docling-ibm-models 1.3.1__py3-none-any.whl → 1.3.2__py3-none-any.whl

docling_ibm_models/tableformer/data_management/tf_predictor.py

@@ -12,7 +12,6 @@ import numpy as np
 import torch
 
 import docling_ibm_models.tableformer.common as c
-import docling_ibm_models.tableformer.data_management.functional as F
 import docling_ibm_models.tableformer.data_management.transforms as T
 import docling_ibm_models.tableformer.settings as s
 import docling_ibm_models.tableformer.utils.utils as u
@@ -21,6 +20,9 @@ from docling_ibm_models.tableformer.data_management.matching_post_processor impo
 )
 from docling_ibm_models.tableformer.data_management.tf_cell_matcher import CellMatcher
 from docling_ibm_models.tableformer.models.common.base_model import BaseModel
+from docling_ibm_models.tableformer.models.table04_rs.tablemodel04_rs import (
+    TableModel04_rs,
+)
 from docling_ibm_models.tableformer.otsl import otsl_to_html
 from docling_ibm_models.tableformer.utils.app_profiler import AggProfiler
 
@@ -187,16 +189,7 @@ class TFPredictor:
         """
 
         self._model_type = self._config["model"]["type"]
-        # Added import here to avoid loading turbotransformer library unnecessarily
-        if self._model_type == "TableModel04_rs":
-            from docling_ibm_models.tableformer.models.table04_rs.tablemodel04_rs import (  # noqa
-                TableModel04_rs,
-            )
-        for candidate in BaseModel.__subclasses__():
-            if candidate.__name__ == self._model_type:
-                model = candidate(
-                    self._config, self._init_data, s.PREDICT_PURPOSE, self._device
-                )
+        model = TableModel04_rs(self._config, self._init_data, self._device)
 
         if model is None:
             err_msg = "Not able to initiate a model for {}".format(self._model_type)
@@ -376,66 +369,6 @@ class TFPredictor:
 
         return new_bboxes
 
-    def _pad_image(self, iocr_page):
-        r"""
-        Adds padding to the image
-
-        Parameters
-        ----------
-        iocr_page : dict
-            Docling provided table data
-
-        Returns
-        -------
-        new_im: PIL image
-            new, padded image
-        new_image_ratio : float
-            Ratio of padded image size to the original image size
-        """
-        _, old_iw, old_ih = iocr_page["image"].shape
-
-        margin_i = self._padding_size  # pixels
-
-        desired_iw = old_iw + (margin_i * 2)
-        desired_ih = old_ih + (margin_i * 2)
-
-        # Ratio of new image size to the original image size
-        new_image_ratio = desired_iw / old_iw
-
-        bcolor = (255, 255, 255)
-        # Create empty canvas of background color and desired size
-        padded_image = F.pad(
-            iocr_page["image"],
-            (desired_iw, desired_ih, desired_iw, desired_ih),
-            fill=bcolor,
-        )
-        return padded_image, new_image_ratio
-
-    def _pre_process_image(self, iocr_page):
-        r"""
-        Pre-process table image in memory, before doing prediction
-        Currently just removes from the image separate PDF cells that only contain "$" sign
-        This is done to remove model confusion when dealing with financial reports
-
-        Parameters
-        ----------
-        iocr_page : dict
-            Docling provided table data
-
-        Returns
-        -------
-        iocr_page["image"] : PIL image
-            updated table image with "$" repainted
-        new_image_ratio : float
-            Ratio of padded image size to the original image size
-        """
-
-        new_image_ratio = 1.0
-
-        ic, iw, ih = iocr_page["image"].shape
-
-        return iocr_page["image"], new_image_ratio
-
     def _merge_tf_output(self, docling_output, pdf_cells):
         tf_output = []
         tf_cells_map = {}
@@ -519,6 +452,7 @@ class TFPredictor:
             sf = r
             dim = (width, int(h * r))
         # resize the image
+        # TODO(Nikos): Try to remove cv2 dependency
         resized = cv2.resize(image, dim, interpolation=inter)
         # return the resized image
         return resized, sf

docling_ibm_models/tableformer/data_management/transforms.py

@@ -13,248 +13,6 @@ import torch
 from docling_ibm_models.tableformer.data_management import functional as F
 
