deepdoctection 0.39.6__py3-none-any.whl → 0.40.0__py3-none-any.whl

deepdoctection/pipe/segment.py

@@ -436,24 +436,24 @@ def segment_table(
     child_ann_ids = table.get_relationship(Relationships.CHILD)
     cell_index_rows, row_index, _, _ = match_anns_by_intersection(
         dp,
-        item_names[0],
-        cell_names,
-        segment_rule,
-        threshold_rows,
-        True,
-        child_ann_ids,
-        child_ann_ids,
+        parent_ann_category_names=item_names[0],
+        child_ann_category_names=cell_names,
+        matching_rule=segment_rule,
+        threshold=threshold_rows,
+        use_weighted_intersections=True,
+        parent_ann_ids=child_ann_ids,
+        child_ann_ids=child_ann_ids,
     )
 
     cell_index_cols, col_index, _, _ = match_anns_by_intersection(
         dp,
-        item_names[1],
-        cell_names,
-        segment_rule,
-        threshold_cols,
-        True,
-        child_ann_ids,
-        child_ann_ids,
+        parent_ann_category_names=item_names[1],
+        child_ann_category_names=cell_names,
+        matching_rule=segment_rule,
+        threshold=threshold_cols,
+        use_weighted_intersections=True,
+        parent_ann_ids=child_ann_ids,
+        child_ann_ids=child_ann_ids,
     )
 
     cells = dp.get_annotation(annotation_ids=child_ann_ids, category_names=cell_names)
@@ -499,7 +499,6 @@ def create_intersection_cells(
     rows: Sequence[ImageAnnotation],
     cols: Sequence[ImageAnnotation],
     table_annotation_id: str,
-    cell_class_id: int,
     sub_item_names: Sequence[ObjectTypes],
 ) -> tuple[Sequence[DetectionResult], Sequence[SegmentationResult]]:
     """
@@ -509,7 +508,6 @@ def create_intersection_cells(
     :param rows: list of rows
     :param cols: list of columns
     :param table_annotation_id: annotation_id of underlying table ImageAnnotation
-    :param cell_class_id: The class_id to a synthetically generated DetectionResult
     :param sub_item_names: ObjectTypes for row-/column number
     :return: Pair of lists of `DetectionResult` and `SegmentationResult`.
     """
@@ -526,7 +524,6 @@ def create_intersection_cells(
             detect_result_cells.append(
                 DetectionResult(
                     box=boxes_cells[idx].to_list(mode="xyxy"),
-                    class_id=cell_class_id,
                     absolute_coords=boxes_cells[idx].absolute_coords,
                     class_name=LayoutType.CELL,
                 )
@@ -574,13 +571,13 @@ def header_cell_to_item_detect_result(
     child_ann_ids = table.get_relationship(Relationships.CHILD)
     item_index, _, items, _ = match_anns_by_intersection(
         dp,
-        item_header_name,
-        item_name,
-        segment_rule,
-        threshold,
-        True,
-        child_ann_ids,
-        child_ann_ids,
+        parent_ann_category_names=item_header_name,
+        child_ann_category_names=item_name,
+        matching_rule=segment_rule,
+        threshold=threshold,
+        use_weighted_intersections=True,
+        parent_ann_ids=child_ann_ids,
+        child_ann_ids=child_ann_ids,
     )
     item_headers = []
     for idx, item in enumerate(items):
@@ -622,24 +619,24 @@ def segment_pubtables(
     child_ann_ids = table.get_relationship(Relationships.CHILD)
     cell_index_rows, row_index, _, _ = match_anns_by_intersection(
         dp,
-        item_names[0],
-        spanning_cell_names,
-        segment_rule,
-        threshold_rows,
-        True,
-        child_ann_ids,
-        child_ann_ids,
+        parent_ann_category_names=item_names[0],
+        child_ann_category_names=spanning_cell_names,
+        matching_rule=segment_rule,
+        threshold=threshold_rows,
+        use_weighted_intersections=True,
+        parent_ann_ids=child_ann_ids,
+        child_ann_ids=child_ann_ids,
     )
 
     cell_index_cols, col_index, _, _ = match_anns_by_intersection(
         dp,
-        item_names[1],
-        spanning_cell_names,
-        segment_rule,
-        threshold_cols,
-        True,
-        child_ann_ids,
-        child_ann_ids,
+        parent_ann_category_names=item_names[1],
+        child_ann_category_names=spanning_cell_names,
+        matching_rule=segment_rule,
+        threshold=threshold_cols,
+        use_weighted_intersections=True,
+        parent_ann_ids=child_ann_ids,
+        child_ann_ids=child_ann_ids,
     )
 
