: ignore
 
     def predict(self, np_img: PixelValues) -> DetectionResult:
-        angle = estimate_orientation(np_img, n_ct=self.number_contours,
-                                     ratio_threshold_for_lines=self.ratio_threshold_for_lines)
+        angle = estimate_orientation(
+            np_img, n_ct=self.number_contours, ratio_threshold_for_lines=self.ratio_threshold_for_lines
+        )
         if angle < 0:
             angle += 360
         return DetectionResult(angle=round(angle, 2))

deepdoctection/mapper/cats.py

@@ -55,7 +55,7 @@ def cat_to_sub_cat(
         sub_cat = ann.get_sub_category(sub_cat_type)
         if sub_cat:
             ann.category_name = sub_cat.category_name
-            ann.category_id = categories_dict_names_as_key.get(ann.category_name,DEFAULT_CATEGORY_ID)
+            ann.category_id = categories_dict_names_as_key.get(ann.category_name, DEFAULT_CATEGORY_ID)
 
     return dp
 

{deepdoctection-0.39.4.dist-info → deepdoctection-0.39.5.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.2
 Name: deepdoctection
-Version: 0.39.4
+Version: 0.39.5
 Summary: Repository for Document AI
 Home-page: https://github.com/deepdoctection/deepdoctection
 Author: Dr. Janis Meyer

