deepdoctection 0.30__py3-none-any.whl → 0.32__py3-none-any.whl

deepdoctection/extern/tessocr.py

@@ -19,21 +19,24 @@
 Tesseract OCR engine for text extraction
 """
 import shlex
+import string
 import subprocess
 import sys
 from errno import ENOENT
 from itertools import groupby
 from os import environ
-from typing import Any, Dict, List, Optional, Union
+from typing import Any, Dict, List, Mapping, Optional, Union
 
-import numpy as np
+from packaging.version import InvalidVersion, Version, parse
 
 from ..utils.context import save_tmp_file, timeout_manager
 from ..utils.detection_types import ImageType, Requirement
-from ..utils.file_utils import _TESS_PATH, TesseractNotFound, get_tesseract_requirement
+from ..utils.error import DependencyError, TesseractError
+from ..utils.file_utils import _TESS_PATH, get_tesseract_requirement
 from ..utils.metacfg import config_to_cli_str, set_config_by_yaml
-from ..utils.settings import LayoutType, ObjectTypes
-from .base import DetectionResult, ObjectDetector, PredictorBase
+from ..utils.settings import LayoutType, ObjectTypes, PageType
+from ..utils.viz import viz_handler
+from .base import DetectionResult, ImageTransformer, ObjectDetector, PredictorBase
 
 # copy and paste with some light modifications from https://github.com/madmaze/pytesseract/tree/master/pytesseract
 
@@ -57,18 +60,6 @@ _LANG_CODE_TO_TESS_LANG_CODE = {
 }
 
 
-class TesseractError(RuntimeError):
-    """
-    Tesseract Error
-    """
-
-    def __init__(self, status: int, message: str) -> None:
-        super().__init__()
-        self.status = status
-        self.message = message
-        self.args = (status, message)
-
-
 def _subprocess_args() -> Dict[str, Any]:
     # See https://github.com/pyinstaller/pyinstaller/wiki/Recipe-subprocess
     # for reference and comments.
@@ -109,7 +100,7 @@ def _run_tesseract(tesseract_args: List[str]) -> None:
     except OSError as error:
         if error.errno != ENOENT:
             raise error from error
-        raise TesseractNotFound("Tesseract not found. Please install or add to your PATH.") from error
+        raise DependencyError("Tesseract not found. Please install or add to your PATH.") from error
 
     with timeout_manager(proc, 0) as error_string:
         if proc.returncode:
@@ -119,6 +110,50 @@ def _run_tesseract(tesseract_args: List[str]) -> None:
             )
 
 
+def get_tesseract_version() -> Version:
+    """
+    Returns Version object of the Tesseract version
+    """
+    try:
+        output = subprocess.check_output(
+            ["tesseract", "--version"],
+            stderr=subprocess.STDOUT,
+            env=environ,
+            stdin=subprocess.DEVNULL,
+        )
+    except OSError as error:
+        raise DependencyError("Tesseract not found. Please install or add to your PATH.") from error
+
+    raw_version = output.decode("utf-8")
+    str_version, *_ = raw_version.lstrip(string.printable[10:]).partition(" ")
+    str_version, *_ = str_version.partition("-")
+
+    try:
+        version = parse(str_version)
+        assert version >= Version("3.05")
+    except (AssertionError, InvalidVersion) as error:
+        raise SystemExit(f'Invalid tesseract version: "{raw_version}"') from error
+
+    return version
+
+
+def image_to_angle(image: ImageType) -> Mapping[str, str]:
+    """
+    Generating a tmp file and running tesseract to get the orientation of the image.
+
+    :param image: Image in np.array.
+    :return: A dictionary with keys 'Orientation in degrees' and 'Orientation confidence'.
+    """
+    with save_tmp_file(image, "tess_") as (tmp_name, input_file_name):
+        _run_tesseract(_input_to_cli_str("osd", "--psm 0", 0, input_file_name, tmp_name))
+        with open(tmp_name + ".osd", "rb") as output_file:
+            output = output_file.read().decode("utf-8")
+
+    return {
+        key_value[0]: key_value[1] for key_value in (line.split(": ") for line in output.split("\n") if len(line) >= 2)
+    }
+
+
 def image_to_dict(image: ImageType, lang: str, config: str) -> Dict[str, List[Union[str, int, float]]]:
     """
     This is more or less pytesseract.image_to_data with a dict as returned value.
@@ -220,7 +255,6 @@ def predict_text(np_img: ImageType, supported_languages: str, text_lines: bool,
     :return: A list of tesseract extractions wrapped in DetectionResult
     """
 
