deepdoctection 0.30__py3-none-any.whl → 0.31__py3-none-any.whl

deepdoctection/pipe/language.py

@@ -25,6 +25,7 @@ from ..datapoint.image import Image
 from ..datapoint.view import Page
 from ..extern.base import LanguageDetector, ObjectDetector
 from ..utils.detection_types import JsonDict
+from ..utils.error import ImageError
 from ..utils.settings import PageType, TypeOrStr, get_type
 from .base import PipelineComponent
 from .registry import pipeline_component_registry
@@ -86,7 +87,7 @@ class LanguageDetectionService(PipelineComponent):
             text = page.text_no_line_break
         else:
             if dp.image is None:
-                raise ValueError("dp.image cannot be None")
+                raise ImageError("image cannot be None")
             detect_result_list = self.text_detector.predict(dp.image)
             # this is a concatenation of all detection result. No reading order
             text = " ".join([result.text for result in detect_result_list if result.text is not None])
@@ -98,7 +99,7 @@ class LanguageDetectionService(PipelineComponent):
     def clone(self) -> PipelineComponent:
         predictor = self.predictor.clone()
         if not isinstance(predictor, LanguageDetector):
-            raise ValueError(f"Predictor must be of type LanguageDetector, but is of type {type(predictor)}")
+            raise TypeError(f"Predictor must be of type LanguageDetector, but is of type {type(predictor)}")
         return self.__class__(
             predictor,
             copy(self.text_container),

deepdoctection/pipe/layout.py

@@ -25,6 +25,7 @@ import numpy as np
 from ..datapoint.image import Image
 from ..extern.base import ObjectDetector, PdfMiner
 from ..utils.detection_types import JsonDict
+from ..utils.error import ImageError
 from ..utils.transform import PadTransform
 from .base import PredictorPipelineComponent
 from .registry import pipeline_component_registry
@@ -79,7 +80,7 @@ class ImageLayoutService(PredictorPipelineComponent):
             if anns:
                 return
         if dp.image is None:
-            raise ValueError("image cannot be None")
+            raise ImageError("image cannot be None")
         np_image = dp.image
         if self.padder:
             np_image = self.padder.apply_image(np_image)
@@ -114,5 +115,5 @@ class ImageLayoutService(PredictorPipelineComponent):
         if self.padder:
             padder_clone = self.padder.clone()
         if not isinstance(predictor, ObjectDetector):
-            raise ValueError(f"predictor must be of type ObjectDetector, but is of type {type(predictor)}")
+            raise TypeError(f"predictor must be of type ObjectDetector, but is of type {type(predictor)}")
         return self.__class__(predictor, self.to_image, self.crop_image, padder_clone, self.skip_if_layout_extracted)

deepdoctection/pipe/lm.py

@@ -252,7 +252,7 @@ class LMTokenClassifierService(LanguageModelPipelineComponent):
             self.language_model.model.__class__.__name__, use_xlm_tokenizer
         )
         if not isinstance(self.tokenizer, type(tokenizer_reference)):
-            raise ValueError(
+            raise TypeError(
                 f"You want to use {type(self.tokenizer)} but you should use {type(tokenizer_reference)} "
                 f"in this framework"
             )
@@ -366,7 +366,7 @@ class LMSequenceClassifierService(LanguageModelPipelineComponent):
             self.language_model.model.__class__.__name__, use_xlm_tokenizer
         )
         if not isinstance(self.tokenizer, type(tokenizer_reference)):
-            raise ValueError(
+            raise TypeError(
                 f"You want to use {type(self.tokenizer)} but you should use {type(tokenizer_reference)} "
                 f"in this framework"
             )