{deepdoctection-0.39.4.dist-info → deepdoctection-0.39.5.dist-info}/RECORD

@@ -1,4 +1,4 @@
-deepdoctection/__init__.py,sha256=4u3rGxdbvfFr1l6xzH6qO5MapLGspBv5XPhBGMeji_4,12754
+deepdoctection/__init__.py,sha256=MbRCNpP9rjZdSs27aZt1LScR-Z_MW-I3kKgnfa8WjlY,12754
 deepdoctection/py.typed,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 deepdoctection/analyzer/__init__.py,sha256=icClxrd20XutD6LxLgEPIWceSs4j_QfI3szCE-9BL2w,729
 deepdoctection/analyzer/_config.py,sha256=1rfvVrp7cI2YLzpahD77aa1tZ_KFAIQ21DM1NWhxYiI,5058
@@ -19,26 +19,26 @@ deepdoctection/datapoint/__init__.py,sha256=3K406GbOPhoEp8koVaSbMocmSsmWifnSZ1SP
 deepdoctection/datapoint/annotation.py,sha256=FEgz4COxVDfjic0gG7kS6iHnWLBIgFnquQ63Cbj2a4Y,22531
 deepdoctection/datapoint/box.py,sha256=UAdSnLexvFyg4KK1u9kXdJxhaWTwRxTU-cnQcvl37Q8,23410
 deepdoctection/datapoint/convert.py,sha256=gJbHY2V8nlMht1N5VdxTmWSsOeydpFPTJsaJHp6XGgE,7516
-deepdoctection/datapoint/image.py,sha256=dImZfJr72jS8yanZx1n70p4lIv0Qa21-qlUcj0DZcls,34060
-deepdoctection/datapoint/view.py,sha256=XPyhbBr2cGIKdAiISBVZWxNxlSvN8kmGsD9P0mfpEEE,50772
+deepdoctection/datapoint/image.py,sha256=uGmlgF6zGptvNowZTqf-io4hbd8aFFngAvQqgdEQ5Kw,34040
+deepdoctection/datapoint/view.py,sha256=mReVQHX1PFGEma5n1-yOrNhp0E6aHaDMOpgtdt7wsm8,50790
 deepdoctection/datasets/__init__.py,sha256=-A3aR90aDsHPmVM35JavfnQ2itYSCn3ujl4krRni1QU,1076
 deepdoctection/datasets/adapter.py,sha256=Ly_vbOAgVI73V41FUccnSX1ECTOyesW_qsuvQuvOZbw,7796
-deepdoctection/datasets/base.py,sha256=DT4i-d74sIEiUNC6UspIHNJuHSK0t1dBv7qwadg4rLw,22341
+deepdoctection/datasets/base.py,sha256=AZx-hw8Mchzb7FiOASt7zCbiybFNsM_diBzKXyC-auU,22618
 deepdoctection/datasets/dataflow_builder.py,sha256=cYU2zV3gZW2bFvMHimlO9VIl3BAUaCwML08cCIQ8Em4,4107
-deepdoctection/datasets/info.py,sha256=6y5TfiUhQppynbMFP5JmUPk95ggsVCtGIw4dYh2lVus,20501
-deepdoctection/datasets/registry.py,sha256=tvzMUk34ZD3AsedS1DFfYATYLxm-7bn2-8J1AJiXGKM,2616
+deepdoctection/datasets/info.py,sha256=sC1QCOdLWFMooVmiShZ43sLUpAi3FK4d0fsLyl_9-gA,20548
+deepdoctection/datasets/registry.py,sha256=j0dqdemhbQNccjZEI33uqeJH5mkHn6psKgKGX71IwVc,3277
 deepdoctection/datasets/save.py,sha256=Y9508Qqp8gIGN7pbGgVBBnkiC6NdCb9L2YR4wVvEUxM,3350
 deepdoctection/datasets/instances/__init__.py,sha256=XEc_4vT5lDn6bbZID9ujDEumWu8Ec2W-QS4pI_bfWWE,1388
-deepdoctection/datasets/instances/doclaynet.py,sha256=wRZT7wMTilZBLZ1gKY2cWReD1EGT735vOOTy0pD0N6M,12038
-deepdoctection/datasets/instances/fintabnet.py,sha256=qYzFK1dWF6MEPkHamP255DvAzlQT_GnkvDe1aM7CgjA,12006
-deepdoctection/datasets/instances/funsd.py,sha256=jxxpOq14-S0tX_IpUzKyKc6hWnKL4UUB-Bp7do3MPNY,6973
-deepdoctection/datasets/instances/iiitar13k.py,sha256=CKB9ZduKGBdHK3hiCKfAV7_s6PjEufHJUdj6H6JqED0,6697
-deepdoctection/datasets/instances/layouttest.py,sha256=CbaPKTA2103kMfOAsxGQkJT5xwlUJ104O4HA7Reo_MY,4400
-deepdoctection/datasets/instances/publaynet.py,sha256=aotY3O_W4fx_OVpkeKVukfeBTjiQm92gIaPW6FeGYHw,5238
-deepdoctection/datasets/instances/pubtables1m.py,sha256=UMomvs9X2d2aZhof9Rt42ud_PZyIfC-4j7oR39mTw1I,12297
-deepdoctection/datasets/instances/pubtabnet.py,sha256=l8qxbfKbXp7czJBHrUafK2hXz2qLpzL5Cbu_LsuvZQk,8592
-deepdoctection/datasets/instances/rvlcdip.py,sha256=bRcpE5XcNV0-7C8DHl0WNdzJzLFr6nOMaUU6xXSjeVs,6624
-deepdoctection/datasets/instances/xfund.py,sha256=AhAdaGhGQVL32WBbvThhXSwSy_WoP_Mv80azXU5oqLI,8784
+deepdoctection/datasets/instances/doclaynet.py,sha256=Az7USCqF0lMk1n1Dk59uUrBgBNAbKEjtUvZnCgdUH70,12286
+deepdoctection/datasets/instances/fintabnet.py,sha256=rOaKD5bruokkbZwjRhEz-5uAKZiMAXzmre_Ecc0YMTk,12250
+deepdoctection/datasets/instances/funsd.py,sha256=K6WQQOaEJrw1TcevScHET-AY9l9aj64dhLRyZ1J86p0,7183
+deepdoctection/datasets/instances/iiitar13k.py,sha256=HGBqR_PeTqpzLV9npWh5VdlHUg0t8vUTcrm3Z2kL6Qk,6923