 
-def box_cxcywh_to_xyxy(x):
-    x_c, y_c, w, h = x.unbind(-1)
-    b = [(x_c - 0.5 * w), (y_c - 0.5 * h), (x_c + 0.5 * w), (y_c + 0.5 * h)]
-    return torch.stack(b, dim=-1)
-
-
-def box_xyxy_to_cxcywh(x):
-    x0, y0, x1, y1 = x.unbind(-1)
-    b = [(x0 + x1) / 2, (y0 + y1) / 2, (x1 - x0), (y1 - y0)]
-    return torch.stack(b, dim=-1)
-
-
-class Lambda(object):
-    """Apply a user-defined lambda as a transform.
-    Attention: The multiprocessing used in dataloader of pytorch
-    is not friendly with lambda function in Windows
-    Args:
-        lambd (function): Lambda/function to be used for transform.
-    """
-
-    def __init__(self, lambd):
-        # assert isinstance(lambd, types.LambdaType)
-        self.lambd = lambd
-        # if 'Windows' in platform.system():
-        #     raise RuntimeError("Can't pickle lambda funciton in windows system")
-
-    def __call__(self, img):
-        return self.lambd(img)
-
-    def __repr__(self):
-        return self.__class__.__name__ + "()"
-
-
-class RandomTransforms(object):
-    """Base class for a list of transformations with randomness
-    Args:
-        transforms (list or tuple): list of transformations
-    """
-
-    def __init__(self, transforms):
-        assert isinstance(transforms, (list, tuple))
-        self.transforms = transforms
-
-    def __call__(self, *args, **kwargs):
-        raise NotImplementedError()
-
-    def __repr__(self):
-        format_string = self.__class__.__name__ + "("
-        for t in self.transforms:
-            format_string += "\n"
-            format_string += "    {0}".format(t)
-        format_string += "\n)"
-        return format_string
-
-
-class RandomChoice(RandomTransforms):
-    """Apply single transformation randomly picked from a list"""
-
-    def __call__(self, img, target):
-        t = random.choice(self.transforms)
-        return t(img, target)
-
-
-class RandomCrop(object):
-    def __init__(self, size, margin_crop):
-        self.size = list(size)
-        self.margin_crop = list(margin_crop)
-        # margin_crop: w, h
-
-    def __call__(self, img, target):
-        # img (w,h,ch)
-        image_height, image_width = img.shape[0], img.shape[1]
-        """
-        img (np.ndarray): Image to be cropped.
-        x: Upper pixel coordinate.
-        y: Left pixel coordinate.
-        h: Height of the cropped image.
-        w: Width of the cropped image.
-        """
-        if image_width > 0 and image_height > 0:
-            cropped_image = F.crop(
-                img,
-                self.margin_crop[1],
-                self.margin_crop[0],
-                image_height - (self.margin_crop[1] * 2),
-                image_width - (self.margin_crop[0] * 2),
-            )
-
-            target_ = target.copy()
-            target_["boxes"][:, 0] = target_["boxes"][:, 0] - self.margin_crop[0]
-            target_["boxes"][:, 1] = target_["boxes"][:, 1] - self.margin_crop[1]
-            target_["boxes"][:, 2] = target_["boxes"][:, 2] - self.margin_crop[0]
-            target_["boxes"][:, 3] = target_["boxes"][:, 3] - self.margin_crop[1]
-        else:
-            cropped_image = img
-        return cropped_image, target_
-
-
-class RandomPad(object):
-    def __init__(self, max_pad):
-        self.max_pad = max_pad
-
-    def __call__(self, img, target):
-        pad_x = random.randint(0, self.max_pad)
-        pad_y = random.randint(0, self.max_pad)
-        pad_x1 = random.randint(0, self.max_pad)
-        pad_y1 = random.randint(0, self.max_pad)
-        img = img.copy()
-        padded_image = F.pad(img, (pad_x, pad_y, pad_x1, pad_y1), fill=(255, 255, 255))
-        target_ = target.copy()
-        if target["boxes"] is not None:
-            target_["boxes"][:, 0] = target_["boxes"][:, 0] + pad_x
-            target_["boxes"][:, 1] = target_["boxes"][:, 1] + pad_y
-            target_["boxes"][:, 2] = target_["boxes"][:, 2] + pad_x
-            target_["boxes"][:, 3] = target_["boxes"][:, 3] + pad_y
-        return padded_image, target_
-
-
-class ColorJitter(object):
-    """Randomly change the brightness, contrast and saturation of an image.
-    Args:
-        brightness (float): How much to jitter brightness. brightness_factor
-            is chosen uniformly from [max(0, 1 - brightness), 1 + brightness].
-        contrast (float): How much to jitter contrast. contrast_factor
-            is chosen uniformly from [max(0, 1 - contrast), 1 + contrast].
-        saturation (float): How much to jitter saturation. saturation_factor