deepdoctection/pipe/refine.py

@@ -33,6 +33,7 @@ from ..datapoint.image import Image
 from ..extern.base import DetectionResult
 from ..mapper.maputils import MappingContextManager
 from ..utils.detection_types import JsonDict
+from ..utils.error import AnnotationError, ImageError
 from ..utils.settings import CellType, LayoutType, Relationships, TableType, get_type
 from .base import PipelineComponent
 from .registry import pipeline_component_registry
@@ -302,7 +303,7 @@ def generate_html_string(table: ImageAnnotation) -> List[str]:
     :return: HTML representation of the table
     """
     if table.image is None:
-        raise ValueError("table.image cannot be None")
+        raise ImageError("table.image cannot be None")
     table_image = table.image
     cells = table_image.get_annotation(
         category_names=[
@@ -412,7 +413,7 @@ class TableSegmentationRefinementService(PipelineComponent):
         tables = dp.get_annotation(category_names=self._table_name)
         for table in tables:
             if table.image is None:
-                raise ValueError("table.image cannot be None")
+                raise ImageError("table.image cannot be None")
             tiles_to_cells_list = tiles_to_cells(dp, table)
             connected_components, tile_to_cell_dict = connected_component_tiles(tiles_to_cells_list)
             rectangle_tiling = generate_rectangle_tiling(connected_components)
@@ -464,14 +465,21 @@ class TableSegmentationRefinementService(PipelineComponent):
             max_col_span = max(int(cell.get_sub_category(CellType.column_span).category_id) for cell in cells)
             # TODO: the summaries should be sub categories of the underlying ann
             if table.image.summary is not None:
-                if TableType.number_of_rows in table.image.summary.sub_categories:
-                    table.get_summary(TableType.number_of_rows)
-                if TableType.number_of_columns in table.image.summary.sub_categories:
-                    table.get_summary(TableType.number_of_columns)
-                if TableType.max_row_span in table.image.summary.sub_categories:
-                    table.get_summary(TableType.max_row_span)
-                if TableType.max_col_span in table.image.summary.sub_categories:
-                    table.get_summary(TableType.max_col_span)
+                if (
+                    TableType.number_of_rows in table.image.summary.sub_categories
+                    and TableType.number_of_columns in table.image.summary.sub_categories
+                    and TableType.max_row_span in table.image.summary.sub_categories
+                    and TableType.max_col_span in table.image.summary.sub_categories
+                ):
+                    table.image.summary.remove_sub_category(TableType.number_of_rows)
+                    table.image.summary.remove_sub_category(TableType.number_of_columns)
+                    table.image.summary.remove_sub_category(TableType.max_row_span)
+                    table.image.summary.remove_sub_category(TableType.max_col_span)
+                else:
+                    raise AnnotationError(
+                        "Table summary does not contain sub categories TableType.number_of_rows, "
+                        "TableType.number_of_columns, TableType.max_row_span, TableType.max_col_span"
+                    )
 
             self.dp_manager.set_summary_annotation(
                 TableType.number_of_rows, TableType.number_of_rows, number_of_rows, annotation_id=table.annotation_id

deepdoctection/pipe/segment.py

@@ -33,6 +33,7 @@ from ..extern.base import DetectionResult
 from ..mapper.maputils import MappingContextManager
 from ..mapper.match import match_anns_by_intersection
 from ..utils.detection_types import JsonDict
+from ..utils.error import ImageError
 from ..utils.settings import CellType, LayoutType, ObjectTypes, Relationships, TableType
 from .base import PipelineComponent
 from .refine import generate_html_string
@@ -136,12 +137,12 @@ def stretch_item_per_table(
 
     rows = dp.get_annotation(category_names=row_name, annotation_ids=item_ann_ids)
     if table.image is None:
-        raise ValueError("table.image cannot be None")
+        raise ImageError("table.image cannot be None")
     table_embedding_box = table.get_bounding_box(dp.image_id)
 
     for row in rows:
         if row.image is None:
-            raise ValueError("row.image cannot be None")
+            raise ImageError("row.image cannot be None")
         row_embedding_box = row.get_bounding_box(dp.image_id)
         row_embedding_box.ulx = table_embedding_box.ulx + 1.0
         row_embedding_box.lrx = table_embedding_box.lrx - 1.0
@@ -166,7 +167,7 @@ def stretch_item_per_table(
 
     for col in cols:
         if col.image is None:
-            raise ValueError("row.image cannot be None")
+            raise ImageError("row.image cannot be None")
         col_embedding_box = col.get_bounding_box(dp.image_id)
         col_embedding_box.uly = table_embedding_box.uly + 1.0
         col_embedding_box.lry = table_embedding_box.lry - 1.0
@@ -194,7 +195,7 @@ def _tile_by_stretching_rows_left_and_rightwise(
     dp: Image, items: List[ImageAnnotation], table: ImageAnnotation, item_name: str
 ) -> None:
     if table.image is None:
-        raise ValueError("table.image cannot be None")
+        raise ImageError("table.image cannot be None")
     table_embedding_box = table.get_bounding_box(dp.image_id)
 