+deepdoctection/datasets/instances/layouttest.py,sha256=nNYDUNcgWA0PilN0w0vAourwXvpcRupVStvlESTc1e0,4515
+deepdoctection/datasets/instances/publaynet.py,sha256=jUKq9iYW0qD5qXMe2xFz8xNxsL0KBTufuwSMkfzwaxA,5447
+deepdoctection/datasets/instances/pubtables1m.py,sha256=KtEHh8G98e-RjIqRbe5fbLNrD52oWA9kKDb3sUPqAk0,12524
+deepdoctection/datasets/instances/pubtabnet.py,sha256=TidllHJdxM8Ii0_gjliLWOWTtTaKjl89Khe1o0jLW4M,8806
+deepdoctection/datasets/instances/rvlcdip.py,sha256=8Vb_iCuR85N8Mx7d5KJ-lXe6PiZPjG0Jfq6EwY1qtkw,6831
+deepdoctection/datasets/instances/xfund.py,sha256=effTZfWI8MvGXCyRhdtwphHCr7WNF8sQOOjUCcKaTVE,9002
 deepdoctection/datasets/instances/xsl/__init__.py,sha256=TX_P6tqDOF1LK1mi9ruAl7x0mtv1Asm8cYWCz3Pe2dk,646
 deepdoctection/datasets/instances/xsl/pascal_voc.xsl,sha256=DlzFV2P8NtQKXVe96i-mIcPWmL6tsW7NQjgCuz2pCL4,1952
 deepdoctection/eval/__init__.py,sha256=rbns4tSEQ30QLj8h0mm3A0dCaKuN9LDxxpVypKKSXSE,932
@@ -53,7 +53,7 @@ deepdoctection/extern/__init__.py,sha256=9Iks9b4Q_LynjcV167TVCoK8YsQRUcA2jjmAmDN
 deepdoctection/extern/base.py,sha256=ONPgappl_P5HSwQr42FatuRnwMTvUPecPsCztDTN0Hw,24108
 deepdoctection/extern/d2detect.py,sha256=zrKv1yurApnjD7QZIZk_8LYCahjmN82MQUjHjv8zvkQ,22127
 deepdoctection/extern/deskew.py,sha256=sPoixu8S9he-0wbs-jgxtPE2V9BiP4-3uZlb6F5Y1SA,3077
-deepdoctection/extern/doctrocr.py,sha256=WrFA0N54fr9C_ahGzZJb4H-fNzz5wXQFveFiERYAm74,24637
+deepdoctection/extern/doctrocr.py,sha256=R1PgKBFxVr_1-frkGvGL2ZBS19jpiktPQ4sJz_nBiNs,24622
 deepdoctection/extern/fastlang.py,sha256=F4gK-SEwcCujjxH327ZDzMGWToJ49xS_dCKcePQ9IlY,4780
 deepdoctection/extern/hfdetr.py,sha256=JzHrrTyzS9qh6T2TsvKboAGZkIhno2txmSoLQ5Vd-lo,12077
 deepdoctection/extern/hflayoutlm.py,sha256=tFaf90FRbZzhSycdp8rGkeiPywQa6UcTEEwbayIXkr0,57023
@@ -88,7 +88,7 @@ deepdoctection/extern/tp/tpfrcnn/utils/__init__.py,sha256=kiPlXxHlTGN9eI7YE9Bgwt
 deepdoctection/extern/tp/tpfrcnn/utils/box_ops.py,sha256=aBLqPg_ApaiimtBRaOsLKTZZFIBh87vVtqjLPMaX9fQ,2379
 deepdoctection/extern/tp/tpfrcnn/utils/np_box_ops.py,sha256=O-q1GQiOEd1lN1MQDsJvHwD2OmBO-qHNeqJ1Qnec93g,3539
 deepdoctection/mapper/__init__.py,sha256=Xqb34aCjslZDQnqQgCSvnloL5DbdT9eHhn-StpVPbzE,1130
-deepdoctection/mapper/cats.py,sha256=Go9k9wiSid1aSPSteTCE0AgQ1tZmOA8pfOPkhKSQhhg,16601
+deepdoctection/mapper/cats.py,sha256=O06WGkpOIlSNMCy5VESl2HYOFDTuT9ls4aZIaWUv9VU,16602
 deepdoctection/mapper/cocostruct.py,sha256=GcbUpPFUg67pcOHQluWBFOFcGaYnlZcTmwBDERBVgCA,5978
 deepdoctection/mapper/d2struct.py,sha256=Dx-YnycsIQH4a5-9Gn_yMhiQ-gOFgMueNeH3rhXjuCU,8555
 deepdoctection/mapper/hfstruct.py,sha256=2PjGKsYturVJBimLT1CahYh09KSRAFEHz_QNtC162kQ,5551
@@ -141,8 +141,8 @@ deepdoctection/utils/transform.py,sha256=3kCgsEeRkG1efCdkfvj7tUFMs-e2jbjbflq826F
 deepdoctection/utils/types.py,sha256=_3dmPdCIZNLbgU5QP5k_c5phDf18xLe1kYL6t2nM45s,2953
 deepdoctection/utils/utils.py,sha256=csVs_VvCq4QBETPoE2JdTTL4MFYnD4xh-Js5vRb612g,6492
 deepdoctection/utils/viz.py,sha256=Jf8ePNYWlpuyaS6SeTYQ4OyA3eNhtgjvAQZnGNdgHC0,27051
-deepdoctection-0.39.4.dist-info/LICENSE,sha256=GQ0rUvuGdrMNEI3iHK5UQx6dIMU1QwAuyXsxUHn5MEQ,11351
-deepdoctection-0.39.4.dist-info/METADATA,sha256=9DvyyvO9Ofd9YFuqQ2SVO2Bi69WayBC2VZyrpMCimZQ,19741
-deepdoctection-0.39.4.dist-info/WHEEL,sha256=52BFRY2Up02UkjOa29eZOS2VxUrpPORXg1pkohGGUS8,91
-deepdoctection-0.39.4.dist-info/top_level.txt,sha256=hs2DdoOL9h4mnHhmO82BT4pz4QATIoOZ20PZmlnxFI8,15
-deepdoctection-0.39.4.dist-info/RECORD,,
+deepdoctection-0.39.5.dist-info/LICENSE,sha256=GQ0rUvuGdrMNEI3iHK5UQx6dIMU1QwAuyXsxUHn5MEQ,11351
+deepdoctection-0.39.5.dist-info/METADATA,sha256=O4KmPHyqhJ44FTeO5OLq1M-5dgBjAQM38ts55lemEiA,19741
+deepdoctection-0.39.5.dist-info/WHEEL,sha256=52BFRY2Up02UkjOa29eZOS2VxUrpPORXg1pkohGGUS8,91
+deepdoctection-0.39.5.dist-info/top_level.txt,sha256=hs2DdoOL9h4mnHhmO82BT4pz4QATIoOZ20PZmlnxFI8,15
+deepdoctection-0.39.5.dist-info/RECORD,,