-            is chosen uniformly from [max(0, 1 - saturation), 1 + saturation].
-        hue(float): How much to jitter hue. hue_factor is chosen uniformly from
-            [-hue, hue]. Should be >=0 and <= 0.5.
-    """
-
-    def __init__(self, brightness=0, contrast=0, saturation=0, hue=0):
-
-        assert isinstance(brightness, float) or (
-            isinstance(brightness, collections.Iterable) and len(brightness) == 2
-        )
-        assert isinstance(contrast, float) or (
-            isinstance(contrast, collections.Iterable) and len(contrast) == 2
-        )
-        assert isinstance(saturation, float) or (
-            isinstance(saturation, collections.Iterable) and len(saturation) == 2
-        )
-        assert isinstance(hue, float) or (
-            isinstance(hue, collections.Iterable) and len(hue) == 2
-        )
-
-        self.brightness = brightness
-        self.contrast = contrast
-        self.saturation = saturation
-        self.hue = hue
-
-    @staticmethod
-    def get_params(brightness, contrast, saturation, hue):
-        """Get a randomized transform to be applied on image.
-        Arguments are same as that of __init__.
-        Returns:
-            Transform which randomly adjusts brightness, contrast and
-            saturation in a random order.
-        """
-        transforms = []
-
-        if isinstance(brightness, numbers.Number):
-
-            if brightness > 0:
-                brightness_factor = random.uniform(
-                    max(0, 1 - brightness), 1 + brightness
-                )
-                transforms.append(
-                    Lambda(lambda img: F.adjust_brightness(img, brightness_factor))
-                )
-
-            if contrast > 0:
-                contrast_factor = random.uniform(max(0, 1 - contrast), 1 + contrast)
-                transforms.append(
-                    Lambda(lambda img: F.adjust_contrast(img, contrast_factor))
-                )
-
-            if saturation > 0:
-                saturation_factor = random.uniform(
-                    max(0, 1 - saturation), 1 + saturation
-                )
-                transforms.append(
-                    Lambda(lambda img: F.adjust_saturation(img, saturation_factor))
-                )
-
-            if hue > 0:
-                hue_factor = random.uniform(-hue, hue)
-                transforms.append(Lambda(lambda img: F.adjust_hue(img, hue_factor)))
-
-        else:
-
-            if brightness[0] > 0 and brightness[1] > 0:
-
-                brightness_factor = random.uniform(brightness[0], brightness[1])
-                transforms.append(
-                    Lambda(lambda img: F.adjust_brightness(img, brightness_factor))
-                )
-
-            if contrast[0] > 0 and contrast[1] > 0:
-
-                contrast_factor = random.uniform(contrast[0], contrast[1])
-                transforms.append(
-                    Lambda(lambda img: F.adjust_contrast(img, contrast_factor))
-                )
-
-            if saturation[0] > 0 and saturation[1] > 0:
-
-                saturation_factor = random.uniform(saturation[0], saturation[1])
-                transforms.append(
-                    Lambda(lambda img: F.adjust_saturation(img, saturation_factor))
-                )
-
-            if hue[0] > 0 and hue[1] > 0:
-                hue_factor = random.uniform(hue[0], hue[1])
-                transforms.append(Lambda(lambda img: F.adjust_hue(img, hue_factor)))
-
-        random.shuffle(transforms)
-        transform = ComposeSingle(transforms)
-
-        return transform
-
-    def __call__(self, img, target):
-        """
-        Args:
-            img (np.ndarray): Input image.
-        Returns:
-            np.ndarray: Color jittered image.
-        """
-        transform = self.get_params(
-            self.brightness, self.contrast, self.saturation, self.hue
-        )
-        return transform(img), target
-
-    def __repr__(self):
-        format_string = self.__class__.__name__ + "("
-        format_string += "brightness={0}".format(self.brightness)
-        format_string += ", contrast={0}".format(self.contrast)
-        format_string += ", saturation={0}".format(self.saturation)
-        format_string += ", hue={0})".format(self.hue)
-        return format_string
-
-
 class Normalize(object):
     """Normalize a tensor image with mean and standard deviation.
     Given mean: ``(M1,...,Mn)`` and std: ``(S1,..,Sn)`` for ``n`` channels, this transform
@@ -284,69 +42,6 @@ class Normalize(object):
         )
 
 
-class NoTransformation(object):
-    """Do Nothing"""
-
-    def __call__(self, img, target):
-        return img, target
-
-
-class Compose(object):
-    """Composes several transforms together.
-    Args:
-        transforms (list of ``Transform`` objects): list of transforms to compose.
-    Example:
-        >>> transforms.Compose([
-        >>>     transforms.CenterCrop(10),
-        >>>     transforms.ToTensor(),
-        >>> ])
-    """
-
-    def __init__(self, transforms):
-        self.transforms = transforms
-
-    def __call__(self, img, target):
-        for t in self.transforms:
-            img, target = t(img, target)
-        return img, target
-
-    def __repr__(self):
-        format_string = self.__class__.__name__ + "("
-        for t in self.transforms:
-            format_string += "\n"
-            format_string += "    {0}".format(t)
-        format_string += "\n)"
-        return format_string
-
-
-class ComposeSingle(object):
-    """Composes several transforms together.
-    Args:
-        transforms (list of ``Transform`` objects): list of transforms to compose.
-    Example:
-        >>> transforms.Compose([
-        >>>     transforms.CenterCrop(10),
-        >>>     transforms.ToTensor(),
-        >>> ])
-    """
-
-    def __init__(self, transforms):
-        self.transforms = transforms
-
-    def __call__(self, img):
-        for t in self.transforms:
-            img = t(img)
-        return img
-
-    def __repr__(self):
-        format_string = self.__class__.__name__ + "("
-        for t in self.transforms:
-            format_string += "\n"
-            format_string += "    {0}".format(t)
-        format_string += "\n)"
-        return format_string
-
-
 class Resize(object):
     """Resize the input PIL Image to the given size.
     Args:

docling_ibm_models/tableformer/models/table04_rs/tablemodel04_rs.py

@@ -26,7 +26,7 @@ class TableModel04_rs(BaseModel, nn.Module):
     TableNet04Model encoder, dual-decoder model with OTSL+ support
     """
 
-    def __init__(self, config, init_data, purpose, device):
+    def __init__(self, config, init_data, device):
         super(TableModel04_rs, self).__init__(config, init_data, device)
 
         self._prof = config["predict"].get("profiling", False)

{docling_ibm_models-1.3.1.dist-info → docling_ibm_models-1.3.2.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: docling-ibm-models
-Version: 1.3.1
+Version: 1.3.2
 Summary: This package contains the AI models used by the Docling PDF conversion package
 License: MIT
 Keywords: docling,convert,document,pdf,layout model,segmentation,table structure,table former

{docling_ibm_models-1.3.1.dist-info → docling_ibm_models-1.3.2.dist-info}/RECORD

@@ -1,32 +1,28 @@
 docling_ibm_models/layoutmodel/layout_predictor.py,sha256=JHZbh6HyA2fLqaN0p9Lv3Y9P9dgkeHUqQI-JyyetocE,6042
 docling_ibm_models/tableformer/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-docling_ibm_models/tableformer/common.py,sha256=RV2ptqgkfz1OIoN-WqiSeln0pkZ_7zTO9DhOcbvPS5k,6023
+docling_ibm_models/tableformer/common.py,sha256=VLBQ_9JWl4EsmBMSftyooIXId8FN4iTVqTIho4eNZrg,3041
 docling_ibm_models/tableformer/data_management/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-docling_ibm_models/tableformer/data_management/data_transformer.py,sha256=lNKkAk0VALbixapCuDDSIQKtA0QPCGQF8AGO3D64new,18263
-docling_ibm_models/tableformer/data_management/functional.py,sha256=UrXsEm4DSc1QXdUPb0tZ7nvbg7mGVjpQhX3pGL6C5bA,20633
+docling_ibm_models/tableformer/data_management/functional.py,sha256=kJntHEXFz2SP7obEcHyjAqZNZC9qh-U75MwUJALLADI,3143
 docling_ibm_models/tableformer/data_management/matching_post_processor.py,sha256=41GLMlkMAY1pkc-elP3ktFgZLCHjscghaHfgIVn2168,57998
 docling_ibm_models/tableformer/data_management/tf_cell_matcher.py,sha256=GaBW5px3xX9JaHVASZArKiQ-qfrzX0oj-E_6P3-OvuU,21238
-docling_ibm_models/tableformer/data_management/tf_dataset.py,sha256=6_qSsYt6qoE2JBzUNrJfCDX3Kgg7tyrv3kimGLdEQ5o,49890
-docling_ibm_models/tableformer/data_management/tf_predictor.py,sha256=32rox4--vqFddCG6oJ1_RQpIoc8nmq4ADvPpgphVR60,40959
-docling_ibm_models/tableformer/data_management/transforms.py,sha256=_i1HXkX8LAuHbeGRrg8kF9yFNJRQZOKmWzxKt559ABQ,13268
+docling_ibm_models/tableformer/data_management/tf_predictor.py,sha256=J_AjIGnpT0SkSV12comBlDa8Ga86WnsyJvKkIok4ohs,38834
+docling_ibm_models/tableformer/data_management/transforms.py,sha256=NNaz_7GI7FCVmu_rJuenqH5VfzRSljJHUHpNQQ8Mq3Q,2983
 docling_ibm_models/tableformer/models/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 docling_ibm_models/tableformer/models/common/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 docling_ibm_models/tableformer/models/common/base_model.py,sha256=SbCjeEvDmGnyoKYhB5pYeg2LFVQdArglfrhqkuW1nUw,10030
 docling_ibm_models/tableformer/models/table04_rs/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 docling_ibm_models/tableformer/models/table04_rs/bbox_decoder_rs.py,sha256=JV9rFh9caT3qnwWlZ0CZpw5aiiNzyTbfVp6H6JMxS0Q,6117
 docling_ibm_models/tableformer/models/table04_rs/encoder04_rs.py,sha256=iExmqJ0Pn0lJU3nWb_x8abTn42GctMqE55_YA2ppgvc,1975
-docling_ibm_models/tableformer/models/table04_rs/tablemodel04_rs.py,sha256=FtmWZNOKjQFLG5GtBCvvU23rWrIsDu3gqfcfl68soPg,12275
+docling_ibm_models/tableformer/models/table04_rs/tablemodel04_rs.py,sha256=Mv17JGgO12hIt8jrnflWLgOimdFYkBLuV0rxaGawBpk,12266
 docling_ibm_models/tableformer/models/table04_rs/transformer_rs.py,sha256=nhnYFlXT5KyJMdB4qMo5r8GimWXVy0lcqcmoHPEl-KE,6416
 docling_ibm_models/tableformer/otsl.py,sha256=oE_s2QHTE74jXD0vsXCuya_woReabUOBg6npprEqt58,21069
 docling_ibm_models/tableformer/settings.py,sha256=UlpsP0cpJZR2Uk48lgysYy0om3fr8Xt3z1xzvlTw5j4,3067
-docling_ibm_models/tableformer/test_dataset_cache.py,sha256=zvVJvUnYz4GxAQfPUmLTHUbqj0Yhi2vwgOBnsRgt1rI,818
-docling_ibm_models/tableformer/test_prepare_image.py,sha256=oPmU93-yWIkCeUYulGQ1p676Vq-zcjw2EX24WA5lspA,3155
 docling_ibm_models/tableformer/utils/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 docling_ibm_models/tableformer/utils/app_profiler.py,sha256=Pb7o1zcikKXh7ninaNt4_nVa1xuUrogZxbTr6U6jkEE,8392
 docling_ibm_models/tableformer/utils/mem_monitor.py,sha256=ycZ07fUBVVKKLTVGF54jGPDM2aTkKuZWk1kMbOS0wwQ,6353
 docling_ibm_models/tableformer/utils/torch_utils.py,sha256=uN0rK9mSXy1ewBnBnILrWebJhhVU4N-XJZBqNiLJwlQ,8893
 docling_ibm_models/tableformer/utils/utils.py,sha256=8Bxf1rEn977lFbY9NX0r5xh9PvxIRipQZX_EZW92XfA,10980
-docling_ibm_models-1.3.1.dist-info/LICENSE,sha256=mBb7ErEcM8VS9OhiGHnQ2kk75HwPhr54W1Oiz3965MY,1088
-docling_ibm_models-1.3.1.dist-info/METADATA,sha256=W7euvW9ItpwNBZbYXelzFY_O1sseHNe0HO4sJdO3Hbo,7088
-docling_ibm_models-1.3.1.dist-info/WHEEL,sha256=sP946D7jFCHeNz5Iq4fL4Lu-PrWrFsgfLXbbkciIZwg,88
-docling_ibm_models-1.3.1.dist-info/RECORD,,
+docling_ibm_models-1.3.2.dist-info/LICENSE,sha256=mBb7ErEcM8VS9OhiGHnQ2kk75HwPhr54W1Oiz3965MY,1088
+docling_ibm_models-1.3.2.dist-info/METADATA,sha256=JoQmgI44L9riX-SDDwu0w9rWu9l4hsuKoaGok5cnoHE,7088
+docling_ibm_models-1.3.2.dist-info/WHEEL,sha256=sP946D7jFCHeNz5Iq4fL4Lu-PrWrFsgfLXbbkciIZwg,88
+docling_ibm_models-1.3.2.dist-info/RECORD,,