     tmp_item_xy = table_embedding_box.uly + 1.0 if item_name == LayoutType.row else table_embedding_box.ulx + 1.0
@@ -206,7 +207,7 @@ def _tile_by_stretching_rows_left_and_rightwise(
             image_annotation={"category_name": item.category_name, "annotation_id": item.annotation_id},
         ):
             if item.image is None:
-                raise ValueError("item.image cannot be None")
+                raise ImageError("item.image cannot be None")
             item_embedding_box = item.get_bounding_box(dp.image_id)
             if idx != len(items) - 1:
                 next_item_embedding_box = items[idx + 1].get_bounding_box(dp.image_id)
@@ -258,7 +259,7 @@ def _tile_by_stretching_rows_leftwise_column_downwise(
     dp: Image, items: List[ImageAnnotation], table: ImageAnnotation, item_name: str
 ) -> None:
     if table.image is None:
-        raise ValueError("table.image cannot be None")
+        raise ImageError("table.image cannot be None")
     table_embedding_box = table.get_bounding_box(dp.image_id)
 
     tmp_item_xy = table_embedding_box.uly + 1.0 if item_name == LayoutType.row else table_embedding_box.ulx + 1.0
@@ -270,7 +271,7 @@ def _tile_by_stretching_rows_leftwise_column_downwise(
             image_annotation={"category_name": item.category_name, "annotation_id": item.annotation_id},
         ):
             if item.image is None:
-                raise ValueError("item.image cannot be None")
+                raise ImageError("item.image cannot be None")
             item_embedding_box = item.get_bounding_box(dp.image_id)
             new_embedding_box = BoundingBox(
                 ulx=item_embedding_box.ulx if item_name == LayoutType.row else tmp_item_xy,
@@ -339,9 +340,9 @@ def tile_tables_with_items_per_table(
     items = dp.get_annotation(category_names=item_name, annotation_ids=item_ann_ids)
 
     items.sort(
-        key=lambda x: x.get_bounding_box(dp.image_id).cx
-        if item_name == LayoutType.column
-        else x.get_bounding_box(dp.image_id).cy
+        key=lambda x: (
+            x.get_bounding_box(dp.image_id).cx if item_name == LayoutType.column else x.get_bounding_box(dp.image_id).cy
+        )
     )
 
     if stretch_rule == "left":
@@ -737,9 +738,11 @@ class TableSegmentationService(PipelineComponent):
 
                 # we will assume that either all or no image attribute has been generated
                 items.sort(
-                    key=lambda x: x.get_bounding_box(dp.image_id).cx  # pylint: disable=W0640
-                    if item_name == LayoutType.column  # pylint: disable=W0640
-                    else x.get_bounding_box(dp.image_id).cy  # pylint: disable=W0640
+                    key=lambda x: (
+                        x.get_bounding_box(dp.image_id).cx  # pylint: disable=W0640
+                        if item_name == LayoutType.column  # pylint: disable=W0640
+                        else x.get_bounding_box(dp.image_id).cy  # pylint: disable=W0640
+                    )
                 )
 
                 for item_number, item in enumerate(items, 1):
@@ -939,9 +942,11 @@ class PubtablesSegmentationService(PipelineComponent):
 
                 # we will assume that either all or no image attribute has been generated
                 items.sort(
-                    key=lambda x: x.get_bounding_box(dp.image_id).cx
-                    if item_name == LayoutType.column  # pylint: disable=W0640
-                    else x.get_bounding_box(dp.image_id).cy
+                    key=lambda x: (
+                        x.get_bounding_box(dp.image_id).cx
+                        if item_name == LayoutType.column  # pylint: disable=W0640
+                        else x.get_bounding_box(dp.image_id).cy
+                    )
                 )
 
                 for item_number, item in enumerate(items, 1):

deepdoctection/pipe/text.py

@@ -26,6 +26,7 @@ from ..datapoint.image import Image
 from ..extern.base import ObjectDetector, PdfMiner, TextRecognizer
 from ..extern.tessocr import TesseractOcrDetector
 from ..utils.detection_types import ImageType, JsonDict
+from ..utils.error import ImageError
 from ..utils.settings import PageType, TypeOrStr, WordType, get_type
 from .base import PredictorPipelineComponent
 from .registry import pipeline_component_registry
@@ -89,7 +90,10 @@ class TextExtractionService(PredictorPipelineComponent):
         super().__init__(self._get_name(text_extract_detector.name), text_extract_detector)
         if self.extract_from_category:
             if not isinstance(self.predictor, (ObjectDetector, TextRecognizer)):
-                raise TypeError("Predicting from a cropped image requires to pass an ObjectDetector or TextRecognizer.")
+                raise TypeError(
+                    f"Predicting from a cropped image requires to pass an ObjectDetector or "
+                    f"TextRecognizer. Got {type(self.predictor)}"
+                )
         if run_time_ocr_language_selection:
             assert isinstance(
                 self.predictor, TesseractOcrDetector
@@ -171,13 +175,13 @@ class TextExtractionService(PredictorPipelineComponent):
 