-    np_img = np_img.astype(np.uint8)
     results = image_to_dict(np_img, supported_languages, config)
     all_results = []
 
@@ -249,6 +283,16 @@ def predict_text(np_img: ImageType, supported_languages: str, text_lines: bool,
     return all_results
 
 
+def predict_rotation(np_img: ImageType) -> Mapping[str, str]:
+    """
+    Predicts the rotation of an image using the Tesseract OCR engine.
+
+    :param np_img: numpy array of the image
+    :return: A dictionary with keys 'Orientation in degrees' and 'Orientation confidence'
+    """
+    return image_to_angle(np_img)
+
+
 class TesseractOcrDetector(ObjectDetector):
     """
     Text object detector based on Tesseracts OCR engine. Note that tesseract has to be installed separately.
@@ -292,7 +336,9 @@ class TesseractOcrDetector(ObjectDetector):
         :param config_overwrite: Overwrite config parameters defined by the yaml file with new values.
                                  E.g. ["oem=14"]
         """
-        self.name = _TESS_PATH
+        self.name = self.get_name()
+        self.model_id = self.get_model_id()
+
         if config_overwrite is None:
             config_overwrite = []
 
@@ -316,13 +362,13 @@ class TesseractOcrDetector(ObjectDetector):
         :param np_img: image as numpy array
         :return: A list of DetectionResult
         """
-        detection_results = predict_text(
+
+        return predict_text(
             np_img,
             supported_languages=self.config.LANGUAGES,
             text_lines=self.config.LINES,
             config=config_to_cli_str(self.config, "LANGUAGES", "LINES"),
         )
-        return detection_results
 
     @classmethod
     def get_requirements(cls) -> List[Requirement]:
@@ -342,3 +388,69 @@ class TesseractOcrDetector(ObjectDetector):
         :param language: `Languages`
         """
         self.config.LANGUAGES = _LANG_CODE_TO_TESS_LANG_CODE.get(language, language.value)
+
+    @staticmethod
+    def get_name() -> str:
+        """Returns the name of the model"""
+        return f"Tesseract_{get_tesseract_version()}"
+
+
+class TesseractRotationTransformer(ImageTransformer):
+    """
+    The `TesseractRotationTransformer` class is a specialized image transformer that is designed to handle image
+    rotation in the context of Optical Character Recognition (OCR) tasks. It inherits from the `ImageTransformer`
+    base class and implements methods for predicting and applying rotation transformations to images.
+
+    The `predict` method determines the angle of the rotated image. It can only handle angles that are multiples of 90
+    degrees.
+    This method uses the Tesseract OCR engine to predict the rotation angle of an image.
+
+    The `transform` method applies the predicted rotation to the image, effectively rotating the image backwards.
+    This method uses either the Pillow library or OpenCV for the rotation operation, depending on the configuration.
+
+    This class can be particularly useful in OCR tasks where the orientation of the text in the image matters.
+    The class also provides methods for cloning itself and for getting the requirements of the Tesseract OCR system.
+
+    **Example:**
+                    transformer = TesseractRotationTransformer()
+                    detection_result = transformer.predict(np_img)
+                    rotated_image = transformer.transform(np_img, detection_result)
+    """
+
+    def __init__(self) -> None:
+        self.name = _TESS_PATH + "-rotation"
+
+    def transform(self, np_img: ImageType, specification: DetectionResult) -> ImageType:
+        """
+        Applies the predicted rotation to the image, effectively rotating the image backwards.
+        This method uses either the Pillow library or OpenCV for the rotation operation, depending on the configuration.
+
+        :param np_img: The input image as a numpy array.
+        :param specification: A `DetectionResult` object containing the predicted rotation angle.
+        :return: The rotated image as a numpy array.
+        """
+        return viz_handler.rotate_image(np_img, specification.angle)  # type: ignore
+
+    def predict(self, np_img: ImageType) -> DetectionResult:
+        """
+        Determines the angle of the rotated image. It can only handle angles that are multiples of 90 degrees.
+        This method uses the Tesseract OCR engine to predict the rotation angle of an image.
+
+        :param np_img: The input image as a numpy array.
+        :return: A `DetectionResult` object containing the predicted rotation angle and confidence.
+        """
+        output_dict = predict_rotation(np_img)
+        return DetectionResult(
+            angle=float(output_dict["Orientation in degrees"]), score=float(output_dict["Orientation confidence"])
+        )
+
+    @classmethod
+    def get_requirements(cls) -> List[Requirement]:
+        return [get_tesseract_requirement()]
+
+    def clone(self) -> PredictorBase:
+        return self.__class__()
+
+    @staticmethod
+    def possible_category() -> PageType:
+        return PageType.angle