     spanning_cells = dp.get_annotation(annotation_ids=child_ann_ids, category_names=spanning_cell_names)
@@ -976,7 +973,6 @@ class PubtablesSegmentationService(PipelineComponent):
         tile_table_with_items: bool,
         remove_iou_threshold_rows: float,
         remove_iou_threshold_cols: float,
-        cell_class_id: int,
         table_name: TypeOrStr,
         cell_names: Sequence[TypeOrStr],
         spanning_cell_names: Sequence[TypeOrStr],
@@ -997,7 +993,6 @@ class PubtablesSegmentationService(PipelineComponent):
                                       the adjacent row. Will do a similar shifting with columns.
         :param remove_iou_threshold_rows: iou threshold for removing overlapping rows
         :param remove_iou_threshold_cols: iou threshold for removing overlapping columns
-        :param cell_class_id: 'category_id' for cells to be generated from intersected rows and columns
         :param table_name: layout type table
         :param cell_names: layout type of cells
         :param spanning_cell_names: layout type of spanning cells
@@ -1022,7 +1017,6 @@ class PubtablesSegmentationService(PipelineComponent):
         self.spanning_cell_names = [get_type(cell_name) for cell_name in spanning_cell_names]
         self.remove_iou_threshold_rows = remove_iou_threshold_rows
         self.remove_iou_threshold_cols = remove_iou_threshold_cols
-        self.cell_class_id = cell_class_id
         self.cell_to_image = cell_to_image
         self.crop_cell_image = crop_cell_image
         self.item_names = [get_type(item_name) for item_name in item_names]  # row names must be before column name
@@ -1089,7 +1083,7 @@ class PubtablesSegmentationService(PipelineComponent):
             rows = dp.get_annotation(category_names=self.item_names[0], annotation_ids=item_ann_ids)
             columns = dp.get_annotation(category_names=self.item_names[1], annotation_ids=item_ann_ids)
             detect_result_cells, segment_result_cells = create_intersection_cells(
-                rows, columns, table.annotation_id, self.cell_class_id, self.sub_item_names
+                rows, columns, table.annotation_id, self.sub_item_names
             )
             cell_rn_cn_to_ann_id = {}
             for detect_result, segment_result in zip(detect_result_cells, segment_result_cells):
@@ -1228,7 +1222,6 @@ class PubtablesSegmentationService(PipelineComponent):
             self.tile_table,
             self.remove_iou_threshold_rows,
             self.remove_iou_threshold_cols,
-            self.cell_class_id,
             self.table_name,
             self.cell_names,
             self.spanning_cell_names,

deepdoctection/pipe/sub_layout.py

@@ -92,7 +92,6 @@ class DetectResultGenerator:
                         detect_result_list.append(
                             DetectionResult(
                                 box=[0.0, 0.0, float(self.width), float(self.height)],  # type: ignore
-                                class_id=self.categories_name_as_key[category_name],
                                 class_name=category_name,
                                 score=0.0,
                                 absolute_coords=self.absolute_coords,
@@ -123,7 +122,7 @@ class DetectResultGenerator:
         """
         sane_detect_results = []
         for detect_result in detect_result_list:
-            if detect_result.box:
+            if detect_result.box is not None:
                 ulx, uly, lrx, lry = detect_result.box
                 if ulx >= 0 and lrx - ulx >= 0 and uly >= 0 and lry - uly >= 0:
                     sane_detect_results.append(detect_result)
@@ -156,14 +155,13 @@ class SubImageLayoutService(PipelineComponent):
             detect_result_generator = DetectResultGenerator(categories_items)
             d_items = TPFrcnnDetector(item_config_path, item_weights_path, {"1": LayoutType.row,
             "2": LayoutType.column})
-            item_component = SubImageLayoutService(d_items, LayoutType.table, {1: 7, 2: 8}, detect_result_generator)
+            item_component = SubImageLayoutService(d_items, LayoutType.table, detect_result_generator)
     """
 
     def __init__(
         self,
         sub_image_detector: ObjectDetector,
         sub_image_names: Union[str, Sequence[TypeOrStr]],
-        category_id_mapping: Optional[dict[int, int]] = None,
         detect_result_generator: Optional[DetectResultGenerator] = None,
         padder: Optional[PadTransform] = None,
     ):
@@ -186,7 +184,6 @@ class SubImageLayoutService(PipelineComponent):
             if isinstance(sub_image_names, str)
             else tuple((get_type(cat) for cat in sub_image_names))
         )
-        self.category_id_mapping = category_id_mapping
         self.detect_result_generator = detect_result_generator
         self.padder = padder
         self.predictor = sub_image_detector
@@ -223,11 +220,6 @@ class SubImageLayoutService(PipelineComponent):
                 detect_result_list = self.detect_result_generator.create_detection_result(detect_result_list)
 