         if isinstance(text_roi, ImageAnnotation):
             if text_roi.image is None:
-                raise ValueError("text_roi.image cannot be None")
+                raise ImageError("text_roi.image cannot be None")
             if text_roi.image.image is None:
-                raise ValueError("text_roi.image.image cannot be None")
+                raise ImageError("text_roi.image.image cannot be None")
             return text_roi.image.image
         if isinstance(self.predictor, ObjectDetector):
             if not isinstance(text_roi, Image):
-                raise ValueError("text_roi must be an image")
+                raise ImageError("text_roi must be an image")
             return text_roi.image
         if isinstance(text_roi, list):
             assert all(roi.image is not None for roi in text_roi)
@@ -201,9 +205,11 @@ class TextExtractionService(PredictorPipelineComponent):
             [
                 (
                     "image_annotations",
-                    self.predictor.possible_categories()
-                    if isinstance(self.predictor, (ObjectDetector, PdfMiner))
-                    else [],
+                    (
+                        self.predictor.possible_categories()
+                        if isinstance(self.predictor, (ObjectDetector, PdfMiner))
+                        else []
+                    ),
                 ),
                 ("sub_categories", sub_cat_dict),
                 ("relationships", {}),
@@ -218,5 +224,5 @@ class TextExtractionService(PredictorPipelineComponent):
     def clone(self) -> "PredictorPipelineComponent":
         predictor = self.predictor.clone()
         if not isinstance(predictor, (ObjectDetector, PdfMiner, TextRecognizer)):
-            raise ValueError(f"predictor must be of type ObjectDetector or PdfMiner, but is of type {type(predictor)}")
+            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)

deepdoctection/pipe/transform.py

@@ -23,7 +23,6 @@ on images (e.g. deskew, de-noising or more general GAN like operations.
 from ..datapoint.image import Image
 from ..extern.base import ImageTransformer
 from ..utils.detection_types import JsonDict
-from ..utils.logger import LoggingRecord, logger
 from .base import ImageTransformPipelineComponent
 from .registry import pipeline_component_registry
 
@@ -49,16 +48,24 @@ class SimpleTransformService(ImageTransformPipelineComponent):
 
     def serve(self, dp: Image) -> None:
         if dp.annotations:
-            logger.warning(
-                LoggingRecord(
-                    f"{self.name} has already received image with image annotations. These annotations "
-                    f"will not be transformed and might cause unexpected output in your pipeline."
-                )
+            raise RuntimeError(
+                "SimpleTransformService receives datapoints with ÌmageAnnotations. This violates the "
+                "pipeline building API but this can currently be catched only at runtime. "
+                "Please make sure that this component is the first one in the pipeline."
             )
+
         if dp.image is not None:
-            np_image_transform = self.transform_predictor.transform(dp.image)
+            detection_result = self.transform_predictor.predict(dp.image)
+            transformed_image = self.transform_predictor.transform(dp.image, detection_result)
             self.dp_manager.datapoint.clear_image(True)
-            self.dp_manager.datapoint.image = np_image_transform
+            self.dp_manager.datapoint.image = transformed_image
+            self.dp_manager.set_summary_annotation(
+                summary_key=self.transform_predictor.possible_category(),
+                summary_name=self.transform_predictor.possible_category(),
+                summary_number=None,
+                summary_value=getattr(detection_result, self.transform_predictor.possible_category().value, None),
+                summary_score=detection_result.score,
+            )
 
     def clone(self) -> "SimpleTransformService":
         return self.__class__(self.transform_predictor)
@@ -69,7 +76,7 @@ class SimpleTransformService(ImageTransformPipelineComponent):
                 ("image_annotations", []),
                 ("sub_categories", {}),
                 ("relationships", {}),
-                ("summaries", []),
+                ("summaries", [self.transform_predictor.possible_category()]),
             ]
         )
 