deepdoctection/extern/texocr.py

@@ -23,14 +23,16 @@ import sys
 import traceback
 from typing import List
 
+from lazy_imports import try_import
+
 from ..datapoint.convert import convert_np_array_to_b64_b
 from ..utils.detection_types import ImageType, JsonDict, Requirement
-from ..utils.file_utils import boto3_available, get_boto3_requirement
+from ..utils.file_utils import get_boto3_requirement
 from ..utils.logger import LoggingRecord, logger
 from ..utils.settings import LayoutType, ObjectTypes
 from .base import DetectionResult, ObjectDetector, PredictorBase
 
-if boto3_available():
+with try_import() as import_guard:
     import boto3  # type:ignore
 
 
@@ -120,6 +122,8 @@ class TextractOcrDetector(ObjectDetector):
         :param credentials_kwargs: `aws_access_key_id`, `aws_secret_access_key` or `aws_session_token`
         """
         self.name = "textract"
+        self.model_id = self.get_model_id()
+
         self.text_lines = text_lines
         self.client = boto3.client("textract", **credentials_kwargs)
         if self.text_lines:

deepdoctection/extern/tp/tfutils.py

@@ -19,7 +19,18 @@
 Tensorflow related utils.
 """
 
-from tensorpack.models import disable_layer_logging  # pylint: disable=E0401
+from __future__ import annotations
+
+import os
+from typing import Optional, Union, ContextManager
+
+from lazy_imports import try_import
+
+with try_import() as import_guard:
+    from tensorpack.models import disable_layer_logging  # pylint: disable=E0401
+
+with try_import() as tf_import_guard:
+    import tensorflow as tf  # pylint: disable=E0401
 
 
 def is_tfv2() -> bool:
@@ -38,16 +49,13 @@ def disable_tfv2() -> bool:
     """
     Disable TF in V2 mode.
     """
-    try:
-        import tensorflow as tf  # pylint: disable=C0415
 
-        tfv1 = tf.compat.v1
-        if is_tfv2():
-            tfv1.disable_v2_behavior()
-            tfv1.disable_eager_execution()
+    tfv1 = tf.compat.v1
+    if is_tfv2():
+        tfv1.disable_v2_behavior()
+        tfv1.disable_eager_execution()
         return True
-    except ModuleNotFoundError:
-        return False
+    return False
 
 
 def disable_tp_layer_logging() -> None:
@@ -55,3 +63,29 @@ def disable_tp_layer_logging() -> None:
     Disables TP layer logging, if not already set
     """
     disable_layer_logging()
+
+
+def get_tf_device(device: Optional[Union[str, tf.device]] = None) -> tf.device:
+    """
+    Selecting a device on which to load a model. The selection follows a cascade of priorities:
+
+    - If a device string is provided, it is used. If the string is "cuda" or "GPU", the first GPU is used.
+    - If the environment variable "USE_CUDA" is set, a GPU is used. If more GPUs are available it will use the first one
+
+    :param device: Device string
+    :return: Tensorflow device
+    """
+    if device is not None:
+        if isinstance(device, ContextManager):
+            return device
+        if isinstance(device, str):
+            if device in ("cuda", "GPU"):
+                device_names = [device.name for device in tf.config.list_logical_devices(device_type="GPU")]
+                return tf.device(device_names[0].name)
+            # The input must be something sensible
+            return tf.device(device)
+    if os.environ.get("USE_CUDA"):
+        device_names = [device.name for device in tf.config.list_logical_devices(device_type="GPU")]
+        return tf.device(device_names[0])
+    device_names = [device.name for device in tf.config.list_logical_devices(device_type="CPU")]
+    return tf.device(device_names[0])