             for detect_result in detect_result_list:
-                if self.category_id_mapping:
-                    if detect_result.class_id:
-                        detect_result.class_id = self.category_id_mapping.get(
-                            detect_result.class_id, detect_result.class_id
-                        )
                 self.dp_manager.set_image_annotation(detect_result, sub_image_ann.annotation_id)
 
     def get_meta_annotation(self) -> MetaAnnotation:
@@ -254,7 +246,6 @@ class SubImageLayoutService(PipelineComponent):
         return self.__class__(
             predictor,
             self.sub_image_name,
-            self.category_id_mapping,
             self.detect_result_generator,
             padder_clone,
         )

deepdoctection/pipe/text.py

@@ -70,7 +70,6 @@ class TextExtractionService(PipelineComponent):
         text_extract_detector: Union[ObjectDetector, PdfMiner, TextRecognizer],
         extract_from_roi: Optional[Union[Sequence[TypeOrStr], TypeOrStr]] = None,
         run_time_ocr_language_selection: bool = False,
-        skip_if_text_extracted: bool = False,
     ):
         """
         :param text_extract_detector: ObjectDetector
@@ -79,8 +78,6 @@ class TextExtractionService(PipelineComponent):
                                                 multiple language selections. Also requires that a language detection
                                                 pipeline component ran before. It will select the expert language OCR
                                                 model based on the determined language.
-        :param skip_if_text_extracted: Set to `True` if text has already been extracted in a previous pipeline component
-                                       and should not be extracted again. Use-case: A PDF with some scanned images.
         """
 
         if extract_from_roi is None:
@@ -104,11 +101,6 @@ class TextExtractionService(PipelineComponent):
                 raise TypeError("Only TesseractOcrDetector supports multiple languages")
 
         self.run_time_ocr_language_selection = run_time_ocr_language_selection
-        self.skip_if_text_extracted = skip_if_text_extracted
-        if self.skip_if_text_extracted and isinstance(self.predictor, TextRecognizer):
-            raise ValueError(
-                "skip_if_text_extracted=True and TextRecognizer in TextExtractionService is not compatible"
-            )
 
     def serve(self, dp: Image) -> None:
         maybe_batched_text_rois = self.get_text_rois(dp)
@@ -154,11 +146,6 @@ class TextExtractionService(PipelineComponent):
         well `get_text_rois` will return an empty list.
         :return: list of ImageAnnotation or Image
         """
-        if self.skip_if_text_extracted:
-            text_categories = self.predictor.get_category_names()
-            text_anns = dp.get_annotation(category_names=text_categories)
-            if text_anns:
-                return []
 
         if self.extract_from_category:
             if self.predictor.accepts_batch:
@@ -223,7 +210,11 @@ class TextExtractionService(PipelineComponent):
         predictor = self.predictor.clone()
         if not isinstance(predictor, (ObjectDetector, PdfMiner, TextRecognizer)):
             raise ImageError(f"predictor must be of type ObjectDetector or PdfMiner, but is of type {type(predictor)}")
-        return self.__class__(predictor, deepcopy(self.extract_from_category), self.run_time_ocr_language_selection)
+        return self.__class__(
+            text_extract_detector=predictor,
+            extract_from_roi=deepcopy(self.extract_from_category),
+            run_time_ocr_language_selection=self.run_time_ocr_language_selection,
+        )
 
     def clear_predictor(self) -> None:
         self.predictor.clear_model()

deepdoctection/train/hf_detr_train.py

@@ -37,6 +37,8 @@ from ..extern.hfdetr import HFDetrDerivedDetector
 from ..mapper.hfstruct import DetrDataCollator, image_to_hf_detr_training
 from ..pipe.base import PipelineComponent
 from ..pipe.registry import pipeline_component_registry
+from ..utils.error import DependencyError
+from ..utils.file_utils import wandb_available
 from ..utils.logger import LoggingRecord, logger
 from ..utils.types import PathLikeOrStr
 from ..utils.utils import string_to_dict
@@ -56,6 +58,9 @@ with try_import() as hf_import_guard:
         TrainingArguments,
     )
 
+with try_import() as wb_import_guard:
+    import wandb
+
 
 class DetrDerivedTrainer(Trainer):
     """
@@ -74,16 +79,18 @@ class DetrDerivedTrainer(Trainer):
         args: TrainingArguments,
         data_collator: DetrDataCollator,
         train_dataset: DatasetAdapter,
+        eval_dataset: Optional[DatasetBase] = None,
     ):
         self.evaluator: Optional[Evaluator] = None
         self.build_eval_kwargs: Optional[dict[str, Any]] = None
-        super().__init__(model, args, data_collator, train_dataset)
+        super().__init__(model, args, data_collator, train_dataset, eval_dataset=eval_dataset)
 
     def setup_evaluator(
         self,
         dataset_val: DatasetBase,
         pipeline_component: PipelineComponent,
         metric: Union[Type[MetricBase], MetricBase],
+        run: Optional[wandb.sdk.wandb_run.Run] = None,
         **build_eval_kwargs: Union[str, int],
     ) -> None:
         """
@@ -93,10 +100,11 @@ class DetrDerivedTrainer(Trainer):
         :param dataset_val: dataset on which to run evaluation
         :param pipeline_component: pipeline component to plug into the evaluator
         :param metric: A metric class
+        :param run: WandB run
         :param build_eval_kwargs:
         """
 
-        self.evaluator = Evaluator(dataset_val, pipeline_component, metric, num_threads=1)
+        self.evaluator = Evaluator(dataset_val, pipeline_component, metric, num_threads=1, run=run)
         assert self.evaluator.pipe_component
         for comp in self.evaluator.pipe_component.pipe_components:
             comp.clear_predictor()
@@ -205,12 +213,19 @@ def train_hf_detr(
         "remove_unused_columns": False,
         "per_device_train_batch_size": 2,
         "max_steps": number_samples,
-        "evaluation_strategy": (
+        "eval_strategy": (
             "steps"
-            if (dataset_val is not None and metric is not None and pipeline_component_name is not None)
+            if (
+                dataset_val is not None
+                and (metric is not None or metric_name is not None)
+                and pipeline_component_name is not None
+            )
             else "no"
         ),
         "eval_steps": 5000,
+        "use_wandb": False,
+        "wandb_project": None,
+        "wandb_repo": "deepdoctection",
     }
 
     for conf in config_overwrite:
@@ -224,6 +239,23 @@ def train_hf_detr(
                 pass
         conf_dict[key] = val
 
+    use_wandb = conf_dict.pop("use_wandb")
+    wandb_project = str(conf_dict.pop("wandb_project"))
+    wandb_repo = str(conf_dict.pop("wandb_repo"))
+
+    # Initialize Wandb, if necessary
+    run = None
+    if use_wandb:
+        if not wandb_available():
+            raise DependencyError("WandB must be installed separately")
+        run = wandb.init(project=wandb_project, config=conf_dict)
+        run._label(repo=wandb_repo)  # pylint: disable=W0212
+        os.environ["WANDB_DISABLED"] = "False"
+        os.environ["WANDB_WATCH"] = "True"
+        os.environ["WANDB_PROJECT"] = wandb_project
+    else:
+        os.environ["WANDB_DISABLED"] = "True"
+
     # Will inform about dataloader warnings if max_steps exceeds length of dataset
     if conf_dict["max_steps"] > number_samples:  # type: ignore
         logger.warning(
@@ -232,7 +264,7 @@ def train_hf_detr(
             )
         )
 
-    arguments = TrainingArguments(**conf_dict)
+    arguments = TrainingArguments(**conf_dict)  # pylint: disable=E1123
     logger.info(LoggingRecord(f"Config: \n {arguments.to_dict()}", arguments.to_dict()))
 
     id2label = {int(k) - 1: v for v, k in categories_dict_name_as_key.items()}
@@ -240,6 +272,7 @@ def train_hf_detr(
         pretrained_model_name_or_path=path_config_json,
         num_labels=len(id2label),
     )
+    config.use_timm_backbone = True
 
     if path_weights != "":
         model = TableTransformerForObjectDetection.from_pretrained(
@@ -252,9 +285,9 @@ def train_hf_detr(
         pretrained_model_name_or_path=path_feature_extractor_config_json
     )
     data_collator = DetrDataCollator(feature_extractor)
-    trainer = DetrDerivedTrainer(model, arguments, data_collator, dataset)
+    trainer = DetrDerivedTrainer(model, arguments, data_collator, dataset, eval_dataset=dataset_val)
 
-    if arguments.evaluation_strategy in (IntervalStrategy.STEPS,):
+    if arguments.eval_strategy in (IntervalStrategy.STEPS,):
         categories = dataset_val.dataflow.categories.get_categories(filtered=True)  # type: ignore
         detector = HFDetrDerivedDetector(
             path_config_json, path_weights, path_feature_extractor_config_json, categories  # type: ignore
@@ -266,6 +299,6 @@ def train_hf_detr(
             metric = metric_registry.get(metric_name)
         assert metric is not None
 
-        trainer.setup_evaluator(dataset_val, pipeline_component, metric)  # type: ignore
+        trainer.setup_evaluator(dataset_val, pipeline_component, metric, run, **build_val_dict)  # type: ignore
 
     trainer.train()

deepdoctection/train/hf_layoutlm_train.py

@@ -395,7 +395,7 @@ def train_hf_layoutlm(
         "remove_unused_columns": False,
         "per_device_train_batch_size": 8,
         "max_steps": number_samples,
-        "evaluation_strategy": (
+        "eval_strategy": (
             "steps"
             if (dataset_val is not None and metric is not None and pipeline_component_name is not None)
             else "no"
@@ -475,7 +475,7 @@ def train_hf_layoutlm(
     )
     trainer = LayoutLMTrainer(model, arguments, data_collator, dataset, eval_dataset=dataset_val)
 
-    if arguments.evaluation_strategy in (IntervalStrategy.STEPS,):
+    if arguments.eval_strategy in (IntervalStrategy.STEPS,):
         assert metric is not None  # silence mypy
         if dataset_type == DatasetType.SEQUENCE_CLASSIFICATION:
             categories = dataset_val.dataflow.categories.get_categories(filtered=True)  # type: ignore

deepdoctection/utils/types.py

@@ -63,7 +63,7 @@ else:
 
 
 JsonDict = dict[str, Any]
-
+BoxCoordinate = Union[int, float]
 
 # Some common deepdoctection dict-types
 AnnotationDict: TypeAlias = dict[str, Any]

{deepdoctection-0.39.6.dist-info → deepdoctection-0.40.0.dist-info}/METADATA

@@ -1,6 +1,6 @@
-Metadata-Version: 2.2
+Metadata-Version: 2.4
 Name: deepdoctection
-Version: 0.39.6
+Version: 0.40.0
 Summary: Repository for Document AI
 Home-page: https://github.com/deepdoctection/deepdoctection
 Author: Dr. Janis Meyer
@@ -133,6 +133,7 @@ Dynamic: description
 Dynamic: description-content-type
 Dynamic: home-page
 Dynamic: license
+Dynamic: license-file
 Dynamic: provides-extra
 Dynamic: requires-dist
 Dynamic: requires-python

{deepdoctection-0.39.6.dist-info → deepdoctection-0.40.0.dist-info}/RECORD

@@ -1,9 +1,9 @@
-deepdoctection/__init__.py,sha256=F9uc6mjLFOYYGkT5UFs6M5YBxhcJlJ33G3-NSctzSF8,12754
+deepdoctection/__init__.py,sha256=Onsg4vkNNIGYytDmH96KsxYt3xQLxcAbyYHCeOqThR8,12780
 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
+deepdoctection/analyzer/_config.py,sha256=kxQzDQvl2ygH84VTnumbRF7JLGM6VeJoBzv1xssm6H4,5019
 deepdoctection/analyzer/dd.py,sha256=bfR7e1JV7BwUNDRLu0jYZU7qQXnyA_vbRAJl2Ylrq5o,5905
-deepdoctection/analyzer/factory.py,sha256=7L-bJ9957TBn_C6OGWJFmZobrh8MPq4Q-Espx5faEiY,32435
+deepdoctection/analyzer/factory.py,sha256=sXGL_faLkKCUBfq5YIpmzV5cWuvWChYy-zP5OtdaM4Y,33251
 deepdoctection/configs/__init__.py,sha256=TX_P6tqDOF1LK1mi9ruAl7x0mtv1Asm8cYWCz3Pe2dk,646
 deepdoctection/configs/conf_dd_one.yaml,sha256=qnrDAST1PHBtdIKE_hdkZexW22FqVvNTI-PEo9wvinM,3025
 deepdoctection/configs/conf_tesseract.yaml,sha256=oF6szDyoi15FHvq7yFUNIEjfA_jNLhGxoowiRsz_zY4,35
@@ -17,16 +17,16 @@ deepdoctection/dataflow/serialize.py,sha256=4pYC7m9h53JCu99waVeKpHDpsCDDdYCrSZpP
 deepdoctection/dataflow/stats.py,sha256=Bsr6v7lcesKXUYtO9wjqlzx_Yq_uyIF3Lel-tQ0i4wI,9619
 deepdoctection/datapoint/__init__.py,sha256=3K406GbOPhoEp8koVaSbMocmSsmWifnSZ1SPb7C1lOY,1643
 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=uGmlgF6zGptvNowZTqf-io4hbd8aFFngAvQqgdEQ5Kw,34040
-deepdoctection/datapoint/view.py,sha256=sK6Ta9R6jdOS7iwF05-uPjL2wSz8wHQ5RIGCatw7i2M,50774
+deepdoctection/datapoint/box.py,sha256=XPhC_xHqLZJjzafg1pIS_CxnVB5-0_yk-twsZZ3ncUU,30093
+deepdoctection/datapoint/convert.py,sha256=Be2FvmRXt-5prZ1vwa5fG6VjgEQ_31hiQ13hAoXoaes,7740
+deepdoctection/datapoint/image.py,sha256=_jN46UJUsOi6GC6VEUcp3L_vLL-iYRW05RKcFLWb6Dc,34048
+deepdoctection/datapoint/view.py,sha256=iZiHMc2hkk6vWn87LK0Qf-toZU_kocW3m7Wq8M4IS2E,50782
 deepdoctection/datasets/__init__.py,sha256=-A3aR90aDsHPmVM35JavfnQ2itYSCn3ujl4krRni1QU,1076
 deepdoctection/datasets/adapter.py,sha256=Ly_vbOAgVI73V41FUccnSX1ECTOyesW_qsuvQuvOZbw,7796
 deepdoctection/datasets/base.py,sha256=AZx-hw8Mchzb7FiOASt7zCbiybFNsM_diBzKXyC-auU,22618
 deepdoctection/datasets/dataflow_builder.py,sha256=cYU2zV3gZW2bFvMHimlO9VIl3BAUaCwML08cCIQ8Em4,4107
 deepdoctection/datasets/info.py,sha256=sC1QCOdLWFMooVmiShZ43sLUpAi3FK4d0fsLyl_9-gA,20548
-deepdoctection/datasets/registry.py,sha256=K6ZHCSIHuElOMWWN_KJjicHP-BUhNWBHBSOFbCGuvRg,3388
+deepdoctection/datasets/registry.py,sha256=utiB-PnE6vc5HvjcudO0O4Urp2BC3snqswY6d8uPQAo,3388
 deepdoctection/datasets/save.py,sha256=Y9508Qqp8gIGN7pbGgVBBnkiC6NdCb9L2YR4wVvEUxM,3350
 deepdoctection/datasets/instances/__init__.py,sha256=XEc_4vT5lDn6bbZID9ujDEumWu8Ec2W-QS4pI_bfWWE,1388
 deepdoctection/datasets/instances/doclaynet.py,sha256=Az7USCqF0lMk1n1Dk59uUrBgBNAbKEjtUvZnCgdUH70,12286
@@ -94,7 +94,7 @@ deepdoctection/mapper/d2struct.py,sha256=Dx-YnycsIQH4a5-9Gn_yMhiQ-gOFgMueNeH3rhX
 deepdoctection/mapper/hfstruct.py,sha256=2PjGKsYturVJBimLT1CahYh09KSRAFEHz_QNtC162kQ,5551
 deepdoctection/mapper/laylmstruct.py,sha256=abMZkYU2W0e_VcCm_c0ZXNFuv-lfMFWcTedcZS5EYvE,42935
 deepdoctection/mapper/maputils.py,sha256=eI6ZcDg9W5uB6xQNBZpMIdEd86HlCxTtkJuyROdTqiw,8146
-deepdoctection/mapper/match.py,sha256=Ed9FsuVPNp_faaW5PKnvUHZoEXcRcrO-muduTMzjp1s,8937
+deepdoctection/mapper/match.py,sha256=RDTYSGtbtT8ph3L83PyHIkezJ2K82MwNerSM72uTMxM,10267
 deepdoctection/mapper/misc.py,sha256=vX-fV420Te00eD-cqTiWBV2twHqdBcBV2_7rAFRgPRg,7164
 deepdoctection/mapper/pascalstruct.py,sha256=TzVU1p0oiw0nOuxTFFbEB9vXJxH1v6VUvTJ7MD0manU,3828
 deepdoctection/mapper/prodigystruct.py,sha256=Re4Sd_zAp6qOvbXZLmMJeG0IGEfMQxebuyDeZgMcTa8,6827
@@ -102,25 +102,25 @@ deepdoctection/mapper/pubstruct.py,sha256=PAJ2N1HSPNS6F2ZrIwlD7PiBhIM-rJscK_Ti8O
 deepdoctection/mapper/tpstruct.py,sha256=YNABRibvcISD5Lavg3jouoE4FMdqXEJoM-hNoB_rnww,4481
 deepdoctection/mapper/xfundstruct.py,sha256=_3r3c0K82fnF2h1HxA85h-9ETYrHwcERa6MNc6Ko6Z8,8807
 deepdoctection/pipe/__init__.py,sha256=ywTVoetftdL6plXg2YlBzMfmqBZupq7yXblSVyvvkcQ,1127
-deepdoctection/pipe/anngen.py,sha256=3319l4aaXzcY4w6ItVBNPX8LGS5fHFDVtyVY9KMefac,16393
+deepdoctection/pipe/anngen.py,sha256=7wvp7eghDwrgcIyu1vjRxmVy4SADPbn-k4ud8y2bgjU,15338
 deepdoctection/pipe/base.py,sha256=wlza9aDOKnHKrXmaz8MLyLz0nMqqcIWQ-6Lu944aicE,15390
-deepdoctection/pipe/common.py,sha256=C1KxEfJFSPeDqlnkiJ1ZYPuA36P8BU_4jVhdsszW_V8,17752
+deepdoctection/pipe/common.py,sha256=S6-NKvR0sqBfqjN-mH76uVgM_aHOZvhPe_ore36UPZA,21028
 deepdoctection/pipe/concurrency.py,sha256=AAKRsVgaBEYNluntbDa46SBF1JZ_XqnWLDSWrNvAzEo,9657
 deepdoctection/pipe/doctectionpipe.py,sha256=bGW3ugky-fb-nEe-3bvO6Oc_4_6w82cQboGM_6p2eIo,12530
 deepdoctection/pipe/language.py,sha256=5zI0UQC6Fh12_r2pfVL42HoCGz2hpHrOhpXAn5m-rYw,5451
-deepdoctection/pipe/layout.py,sha256=xIhnJpyUSbvLbhTXyAKXY1hmG9352jihGYFSclTH_1g,5567
+deepdoctection/pipe/layout.py,sha256=ThULc0b1f9KyaXYk9z0qbuJ0nhIodah9PcrEq2xKpAY,5670
 deepdoctection/pipe/lm.py,sha256=x9NoYpivdjQF1r76a7PPrUuBEmuHP7ZukuXFDkXhXBc,17572
-deepdoctection/pipe/order.py,sha256=PnJZiCnxFluJiECXLTZT0c1Rr66vIRBFraa_G41UA2k,40121
+deepdoctection/pipe/order.py,sha256=0KNiMinedjfuDVVHxJSaDL1yl4Sub-miMPcEC4gGwPA,39423
 deepdoctection/pipe/refine.py,sha256=dTfI396xydPdbzpfo4yqFcuxl3UAB1y-WbSQn1o76ec,22367
 deepdoctection/pipe/registry.py,sha256=aFx-Tn0xhVA5l5H18duNW5QoTNKQltybsEUEzsMgUfg,902
-deepdoctection/pipe/segment.py,sha256=mWYRg7UR80PtIj1SIg_hiujDcCtLlvKJUP9vx4ZpW0Y,59318
-deepdoctection/pipe/sub_layout.py,sha256=N1RcID-boORcwsW_j0l64HpUu3rff0ge5qEanudLYgk,13838
-deepdoctection/pipe/text.py,sha256=h9q6d3HFOs7LOg-iwdLUPiQxrPqgunBVNmtYMBrfRQE,11180
+deepdoctection/pipe/segment.py,sha256=sny59GuP7dxLGX3YjHF0wllPxSiXL1GNQEhMGKcF8ZU,59594
+deepdoctection/pipe/sub_layout.py,sha256=OLKvCYJynoFpo7bf2b3HzY0k-TJDLc0PHveWKcDbqZI,13324
+deepdoctection/pipe/text.py,sha256=tLlJtneM__WsrAvp4pQFqwNlmq2RLqKqiPXlJ2lkniU,10483
 deepdoctection/pipe/transform.py,sha256=9Om7X7hJeL4jgUwHM1CHa4sb5v7Qo1PtVG0ls_3nI7w,3798
 deepdoctection/train/__init__.py,sha256=YFTRAZF1F7cEAKTdAIi1BLyYb6rSRcwq09Ui5Lu8d6E,1071
 deepdoctection/train/d2_frcnn_train.py,sha256=sFc_G-mEpaM8d1CCE0_6Gl4nBh11X2RYRBA3p_ylFJQ,16000
-deepdoctection/train/hf_detr_train.py,sha256=eHSdI11U8oGy93noZxAISfukhRBElj4dBerJ4Xcercw,10785
-deepdoctection/train/hf_layoutlm_train.py,sha256=DTPJZYKeDdRtDpcObYh93uh5D4sgT4c0ckHiAknCroY,22568
+deepdoctection/train/hf_detr_train.py,sha256=uBkkRyxrJF5UF__KbYvIlmb-HRWQ9TY6LiJr1Rm56kI,12043
+deepdoctection/train/hf_layoutlm_train.py,sha256=8kiGp_8GEyqCkLgeMgCJOLJWSVoKWkUBHsZtDjZOcRk,22556
 deepdoctection/train/tp_frcnn_train.py,sha256=pEpXokSVGveqo82pRnhnAmHPmjQ_8wQWpqM4ZyNHJgs,13049
 deepdoctection/utils/__init__.py,sha256=brBceRWeov9WXMiJTjyJOF2rHMP8trGGRRjhMdZ61nI,2371
 deepdoctection/utils/concurrency.py,sha256=nIhpkSncmv0LBB8PtcOLY-BsRGlfcDpz7foVdgzZd20,4598
@@ -138,11 +138,11 @@ deepdoctection/utils/pdf_utils.py,sha256=Fi0eZ2GbnO7N61Rd8b8YRKRff4dalHAzkcn3zpG
 deepdoctection/utils/settings.py,sha256=hDD6yDX_4pQXwR5ILVwJIj6hb7NXA0-ifnC25ldcUjA,12464
 deepdoctection/utils/tqdm.py,sha256=cBUtR0L1x0KMeYrLP2rrzyzCamCjpQAKroHXLv81_pk,1820
 deepdoctection/utils/transform.py,sha256=3kCgsEeRkG1efCdkfvj7tUFMs-e2jbjbflq826F2GPU,8502
-deepdoctection/utils/types.py,sha256=_3dmPdCIZNLbgU5QP5k_c5phDf18xLe1kYL6t2nM45s,2953
+deepdoctection/utils/types.py,sha256=ti4WdtIJSg3TGK_YPkkoY9PYGMnR2tTX6Xfik8U1pNk,2986
 deepdoctection/utils/utils.py,sha256=csVs_VvCq4QBETPoE2JdTTL4MFYnD4xh-Js5vRb612g,6492
 deepdoctection/utils/viz.py,sha256=Jf8ePNYWlpuyaS6SeTYQ4OyA3eNhtgjvAQZnGNdgHC0,27051
-deepdoctection-0.39.6.dist-info/LICENSE,sha256=GQ0rUvuGdrMNEI3iHK5UQx6dIMU1QwAuyXsxUHn5MEQ,11351
-deepdoctection-0.39.6.dist-info/METADATA,sha256=ezZIfdIjMmVp_60jLqco8OMeHQG_ksT4zEhflFLB5tI,19741
-deepdoctection-0.39.6.dist-info/WHEEL,sha256=beeZ86-EfXScwlR_HKu4SllMC9wUEj_8Z_4FJ3egI2w,91
-deepdoctection-0.39.6.dist-info/top_level.txt,sha256=hs2DdoOL9h4mnHhmO82BT4pz4QATIoOZ20PZmlnxFI8,15
-deepdoctection-0.39.6.dist-info/RECORD,,
+deepdoctection-0.40.0.dist-info/licenses/LICENSE,sha256=GQ0rUvuGdrMNEI3iHK5UQx6dIMU1QwAuyXsxUHn5MEQ,11351
+deepdoctection-0.40.0.dist-info/METADATA,sha256=YyPBlJBcUfAQP_cW7Mhq3eNs2-924o4BMS4X6Sn0Xwo,19763
+deepdoctection-0.40.0.dist-info/WHEEL,sha256=CmyFI0kx5cdEMTLiONQRbGQwjIoR1aIYB7eCAQ4KPJ0,91
+deepdoctection-0.40.0.dist-info/top_level.txt,sha256=hs2DdoOL9h4mnHhmO82BT4pz4QATIoOZ20PZmlnxFI8,15
+deepdoctection-0.40.0.dist-info/RECORD,,

{deepdoctection-0.39.6.dist-info → deepdoctection-0.40.0.dist-info}/WHEEL

@@ -1,5 +1,5 @@
 Wheel-Version: 1.0
-Generator: setuptools (76.1.0)
+Generator: setuptools (78.1.0)
 Root-Is-Purelib: true
 Tag: py3-none-any