deepdoctection 0.39.3__tar.gz → 0.39.5__tar.gz

{deepdoctection-0.39.3 → deepdoctection-0.39.5}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.2
 Name: deepdoctection
-Version: 0.39.3
+Version: 0.39.5
 Summary: Repository for Document AI
 Home-page: https://github.com/deepdoctection/deepdoctection
 Author: Dr. Janis Meyer
@@ -57,7 +57,7 @@ Requires-Dist: tensorpack==0.11; extra == "tf"
 Requires-Dist: protobuf==3.20.1; extra == "tf"
 Requires-Dist: tensorflow-addons>=0.17.1; extra == "tf"
 Requires-Dist: tf2onnx>=1.9.2; extra == "tf"
-Requires-Dist: python-doctr==0.8.1; extra == "tf"
+Requires-Dist: python-doctr==0.9.0; extra == "tf"
 Requires-Dist: pycocotools>=2.0.2; extra == "tf"
 Requires-Dist: boto3==1.34.102; extra == "tf"
 Requires-Dist: pdfplumber>=0.11.0; extra == "tf"
@@ -88,7 +88,7 @@ Requires-Dist: tqdm==4.64.0; extra == "pt"
 Requires-Dist: timm>=0.9.16; extra == "pt"
 Requires-Dist: transformers>=4.48.0; extra == "pt"
 Requires-Dist: accelerate>=0.29.1; extra == "pt"
-Requires-Dist: python-doctr==0.8.1; extra == "pt"
+Requires-Dist: python-doctr==0.9.0; extra == "pt"
 Requires-Dist: boto3==1.34.102; extra == "pt"
 Requires-Dist: pdfplumber>=0.11.0; extra == "pt"
 Requires-Dist: fasttext-wheel; extra == "pt"

{deepdoctection-0.39.3 → deepdoctection-0.39.5}/deepdoctection/__init__.py

@@ -25,7 +25,7 @@ from .utils.logger import LoggingRecord, logger
 
 # pylint: enable=wrong-import-position
 
-__version__ = "0.39.3"
+__version__ = "0.39.5"
 
 _IMPORT_STRUCTURE = {
     "analyzer": ["config_sanity_checks", "get_dd_analyzer", "ServiceFactory"],

{deepdoctection-0.39.3 → deepdoctection-0.39.5}/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-0.39.3 → deepdoctection-0.39.5}/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-0.39.3 → deepdoctection-0.39.5}/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-0.39.3 → deepdoctection-0.39.5}/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-0.39.3 → deepdoctection-0.39.5}/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-0.39.3 → deepdoctection-0.39.5}/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-0.39.3 → deepdoctection-0.39.5}/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-0.39.3 → deepdoctection-0.39.5}/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-0.39.3 → deepdoctection-0.39.5}/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-0.39.3 → deepdoctection-0.39.5}/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-0.39.3 → deepdoctection-0.39.5}/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-0.39.3 → deepdoctection-0.39.5}/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-0.39.3 → deepdoctection-0.39.5}/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-0.39.3 → deepdoctection-0.39.5}/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-0.39.3 → deepdoctection-0.39.5}/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-0.39.3 → deepdoctection-0.39.5}/deepdoctection/extern/doctrocr.py

@@ -79,8 +79,8 @@ def _load_model(
         state_dict = torch.load(os.fspath(path_weights), map_location=device)
         for key in list(state_dict.keys()):
             state_dict["model." + key] = state_dict.pop(key)
-        doctr_predictor.load_state_dict(state_dict)
-        doctr_predictor.to(device)
+        doctr_predictor.load_state_dict(state_dict)  # type: ignore
+        doctr_predictor.to(device)  # type: ignore
     elif lib == "TF":
         # Unzip the archive
         params_path = Path(path_weights).parent
@@ -88,9 +88,9 @@ def _load_model(
         if is_zip_path:
             with ZipFile(path_weights, "r") as file:
                 file.extractall(path=params_path)
-                doctr_predictor.model.load_weights(params_path / "weights")
+                doctr_predictor.model.load_weights(params_path / "weights")  # type: ignore
         else:
-            doctr_predictor.model.load_weights(os.fspath(path_weights))
+            doctr_predictor.model.load_weights(os.fspath(path_weights))  # type: ignore
 
 
 def auto_select_lib_for_doctr() -> Literal["PT", "TF"]:
@@ -125,7 +125,7 @@ def doctr_predict_text_lines(
         DetectionResult(
             box=box[:4].tolist(), class_id=1, score=box[4], absolute_coords=False, class_name=LayoutType.WORD
         )
-        for box in raw_output[0]["words"]
+        for box in raw_output[0]["words"]  # type: ignore
     ]
     return detection_results
 
@@ -480,7 +480,7 @@ class DoctrTextRecognizer(TextRecognizer):
         return auto_select_lib_for_doctr()
 
     def clear_model(self) -> None:
-        self.doctr_predictor = None
+        self.doctr_predictor = None  # type: ignore
 
 
 class DocTrRotationTransformer(ImageTransformer):
@@ -527,7 +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, self.number_contours, 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-0.39.3 → deepdoctection-0.39.5}/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-0.39.3 → deepdoctection-0.39.5}/deepdoctection.egg-info/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.2
 Name: deepdoctection
-Version: 0.39.3
+Version: 0.39.5
 Summary: Repository for Document AI
 Home-page: https://github.com/deepdoctection/deepdoctection
 Author: Dr. Janis Meyer
@@ -57,7 +57,7 @@ Requires-Dist: tensorpack==0.11; extra == "tf"
 Requires-Dist: protobuf==3.20.1; extra == "tf"
 Requires-Dist: tensorflow-addons>=0.17.1; extra == "tf"
 Requires-Dist: tf2onnx>=1.9.2; extra == "tf"
-Requires-Dist: python-doctr==0.8.1; extra == "tf"
+Requires-Dist: python-doctr==0.9.0; extra == "tf"
 Requires-Dist: pycocotools>=2.0.2; extra == "tf"
 Requires-Dist: boto3==1.34.102; extra == "tf"
 Requires-Dist: pdfplumber>=0.11.0; extra == "tf"
@@ -88,7 +88,7 @@ Requires-Dist: tqdm==4.64.0; extra == "pt"
 Requires-Dist: timm>=0.9.16; extra == "pt"
 Requires-Dist: transformers>=4.48.0; extra == "pt"
 Requires-Dist: accelerate>=0.29.1; extra == "pt"
-Requires-Dist: python-doctr==0.8.1; extra == "pt"
+Requires-Dist: python-doctr==0.9.0; extra == "pt"
 Requires-Dist: boto3==1.34.102; extra == "pt"
 Requires-Dist: pdfplumber>=0.11.0; extra == "pt"
 Requires-Dist: fasttext-wheel; extra == "pt"

{deepdoctection-0.39.3 → deepdoctection-0.39.5}/deepdoctection.egg-info/requires.txt

@@ -69,7 +69,7 @@ tqdm==4.64.0
 timm>=0.9.16
 transformers>=4.48.0
 accelerate>=0.29.1
-python-doctr==0.8.1
+python-doctr==0.9.0
 boto3==1.34.102
 pdfplumber>=0.11.0
 fasttext-wheel
@@ -105,7 +105,7 @@ tensorpack==0.11
 protobuf==3.20.1
 tensorflow-addons>=0.17.1
 tf2onnx>=1.9.2
-python-doctr==0.8.1
+python-doctr==0.9.0
 pycocotools>=2.0.2
 boto3==1.34.102
 pdfplumber>=0.11.0

{deepdoctection-0.39.3 → deepdoctection-0.39.5}/setup.py

@@ -89,7 +89,7 @@ _DEPS = [
     "pdfplumber>=0.11.0",
     "tensorflow-addons>=0.17.1",
     "tf2onnx>=1.9.2",
-    "python-doctr==0.8.1",
+    "python-doctr==0.9.0",
     "fasttext-wheel",
     # dev dependencies
     "python-dotenv==1.0.0",