deepdoctection/extern/tp/tpcompat.py

@@ -18,21 +18,24 @@
 """
 Compatibility classes and methods related to Tensorpack package
 """
+from __future__ import annotations
 
 from abc import ABC, abstractmethod
 from typing import Any, List, Mapping, Tuple, Union
 
-from tensorpack.predict import OfflinePredictor, PredictConfig  # pylint: disable=E0401
-from tensorpack.tfutils import SmartInit  # pylint: disable=E0401
-
-# pylint: disable=import-error
-from tensorpack.train.model_desc import ModelDesc
-from tensorpack.utils.gpu import get_num_gpu
+from lazy_imports import try_import
 
 from ...utils.metacfg import AttrDict
 from ...utils.settings import ObjectTypes
 
-# pylint: enable=import-error
+with try_import() as import_guard:
+    from tensorpack.predict import OfflinePredictor, PredictConfig  # pylint: disable=E0401
+    from tensorpack.tfutils import SmartInit  # pylint: disable=E0401
+    from tensorpack.train.model_desc import ModelDesc  # pylint: disable=E0401
+    from tensorpack.utils.gpu import get_num_gpu  # pylint: disable=E0401
+
+if not import_guard.is_successful():
+    from ...utils.mocks import ModelDesc
 
 
 class ModelDescWithConfig(ModelDesc, ABC):  # type: ignore
@@ -55,7 +58,7 @@ class ModelDescWithConfig(ModelDesc, ABC):  # type: ignore
 
         :return: Tuple of list input and list output names. The names must coincide with tensor within the model.
         """
-        raise NotImplementedError
+        raise NotImplementedError()
 
 
 class TensorpackPredictor(ABC):
@@ -106,14 +109,14 @@ class TensorpackPredictor(ABC):
 
     @staticmethod
     @abstractmethod
-    def set_model(
+    def get_wrapped_model(
         path_yaml: str, categories: Mapping[str, ObjectTypes], config_overwrite: Union[List[str], None]
     ) -> ModelDescWithConfig:
         """
         Implement the config generation, its modification and instantiate a version of the model. See
         `pipe.tpfrcnn.TPFrcnnDetector` for an example
         """
-        raise NotImplementedError
+        raise NotImplementedError()
 
     @abstractmethod
     def predict(self, np_img: Any) -> Any:
@@ -121,7 +124,7 @@ class TensorpackPredictor(ABC):
         Implement, how `self.tp_predictor` is invoked and raw prediction results are generated. Do use only raw
         objects and nothing, which is related to the DD API.
         """
-        raise NotImplementedError
+        raise NotImplementedError()
 
     @property
     def model(self) -> ModelDescWithConfig:

deepdoctection/extern/tp/tpfrcnn/__init__.py

@@ -0,0 +1,20 @@
+# -*- coding: utf-8 -*-
+# File: __init__.py
+
+# Copyright 2021 Dr. Janis Meyer. All rights reserved.
+#
+# Licensed under the Apache License, Version 2.0 (the "License");
+# you may not use this file except in compliance with the License.
+# You may obtain a copy of the License at
+#
+#     http://www.apache.org/licenses/LICENSE-2.0
+#
+# Unless required by applicable law or agreed to in writing, software
+# distributed under the License is distributed on an "AS IS" BASIS,
+# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+# See the License for the specific language governing permissions and
+# limitations under the License.
+
+"""
+Init file for code for Tensorpack FRCNN example
+"""

deepdoctection/extern/tp/tpfrcnn/common.py

@@ -11,13 +11,17 @@ This file is modified from
 
 
 import numpy as np
-from tensorpack.dataflow.imgaug import ImageAugmentor, ResizeTransform  # pylint: disable=E0401
+from lazy_imports import try_import
 
