deepdoctection 0.31__py3-none-any.whl → 0.32__py3-none-any.whl

deepdoctection/datasets/base.py

@@ -18,6 +18,8 @@
 """
 Module for the base class of datasets.
 """
+from __future__ import annotations
+
 import json
 import os
 import pprint
@@ -33,7 +35,7 @@ from ..dataflow import CacheData, ConcatData, CustomDataFromList, DataFlow
 from ..datapoint.image import Image
 from ..utils.detection_types import Pathlike
 from ..utils.logger import LoggingRecord, logger
-from ..utils.settings import ObjectTypes, TypeOrStr, get_type
+from ..utils.settings import DatasetType, ObjectTypes, TypeOrStr, get_type
 from .dataflow_builder import DataFlowBaseBuilder
 from .info import DatasetCategories, DatasetInfo, get_merged_categories
 
@@ -423,7 +425,7 @@ class CustomDataset(DatasetBase):
         """
 
         self.name = name
-        self.type = get_type(dataset_type)
+        self.type: DatasetType = get_type(dataset_type)  # type: ignore
         self.location = location
         self.init_categories = init_categories
         if init_sub_categories is None:
@@ -449,7 +451,7 @@ class CustomDataset(DatasetBase):
         return self.dataflow_builder
 
     @staticmethod
-    def from_dataset_card(file_path: str, dataflow_builder: Type[DataFlowBaseBuilder]) -> "CustomDataset":
+    def from_dataset_card(file_path: str, dataflow_builder: Type[DataFlowBaseBuilder]) -> CustomDataset:
         """
         This static method creates a CustomDataset instance from a dataset card.
 

deepdoctection/datasets/info.py

@@ -24,7 +24,7 @@ from dataclasses import dataclass, field
 from itertools import chain
 from typing import Any, Dict, List, Literal, Mapping, Optional, Sequence, Set, Union, no_type_check, overload
 
-from ..utils.settings import DefaultType, ObjectTypes, TypeOrStr, get_type
+from ..utils.settings import DatasetType, ObjectTypes, TypeOrStr, get_type
 from ..utils.utils import call_only_once
 
 __all__ = ["DatasetInfo", "DatasetCategories", "get_merged_categories"]
@@ -89,7 +89,7 @@ class DatasetInfo:
     license: str = field(default="")
     url: Union[str, Sequence[str]] = field(default="")
     splits: Mapping[str, str] = field(default_factory=dict)
-    type: ObjectTypes = field(default=DefaultType.default_type)
+    type: DatasetType = field(default=DatasetType.default)
 
     def get_split(self, key: str) -> str:
         """

deepdoctection/datasets/instances/doclaynet.py

@@ -25,6 +25,7 @@ Module for DocLayNet dataset. Place the dataset as follows
     ├── PNG
     │ ├── 0a0d43e301facee9e99cc33b9b16e732dd207135f4027e75f6aea2bf117535a2.png
 """
+from __future__ import annotations
 
 import os
 from typing import Mapping, Sequence, Union
@@ -109,7 +110,7 @@ class DocLayNet(DatasetBase):
     def _categories(self) -> DatasetCategories:
         return DatasetCategories(init_categories=_INIT_CATEGORIES, init_sub_categories=_SUB_CATEGORIES)
 
-    def _builder(self) -> "DocLayNetBuilder":
+    def _builder(self) -> DocLayNetBuilder:
         return DocLayNetBuilder(location=_LOCATION, annotation_files=_ANNOTATION_FILES)
 
 
@@ -209,7 +210,7 @@ class DocLayNetSeq(DatasetBase):
     def _categories(self) -> DatasetCategories:
         return DatasetCategories(init_categories=_INIT_CATEGORIES_SEQ)
 
-    def _builder(self) -> "DocLayNetSeqBuilder":
+    def _builder(self) -> DocLayNetSeqBuilder:
         return DocLayNetSeqBuilder(location=_LOCATION, annotation_files=_ANNOTATION_FILES)
 
 

deepdoctection/datasets/instances/fintabnet.py

@@ -30,6 +30,7 @@ Module for Fintabnet dataset. Place the dataset as follows
     ├── FinTabNet_1.0.0_table_train.jsonl
     ├── FinTabNet_1.0.0_table_val.jsonl
 """
+from __future__ import annotations
 
 from pathlib import Path
 from typing import List, Mapping, Sequence, Union
@@ -133,7 +134,7 @@ class Fintabnet(_BuiltInDataset):
     def _categories(self) -> DatasetCategories:
         return DatasetCategories(init_categories=_INIT_CATEGORIES, init_sub_categories=_SUB_CATEGORIES)
 
-    def _builder(self) -> "FintabnetBuilder":
+    def _builder(self) -> FintabnetBuilder:
         return FintabnetBuilder(location=_LOCATION, annotation_files=_ANNOTATION_FILES)
 
 

deepdoctection/datasets/instances/funsd.py

@@ -32,6 +32,7 @@ Module for Funsd dataset.  Install the dataset following the folder structure
     │ ├── images
     │ │ ├── ...
 """
+from __future__ import annotations
 
 import os
 from typing import Dict, List, Mapping, Union
@@ -120,7 +121,7 @@ class Funsd(_BuiltInDataset):
     def _categories(self) -> DatasetCategories:
         return DatasetCategories(init_categories=_INIT_CATEGORIES, init_sub_categories=_SUB_CATEGORIES)
 
-    def _builder(self) -> "FunsdBuilder":
+    def _builder(self) -> FunsdBuilder:
         return FunsdBuilder(location=_LOCATION, annotation_files=_ANNOTATION_FILES)
 
 

deepdoctection/datasets/instances/iiitar13k.py

@@ -35,10 +35,13 @@ Module for IIITar13K dataset. Install the dataset following the folder structure
     │ ├── ...
 
 """
+from __future__ import annotations
 
 import os
 from typing import Mapping, Union
 
+from lazy_imports import try_import
+
 from ...dataflow import DataFlow, MapData, SerializerFiles
 from ...datasets.info import DatasetInfo
 from ...mapper.maputils import curry
@@ -53,7 +56,7 @@ from ..dataflow_builder import DataFlowBaseBuilder
 from ..info import DatasetCategories
 from ..registry import dataset_registry
 
-if lxml_available():
+with try_import() as import_guard:
     from lxml import etree
 
 _NAME = "iiitar13k"
@@ -99,7 +102,7 @@ class IIITar13K(_BuiltInDataset):
     def _categories(self) -> DatasetCategories:
         return DatasetCategories(init_categories=_INIT_CATEGORIES)
 
-    def _builder(self) -> "IIITar13KBuilder":
+    def _builder(self) -> IIITar13KBuilder:
         return IIITar13KBuilder(location=_LOCATION, annotation_files=_ANNOTATION_FILES)
 
 

deepdoctection/datasets/instances/layouttest.py

@@ -24,6 +24,7 @@ Module for Testlayout dataset. Install the dataset following the folder structur
     ├── test
     │ ├── xrf_layout_test.jsonl
 """
+from __future__ import annotations
 
 from typing import Mapping, Union
 
@@ -77,7 +78,7 @@ class LayoutTest(_BuiltInDataset):
     def _categories(self) -> DatasetCategories:
         return DatasetCategories(init_categories=_INIT_CATEGORIES)
 
-    def _builder(self) -> "LayoutTestBuilder":
+    def _builder(self) -> LayoutTestBuilder:
         return LayoutTestBuilder(location=_LOCATION, annotation_files=_ANNOTATION_FILES)
 
 

deepdoctection/datasets/instances/publaynet.py

@@ -28,7 +28,7 @@ Module for Publaynet dataset. Place the dataset as follows
     ├── train.json
     ├── val.json
 """
-
+from __future__ import annotations
 
 from typing import Mapping, Union
 
@@ -84,7 +84,7 @@ class Publaynet(_BuiltInDataset):
     def _categories(self) -> DatasetCategories:
         return DatasetCategories(init_categories=_INIT_CATEGORIES)
 
-    def _builder(self) -> "PublaynetBuilder":
+    def _builder(self) -> PublaynetBuilder:
         return PublaynetBuilder(location=_LOCATION, annotation_files=_ANNOTATION_FILES)
 
 

deepdoctection/datasets/instances/pubtables1m.py

@@ -37,10 +37,13 @@ Module for PubTables1M-Detection-PASCAL-VOC dataset. Install the dataset followi
     ├── PubTables-1M-Structure_Annotations_Test
     ├── PubTables-1M-Structure_Images_Test
 """
+from __future__ import annotations
 
 import os
 from typing import Mapping, Union
 
+from lazy_imports import try_import
+
 from ...dataflow import DataFlow, MapData, SerializerFiles
 from ...datasets.info import DatasetInfo
 from ...mapper.cats import filter_cat
@@ -56,7 +59,7 @@ from ..dataflow_builder import DataFlowBaseBuilder
 from ..info import DatasetCategories
 from ..registry import dataset_registry
 
-if lxml_available():
+with try_import() as import_guard:
     from lxml import etree
 
 _NAME = "pubtables1m_det"
@@ -102,7 +105,7 @@ class Pubtables1MDet(_BuiltInDataset):
     def _categories(self) -> DatasetCategories:
         return DatasetCategories(init_categories=_INIT_CATEGORIES_DET)
 
-    def _builder(self) -> "Pubtables1MBuilder":
+    def _builder(self) -> Pubtables1MBuilder:
         return Pubtables1MBuilder(location=_LOCATION, annotation_files=_ANNOTATION_FILES)
 
 
@@ -225,7 +228,7 @@ class Pubtables1MStruct(_BuiltInDataset):
     def _categories(self) -> DatasetCategories:
         return DatasetCategories(init_categories=_INIT_CATEGORIES_STRUCT)
 
-    def _builder(self) -> "Pubtables1MBuilderStruct":
+    def _builder(self) -> Pubtables1MBuilderStruct:
         return Pubtables1MBuilderStruct(location=_LOCATION, annotation_files=_ANNOTATION_FILES_STRUCT)
 
 

deepdoctection/datasets/instances/pubtabnet.py

@@ -27,6 +27,7 @@ Module for Pubtabnet dataset. Place the dataset as follows
     │ ├── PMC3.png
     ├── PubTabNet_2.0.0.jsonl
 """
+from __future__ import annotations
 
 from typing import Dict, List, Mapping, Union
 
@@ -119,7 +120,7 @@ class Pubtabnet(_BuiltInDataset):
     def _categories(self) -> DatasetCategories:
         return DatasetCategories(init_categories=_INIT_CATEGORIES, init_sub_categories=_SUB_CATEGORIES)
 
-    def _builder(self) -> "PubtabnetBuilder":
+    def _builder(self) -> PubtabnetBuilder:
         return PubtabnetBuilder(location=_LOCATION, annotation_files=_ANNOTATION_FILES)
 
 

deepdoctection/datasets/instances/rvlcdip.py

@@ -29,6 +29,7 @@ Module for Publaynet dataset. Place the dataset as follows
     │ ├── train.txt
     │ ├── val.txt
 """
+from __future__ import annotations
 
 import os
 from typing import Mapping, Union
@@ -102,7 +103,7 @@ class Rvlcdip(_BuiltInDataset):
     def _categories(self) -> DatasetCategories:
         return DatasetCategories(init_categories=_INIT_CATEGORIES)
 
-    def _builder(self) -> "RvlcdipBuilder":
+    def _builder(self) -> RvlcdipBuilder:
         return RvlcdipBuilder(location=_LOCATION, annotation_files=_ANNOTATION_FILES)
 
 

deepdoctection/datasets/instances/xfund.py

@@ -27,6 +27,7 @@ Module for XFUND dataset. Install the dataset following the folder structure
     │ ├── de_val_0.jpg
     ├── es_train
 """
+from __future__ import annotations
 
 import json
 import os
@@ -108,7 +109,7 @@ class Xfund(_BuiltInDataset):
     def _categories(self) -> DatasetCategories:
         return DatasetCategories(init_categories=_INIT_CATEGORIES, init_sub_categories=_SUB_CATEGORIES)
 
-    def _builder(self) -> "XfundBuilder":
+    def _builder(self) -> XfundBuilder:
         return XfundBuilder(location=_LOCATION, annotation_files=_ANNOTATION_FILES)
 
 

deepdoctection/eval/__init__.py

@@ -20,12 +20,9 @@ Init file for eval package. Contains metrics (customized for special tasks), eva
 for training.
 """
 
-from ..utils.file_utils import apted_available
 from .accmetric import *
 from .base import *
 from .cocometric import *
 from .eval import *
 from .registry import *
-
-if apted_available():
-    from .tedsmetric import *
+from .tedsmetric import *

deepdoctection/eval/cocometric.py

@@ -23,6 +23,7 @@ from copy import copy
 from typing import Dict, List, Optional, Tuple, Union
 
 import numpy as np
+from lazy_imports import try_import
 
 from ..dataflow import DataFlow
 from ..datasets.info import DatasetCategories
@@ -33,7 +34,7 @@ from ..utils.file_utils import Requirement, cocotools_available, get_cocotools_r
 from .base import MetricBase
 from .registry import metric_registry
 
-if cocotools_available():
+with try_import() as cc_import_guard:
     from pycocotools.coco import COCO
     from pycocotools.cocoeval import COCOeval
 

deepdoctection/eval/eval.py

@@ -19,36 +19,35 @@
 """
 Module for `Evaluator`
 """
-
-__all__ = ["Evaluator"]
+from __future__ import annotations
 
 from copy import deepcopy
-from typing import Any, Dict, List, Literal, Mapping, Optional, Type, Union, overload
+from typing import Any, Dict, Generator, List, Literal, Mapping, Optional, Type, Union, overload
 
 import numpy as np
+from lazy_imports import try_import
 
 from ..dataflow import CacheData, DataFlow, DataFromList, MapData
 from ..datapoint.image import Image
 from ..datasets.base import DatasetBase
 from ..mapper.cats import filter_cat, remove_cats
+from ..mapper.d2struct import to_wandb_image
 from ..mapper.misc import maybe_load_image, maybe_remove_image, maybe_remove_image_from_category
 from ..pipe.base import LanguageModelPipelineComponent, PredictorPipelineComponent
 from ..pipe.common import PageParsingService
 from ..pipe.concurrency import MultiThreadPipelineComponent
 from ..pipe.doctectionpipe import DoctectionPipe
 from ..utils.detection_types import ImageType
-from ..utils.file_utils import detectron2_available, wandb_available
 from ..utils.logger import LoggingRecord, logger
 from ..utils.settings import DatasetType, LayoutType, TypeOrStr, get_type
 from ..utils.viz import interactive_imshow
 from .base import MetricBase
 
-if wandb_available():
+with try_import() as wb_import_guard:
     import wandb  # pylint:disable=W0611
     from wandb import Artifact, Table
 
-if wandb_available() and detectron2_available():
-    from ..mapper.d2struct import to_wandb_image
+__all__ = ["Evaluator"]
 
 
 class Evaluator:
@@ -94,7 +93,7 @@ class Evaluator:
         component_or_pipeline: Union[PredictorPipelineComponent, LanguageModelPipelineComponent, DoctectionPipe],
         metric: Union[Type[MetricBase], MetricBase],
         num_threads: int = 2,
-        run: Optional["wandb.sdk.wandb_run.Run"] = None,
+        run: Optional[wandb.sdk.wandb_run.Run] = None,
     ) -> None:
         """
         Evaluating a pipeline component on a dataset with a given metric.
@@ -275,7 +274,7 @@ class Evaluator:
 
         return df_pr
 
-    def compare(self, interactive: bool = False, **kwargs: Union[str, int]) -> Optional[ImageType]:
+    def compare(self, interactive: bool = False, **kwargs: Union[str, int]) -> Generator[ImageType, None, None]:
         """
         Visualize ground truth and prediction datapoint. Given a dataflow config it will run predictions per sample
         and concat the prediction image (with predicted bounding boxes) with ground truth image.
@@ -292,6 +291,8 @@ class Evaluator:
         show_layouts = kwargs.pop("show_layouts", True)
         show_table_structure = kwargs.pop("show_table_structure", True)
         show_words = kwargs.pop("show_words", False)
+        show_token_class = kwargs.pop("show_token_class", True)
+        ignore_default_token_class = kwargs.pop("ignore_default_token_class", False)
 
         df_gt = self.dataset.dataflow.build(**kwargs)
         df_pr = self.dataset.dataflow.build(**kwargs)
@@ -321,18 +322,21 @@ class Evaluator:
                 show_layouts=show_layouts,
                 show_table_structure=show_table_structure,
                 show_words=show_words,
+                show_token_class=show_token_class,
+                ignore_default_token_class=ignore_default_token_class,
             ), dp_pred.viz(
                 show_tables=show_tables,
                 show_layouts=show_layouts,
                 show_table_structure=show_table_structure,
                 show_words=show_words,
+                show_token_class=show_token_class,
+                ignore_default_token_class=ignore_default_token_class,
             )
             img_concat = np.concatenate((img_gt, img_pred), axis=1)
             if interactive:
                 interactive_imshow(img_concat)
             else:
-                return img_concat
-        return None
+                yield img_concat
 
 
 class WandbTableAgent:
@@ -350,7 +354,7 @@ class WandbTableAgent:
 
     def __init__(
         self,
-        wandb_run: "wandb.sdk.wandb_run.Run",
+        wandb_run: wandb.sdk.wandb_run.Run,
         dataset_name: str,
         num_samples: int,
         categories: Mapping[str, TypeOrStr],
@@ -409,7 +413,7 @@ class WandbTableAgent:
         self._table_rows = []
         self._counter = 0
 
-    def _build_table(self) -> "Table":
+    def _build_table(self) -> Table:
         """
         Builds wandb.Table object for logging evaluation
 

deepdoctection/eval/tedsmetric.py

@@ -20,28 +20,31 @@ import statistics
 from collections import defaultdict, deque
 from typing import Any, List, Optional, Tuple
 
+from lazy_imports import try_import
+
 from ..dataflow import DataFlow, DataFromList, MapData, MultiThreadMapData
 from ..datapoint.view import Page
 from ..datasets.base import DatasetCategories
 from ..utils.detection_types import JsonDict
-from ..utils.file_utils import (
-    Requirement,
-    apted_available,
-    distance_available,
-    get_apted_requirement,
-    get_distance_requirement,
-    get_lxml_requirement,
-    lxml_available,
-)
+from ..utils.file_utils import Requirement, get_apted_requirement, get_distance_requirement, get_lxml_requirement
 from ..utils.logger import LoggingRecord, logger
 from ..utils.settings import LayoutType
 from .base import MetricBase
 from .registry import metric_registry
 
-if distance_available() and lxml_available() and apted_available():
-    import distance  # type: ignore
+with try_import() as ap_import_guard:
     from apted import APTED, Config  # type: ignore
     from apted.helpers import Tree  # type: ignore
+
+
+if not ap_import_guard.is_successful():
+    from ..utils.mocks import Config, Tree
+
+
+with try_import() as ds_import_guard:
+    import distance  # type: ignore
+
+with try_import() as lx_import_guard:
     from lxml import etree
 
 

deepdoctection/eval/tp_eval_callback.py

@@ -19,13 +19,16 @@
 Module for EvalCallback in Tensorpack
 """
 
+from __future__ import annotations
+
 from itertools import count
 from typing import Mapping, Optional, Sequence, Type, Union
 
+from lazy_imports import try_import
+
 from ..datasets import DatasetBase
 from ..extern.tpdetect import TPFrcnnDetector
 from ..pipe.base import PredictorPipelineComponent
-from ..utils.file_utils import tensorpack_available
 from ..utils.logger import LoggingRecord, logger
 from ..utils.metacfg import AttrDict
 from ..utils.settings import ObjectTypes
@@ -33,12 +36,15 @@ from .base import MetricBase
 from .eval import Evaluator
 
 # pylint: disable=import-error
-if tensorpack_available():
+with try_import() as import_guard:
     from tensorpack.callbacks import Callback
     from tensorpack.predict import OnlinePredictor
     from tensorpack.utils.gpu import get_num_gpu
 # pylint: enable=import-error
 
+if not import_guard.is_successful():
+    from ..utils.mocks import Callback
+
 
 # The following class is modified from
 # https://github.com/tensorpack/tensorpack/blob/master/examples/FasterRCNN/eval.py
@@ -53,7 +59,7 @@ class EvalCallback(Callback):  # pylint: disable=R0903
 
     _chief_only = False
 
-    def __init__(
+    def __init__(  # pylint: disable=W0231
         self,
         dataset: DatasetBase,
         category_names: Optional[Union[ObjectTypes, Sequence[ObjectTypes]]],

deepdoctection/extern/__init__.py

@@ -19,8 +19,8 @@
 Wrappers for models of external libraries as well as implementation of the Cascade-RCNN model of Tensorpack.
 """
 
-from ..utils.file_utils import detectron2_available, tensorpack_available
 from .base import *
+from .d2detect import *
 from .deskew import *
 from .doctrocr import *
 from .fastlang import *
@@ -30,9 +30,4 @@ from .model import *
 from .pdftext import *
 from .tessocr import *
 from .texocr import *  # type: ignore
-
-if tensorpack_available():
-    from .tpdetect import *
-
-if detectron2_available():
-    from .d2detect import *
+from .tpdetect import *