deepdoctection/train/d2_frcnn_train.py

@@ -43,6 +43,7 @@ from ..extern.pt.ptutils import get_num_gpu
 from ..mapper.d2struct import image_to_d2_frcnn_training
 from ..pipe.base import PredictorPipelineComponent
 from ..pipe.registry import pipeline_component_registry
+from ..utils.error import DependencyError
 from ..utils.file_utils import get_wandb_requirement, wandb_available
 from ..utils.logger import LoggingRecord, logger
 from ..utils.utils import string_to_dict
@@ -153,16 +154,18 @@ class D2Trainer(DefaultTrainer):
         ret = [
             hooks.IterationTimer(),
             hooks.LRScheduler(),
-            hooks.PreciseBN(
-                # Run at the same freq as (but before) evaluation.
-                cfg.TEST.EVAL_PERIOD,
-                self.model,  # pylint: disable=E1101
-                # Build a new data loader to not affect training
-                self.build_train_loader(cfg),
-                cfg.TEST.PRECISE_BN.NUM_ITER,
-            )
-            if cfg.TEST.PRECISE_BN.ENABLED and get_bn_modules(self.model)  # pylint: disable=E1101
-            else None,
+            (
+                hooks.PreciseBN(
+                    # Run at the same freq as (but before) evaluation.
+                    cfg.TEST.EVAL_PERIOD,
+                    self.model,  # pylint: disable=E1101
+                    # Build a new data loader to not affect training
+                    self.build_train_loader(cfg),
+                    cfg.TEST.PRECISE_BN.NUM_ITER,
+                )
+                if cfg.TEST.PRECISE_BN.ENABLED and get_bn_modules(self.model)  # pylint: disable=E1101
+                else None
+            ),
         ]
 
         # Do PreciseBN before checkpointer, because it updates the model and need to
@@ -201,7 +204,7 @@ class D2Trainer(DefaultTrainer):
         if self.cfg.WANDB.USE_WANDB:
             _, _wandb_available, err_msg = get_wandb_requirement()
             if not _wandb_available:
-                raise ImportError(err_msg)
+                raise DependencyError(err_msg)
             if self.cfg.WANDB.PROJECT is None:
                 raise ValueError("When using W&B, you must specify a project, i.e. WANDB.PROJECT")
             writers_list.append(WandbWriter(self.cfg.WANDB.PROJECT, self.cfg.WANDB.REPO, self.cfg))
@@ -269,7 +272,7 @@ class D2Trainer(DefaultTrainer):
 
     @classmethod
     def build_evaluator(cls, cfg, dataset_name):  # type: ignore
-        raise NotImplementedError
+        raise NotImplementedError()
 
 
 def train_d2_faster_rcnn(

deepdoctection/train/hf_detr_train.py

@@ -97,9 +97,9 @@ class DetrDerivedTrainer(Trainer):
 
     def evaluate(
         self,
-        eval_dataset: Optional[Dataset[Any]] = None,
-        ignore_keys: Optional[List[str]] = None,
-        metric_key_prefix: str = "eval",
+        eval_dataset: Optional[Dataset[Any]] = None,  # pylint: disable=W0613
+        ignore_keys: Optional[List[str]] = None,  # pylint: disable=W0613
+        metric_key_prefix: str = "eval",  # pylint: disable=W0613
     ) -> Dict[str, float]:
         """
         Overwritten method from `Trainer`. Arguments will not be used.
@@ -193,9 +193,11 @@ def train_hf_detr(
         "remove_unused_columns": False,
         "per_device_train_batch_size": 2,
         "max_steps": number_samples,
-        "evaluation_strategy": "steps"
-        if (dataset_val is not None and metric is not None and pipeline_component_name is not None)
-        else "no",
+        "evaluation_strategy": (
+            "steps"
+            if (dataset_val is not None and metric is not None and pipeline_component_name is not None)
+            else "no"
+        ),
         "eval_steps": 5000,
     }
 

deepdoctection/train/hf_layoutlm_train.py

@@ -63,6 +63,7 @@ from ..pipe.base import LanguageModelPipelineComponent
 from ..pipe.lm import get_tokenizer_from_architecture
 from ..pipe.registry import pipeline_component_registry
 from ..utils.env_info import get_device
+from ..utils.error import DependencyError
 from ..utils.file_utils import wandb_available
 from ..utils.logger import LoggingRecord, logger
 from ..utils.settings import DatasetType, LayoutType, ObjectTypes, WordType
@@ -180,15 +181,17 @@ class LayoutLMTrainer(Trainer):
 
     def evaluate(
         self,
-        eval_dataset: Optional[Dataset[Any]] = None,
-        ignore_keys: Optional[List[str]] = None,
-        metric_key_prefix: str = "eval",
+        eval_dataset: Optional[Dataset[Any]] = None,  # pylint: disable=W0613
+        ignore_keys: Optional[List[str]] = None,  # pylint: disable=W0613
+        metric_key_prefix: str = "eval",  # pylint: disable=W0613
     ) -> Dict[str, float]:
         """
         Overwritten method from `Trainer`. Arguments will not be used.
         """
-        assert self.evaluator is not None
-        assert self.evaluator.pipe_component is not None
+        if self.evaluator is None:
+            raise ValueError("Evaluator not set up. Please use `setup_evaluator` before running evaluation")
+        if self.evaluator.pipe_component is None:
+            raise ValueError("Pipeline component not set up. Please use `setup_evaluator` before running evaluation")
 
         # memory metrics - must set up as early as possible
         self._memory_tracker.start()
@@ -222,7 +225,7 @@ def _get_model_class_and_tokenizer(
         raise KeyError("model_type and architectures not available in configs")
 
     if not model_cls:
-        raise ValueError("model not eligible to run with this framework")
+        raise UserWarning("model not eligible to run with this framework")
 
     return config_cls, model_cls, model_wrapper_cls, tokenizer_fast
 
@@ -347,7 +350,7 @@ def train_hf_layoutlm(
                 name_as_key=True,
             )[LayoutType.word][WordType.token_class]
     else:
-        raise ValueError("Dataset type not supported for training")
+        raise UserWarning("Dataset type not supported for training")
 
     config_cls, model_cls, model_wrapper_cls, tokenizer_fast = _get_model_class_and_tokenizer(
         path_config_json, dataset_type, use_xlm_tokenizer
@@ -374,9 +377,11 @@ def train_hf_layoutlm(
         "remove_unused_columns": False,
         "per_device_train_batch_size": 8,
         "max_steps": number_samples,
-        "evaluation_strategy": "steps"
-        if (dataset_val is not None and metric is not None and pipeline_component_name is not None)
-        else "no",
+        "evaluation_strategy": (
+            "steps"
+            if (dataset_val is not None and metric is not None and pipeline_component_name is not None)
+            else "no"
+        ),
         "eval_steps": 100,
         "use_wandb": False,
         "wandb_project": None,
@@ -416,7 +421,7 @@ def train_hf_layoutlm(
     run = None
     if use_wandb:
         if not wandb_available():
-            raise ModuleNotFoundError("WandB must be installed separately")
+            raise DependencyError("WandB must be installed separately")
         run = wandb.init(project=wandb_project, config=conf_dict)  # type: ignore
         run._label(repo=wandb_repo)  # type: ignore # pylint: disable=W0212
     else:

deepdoctection/utils/__init__.py

@@ -6,7 +6,10 @@ Init file for utils package
 """
 from typing import Optional, Tuple, Union, no_type_check
 
+from .concurrency import *
 from .context import *
+from .env_info import *
+from .error import *
 from .file_utils import *
 from .fs import *
 from .identifier import *

deepdoctection/utils/concurrency.py

@@ -109,7 +109,7 @@ def enable_death_signal(_warn: bool = True) -> None:
         prctl, "set_pdeathsig"
     ), "prctl.set_pdeathsig does not exist! Note that you need to install 'python-prctl' instead of 'prctl'."
     # is SIGHUP a good choice?
-    prctl.set_pdeathsig(signal.SIGHUP)
+    prctl.set_pdeathsig(signal.SIGHUP)  # pylint: disable=E1101
 
 
 # taken from https://github.com/tensorpack/dataflow/blob/master/dataflow/utils/concurrency.py

deepdoctection/utils/context.py

@@ -61,7 +61,7 @@ def timeout_manager(proc, seconds: Optional[int] = None) -> Iterator[str]:  # ty
             proc.terminate()
             proc.kill()
             proc.returncode = -1
-            raise RuntimeError("Tesseract process timeout")  # pylint: disable=W0707
+            raise RuntimeError(f"timeout for process id: {proc.pid}")  # pylint: disable=W0707
     finally:
         if proc.stdin is not None:
             proc.stdin.close()
@@ -88,7 +88,7 @@ def save_tmp_file(image: Union[str, ImageType, bytes], prefix: str) -> Iterator[
                 yield file.name, path.realpath(path.normpath(path.normcase(image)))
                 return
             if isinstance(image, (np.ndarray, np.generic)):
-                input_file_name = file.name + ".PNG"
+                input_file_name = file.name + "_input.PNG"
                 viz_handler.write_image(input_file_name, image)
                 yield file.name, input_file_name
             if isinstance(image, bytes):