-from ....utils.file_utils import cocotools_available
+with try_import() as import_guard:
+    from tensorpack.dataflow.imgaug import ImageAugmentor, ResizeTransform  # pylint: disable=E0401
 
-if cocotools_available():
+with try_import() as cc_import_guard:
     import pycocotools.mask as coco_mask
 
+if not import_guard.is_successful():
+    from ....utils.mocks import ImageAugmentor
+
 
 class CustomResize(ImageAugmentor):
     """

deepdoctection/extern/tp/tpfrcnn/config/__init__.py

@@ -0,0 +1,20 @@
+# -*- coding: utf-8 -*-
+# File: __init__.py
+
+# Copyright 2021 Dr. Janis Meyer. All rights reserved.
+#
+# Licensed under the Apache License, Version 2.0 (the "License");
+# you may not use this file except in compliance with the License.
+# You may obtain a copy of the License at
+#
+#     http://www.apache.org/licenses/LICENSE-2.0
+#
+# Unless required by applicable law or agreed to in writing, software
+# distributed under the License is distributed on an "AS IS" BASIS,
+# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+# See the License for the specific language governing permissions and
+# limitations under the License.
+
+"""
+Init file for code for Tensorpack's FRCNN configs
+"""

deepdoctection/extern/tp/tpfrcnn/config/config.py

@@ -191,16 +191,19 @@ import os
 from typing import List, Mapping, Tuple
 
 import numpy as np
-from tensorpack.tfutils import collect_env_info  # pylint: disable=E0401
-from tensorpack.utils import logger  # pylint: disable=E0401
-
-# pylint: disable=import-error
-from tensorpack.utils.gpu import get_num_gpu
+from lazy_imports import try_import
 
 from .....utils.metacfg import AttrDict
 from .....utils.settings import ObjectTypes
 
-# pylint: enable=import-error
+with try_import() as import_guard:
+    from tensorpack.tfutils import collect_env_info  # pylint: disable=E0401
+    from tensorpack.utils import logger  # pylint: disable=E0401
+
+    # pylint: disable=import-error
+    from tensorpack.utils.gpu import get_num_gpu
+
+    # pylint: enable=import-error
 
 
 __all__ = ["train_frcnn_config", "model_frcnn_config"]

deepdoctection/extern/tp/tpfrcnn/modeling/__init__.py

@@ -0,0 +1,20 @@
+# -*- coding: utf-8 -*-
+# File: __init__.py
+
+# Copyright 2021 Dr. Janis Meyer. All rights reserved.
+#
+# Licensed under the Apache License, Version 2.0 (the "License");
+# you may not use this file except in compliance with the License.
+# You may obtain a copy of the License at
+#
+#     http://www.apache.org/licenses/LICENSE-2.0
+#
+# Unless required by applicable law or agreed to in writing, software
+# distributed under the License is distributed on an "AS IS" BASIS,
+# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+# See the License for the specific language governing permissions and
+# limitations under the License.
+
+"""
+Init file for code for Tensorpack's FRCNN configs
+"""

deepdoctection/extern/tp/tpfrcnn/modeling/backbone.py

@@ -12,22 +12,30 @@ This file is modified from
 from contextlib import ExitStack, contextmanager
 
 import numpy as np
+from lazy_imports import try_import
 
 # pylint: disable=import-error
-import tensorflow as tf
-from tensorpack import tfv1
-from tensorpack.models import BatchNorm, Conv2D, MaxPooling, layer_register
-from tensorpack.tfutils import argscope
-from tensorpack.tfutils.varreplace import custom_getter_scope, freeze_variables
+
+with try_import() as import_guard:
+    import tensorflow as tf
+    from tensorpack import tfv1
+    from tensorpack.models import BatchNorm, Conv2D, MaxPooling, layer_register
+    from tensorpack.tfutils import argscope
+    from tensorpack.tfutils.varreplace import custom_getter_scope, freeze_variables
 
 # pylint: enable=import-error
 
+if not import_guard.is_successful():
+    from .....utils.mocks import layer_register
+
 
 @layer_register(log_shape=True)
-def GroupNorm(x, group=32, gamma_initializer=tf.constant_initializer(1.0)):
+def GroupNorm(x, group=32, gamma_initializer=None):
     """
     More code that reproduces the paper can be found at <https://github.com/ppwwyyxx/GroupNorm-reproduce/>.
     """
+    if gamma_initializer is None:
+        gamma_initializer = tf.constant_initializer(1.0)
     shape = x.get_shape().as_list()
     ndims = len(shape)
     assert ndims == 4, shape
@@ -153,7 +161,7 @@ def get_norm(cfg, zero_init=False):
     return lambda x: norm(layer_name, x, gamma_initializer=tf.zeros_initializer() if zero_init else None)
 
 
-def resnet_shortcut(l, n_out, stride, activation=tf.identity):
+def resnet_shortcut(l, n_out, stride, activation=None):
     """
     Defining the skip connection in bottleneck
 
@@ -163,6 +171,8 @@ def resnet_shortcut(l, n_out, stride, activation=tf.identity):
     :param activation: An activation function
     :return: tf.Tensor
     """
+    if activation is None:
+        activation = tf.identity
     n_in = l.shape[1]
     if n_in != n_out:  # change dimension when channel is not the same
         return Conv2D("convshortcut", l, n_out, 1, strides=stride, activation=activation)  # pylint: disable=E1124

deepdoctection/extern/tp/tpfrcnn/modeling/generalized_rcnn.py

@@ -9,12 +9,8 @@ This file is modified from
 <https://github.com/tensorpack/tensorpack/blob/master/examples/FasterRCNN/modeling/generalized_rcnn.py>
 """
 
-# pylint: disable=import-error
-import tensorflow as tf
-from tensorpack import tfv1
-from tensorpack.models import l2_regularizer, regularize_cost
-from tensorpack.tfutils import optimizer
-from tensorpack.tfutils.summary import add_moving_summary
+
+from lazy_imports import try_import
 
 from ...tpcompat import ModelDescWithConfig
 from ..utils.box_ops import area as tf_area
@@ -40,6 +36,16 @@ from .model_frcnn import (
 from .model_mrcnn import maskrcnn_loss, unpackbits_masks
 from .model_rpn import rpn_head
 
+with try_import() as import_guard:
+    # pylint: disable=import-error
+    import tensorflow as tf
+    from tensorpack import tfv1
+    from tensorpack.models import l2_regularizer, regularize_cost
+    from tensorpack.tfutils import optimizer
+    from tensorpack.tfutils.summary import add_moving_summary
+
+    # pylint: enable=import-error
+
 
 class GeneralizedRCNN(ModelDescWithConfig):
     """

deepdoctection/extern/tp/tpfrcnn/modeling/model_box.py

@@ -11,12 +11,17 @@ This file is modified from
 from collections import namedtuple
 
 import numpy as np
+from lazy_imports import try_import
 
-# pylint: disable=import-error
-import tensorflow as tf
-from tensorpack.tfutils.scope_utils import under_name_scope
+with try_import() as import_guard:
+    # pylint: disable=import-error
+    import tensorflow as tf
+    from tensorpack.tfutils.scope_utils import under_name_scope
 
-# pylint: enable=import-error
+    # pylint: enable=import-error
+
+if not import_guard.is_successful():
+    from .....utils.mocks import under_name_scope
 
 
 @under_name_scope()

deepdoctection/extern/tp/tpfrcnn/modeling/model_cascade.py

@@ -9,17 +9,20 @@ This file is modified from
 <https://github.com/tensorpack/tensorpack/blob/master/examples/FasterRCNN/modeling/model_cascade.py>
 """
 
-# pylint: disable=import-error
-import tensorflow as tf
-from tensorpack import tfv1
-from tensorpack.tfutils import get_current_tower_context
+from lazy_imports import try_import
 
 from ..utils.box_ops import area as tf_area
 from ..utils.box_ops import pairwise_iou
 from .model_box import clip_boxes
 from .model_frcnn import BoxProposals, FastRCNNHead, fastrcnn_outputs
 
-# pylint: enable=import-error
+with try_import() as import_guard:
+    # pylint: disable=import-error
+    import tensorflow as tf
+    from tensorpack import tfv1
+    from tensorpack.tfutils import get_current_tower_context
+
+    # pylint: enable=import-error
 
 
 class CascadeRCNNHead: