python-doctr 0.8.1__py3-none-any.whl → 0.9.0__py3-none-any.whl

doctr/transforms/modules/tensorflow.py

@@ -4,7 +4,7 @@
 # See LICENSE or go to <https://opensource.org/licenses/Apache-2.0> for full license details.
 
 import random
-from typing import Any, Callable, Dict, Iterable, List, Optional, Tuple, Union
+from typing import Any, Callable, Iterable, List, Optional, Tuple, Union
 
 import numpy as np
 import tensorflow as tf
@@ -30,6 +30,7 @@ __all__ = [
     "GaussianNoise",
     "RandomHorizontalFlip",
     "RandomShadow",
+    "RandomResize",
 ]
 
 
@@ -457,10 +458,7 @@ class RandomHorizontalFlip(NestedObject):
     >>> from doctr.transforms import RandomHorizontalFlip
     >>> transfo = RandomHorizontalFlip(p=0.5)
     >>> image = tf.random.uniform(shape=[64, 64, 3], minval=0, maxval=1)
-    >>> target = {
-    >>> "boxes": np.array([[0.1, 0.1, 0.4, 0.5] ], dtype= np.float32),
-    >>> "labels": np.ones(1, dtype= np.int64)
-    >>> }
+    >>> target = np.array([[0.1, 0.1, 0.4, 0.5] ], dtype= np.float32)
     >>> out = transfo(image, target)
 
     Args:
@@ -472,12 +470,15 @@ class RandomHorizontalFlip(NestedObject):
         super().__init__()
         self.p = p
 
-    def __call__(self, img: Union[tf.Tensor, np.ndarray], target: Dict[str, Any]) -> Tuple[tf.Tensor, Dict[str, Any]]:
+    def __call__(self, img: Union[tf.Tensor, np.ndarray], target: np.ndarray) -> Tuple[tf.Tensor, np.ndarray]:
         if np.random.rand(1) <= self.p:
             _img = tf.image.flip_left_right(img)
             _target = target.copy()
             # Changing the relative bbox coordinates
-            _target["boxes"][:, ::2] = 1 - target["boxes"][:, [2, 0]]
+            if target.shape[1:] == (4,):
+                _target[:, ::2] = 1 - target[:, [2, 0]]
+            else:
+                _target[..., 0] = 1 - target[..., 0]
             return _img, _target
         return img, target
 
@@ -515,3 +516,58 @@ class RandomShadow(NestedObject):
 
     def extra_repr(self) -> str:
         return f"opacity_range={self.opacity_range}"
+
+
+class RandomResize(NestedObject):
+    """Randomly resize the input image and align corresponding targets
+
+    >>> import tensorflow as tf
+    >>> from doctr.transforms import RandomResize
+    >>> transfo = RandomResize((0.3, 0.9), preserve_aspect_ratio=True, symmetric_pad=True, p=0.5)
+    >>> out = transfo(tf.random.uniform(shape=[64, 64, 3], minval=0, maxval=1))
+
+    Args:
+    ----
+        scale_range: range of the resizing factor for width and height (independently)
+        preserve_aspect_ratio: whether to preserve the aspect ratio of the image,
+            given a float value, the aspect ratio will be preserved with this probability
+        symmetric_pad: whether to symmetrically pad the image,
+            given a float value, the symmetric padding will be applied with this probability
+        p: probability to apply the transformation
+    """
+
+    def __init__(
+        self,
+        scale_range: Tuple[float, float] = (0.3, 0.9),
+        preserve_aspect_ratio: Union[bool, float] = False,
+        symmetric_pad: Union[bool, float] = False,
+        p: float = 0.5,
+    ):
+        super().__init__()
+        self.scale_range = scale_range
+        self.preserve_aspect_ratio = preserve_aspect_ratio
+        self.symmetric_pad = symmetric_pad
+        self.p = p
+        self._resize = Resize
+
+    def __call__(self, img: tf.Tensor, target: np.ndarray) -> Tuple[tf.Tensor, np.ndarray]:
+        if np.random.rand(1) <= self.p:
+            scale_h = random.uniform(*self.scale_range)
+            scale_w = random.uniform(*self.scale_range)
+            new_size = (int(img.shape[-3] * scale_h), int(img.shape[-2] * scale_w))
+
+            _img, _target = self._resize(
+                new_size,
+                preserve_aspect_ratio=self.preserve_aspect_ratio
+                if isinstance(self.preserve_aspect_ratio, bool)
+                else bool(np.random.rand(1) <= self.symmetric_pad),
+                symmetric_pad=self.symmetric_pad
+                if isinstance(self.symmetric_pad, bool)
+                else bool(np.random.rand(1) <= self.symmetric_pad),
+            )(img, target)
+
+            return _img, _target
+        return img, target
+
+    def extra_repr(self) -> str:
+        return f"scale_range={self.scale_range}, preserve_aspect_ratio={self.preserve_aspect_ratio}, symmetric_pad={self.symmetric_pad}, p={self.p}"  # noqa: E501

doctr/utils/fonts.py

@@ -5,14 +5,16 @@
 
 import logging
 import platform
-from typing import Optional
+from typing import Optional, Union
 
 from PIL import ImageFont
 
 __all__ = ["get_font"]
 
 
-def get_font(font_family: Optional[str] = None, font_size: int = 13) -> ImageFont.ImageFont:
+def get_font(
+    font_family: Optional[str] = None, font_size: int = 13
+) -> Union[ImageFont.FreeTypeFont, ImageFont.ImageFont]:
     """Resolves a compatible ImageFont for the system
 
     Args:
@@ -28,14 +30,14 @@ def get_font(font_family: Optional[str] = None, font_size: int = 13) -> ImageFon
     if font_family is None:
         try:
             font = ImageFont.truetype("FreeMono.ttf" if platform.system() == "Linux" else "Arial.ttf", font_size)
-        except OSError:
-            font = ImageFont.load_default()
+        except OSError:  # pragma: no cover
+            font = ImageFont.load_default()  # type: ignore[assignment]
             logging.warning(
                 "unable to load recommended font family. Loading default PIL font,"
                 "font size issues may be expected."
                 "To prevent this, it is recommended to specify the value of 'font_family'."
             )
-    else:
+    else:  # pragma: no cover
         font = ImageFont.truetype(font_family, font_size)
 
     return font

doctr/utils/geometry.py

@@ -25,6 +25,7 @@ __all__ = [
     "rotate_abs_geoms",
     "extract_crops",
     "extract_rcrops",
+    "detach_scores",
 ]
 
 
@@ -57,6 +58,28 @@ def polygon_to_bbox(polygon: Polygon4P) -> BoundingBox:
     return (min(x), min(y)), (max(x), max(y))
 
 
+def detach_scores(boxes: List[np.ndarray]) -> Tuple[List[np.ndarray], List[np.ndarray]]:
+    """Detach the objectness scores from box predictions
+
+    Args:
+    ----
+        boxes: list of arrays with boxes of shape (N, 5) or (N, 5, 2)
+
+    Returns:
+    -------
+        a tuple of two lists: the first one contains the boxes without the objectness scores,
+        the second one contains the objectness scores
+    """
+
+    def _detach(boxes: np.ndarray) -> Tuple[np.ndarray, np.ndarray]:
+        if boxes.ndim == 2:
+            return boxes[:, :-1], boxes[:, -1]
+        return boxes[:, :-1], boxes[:, -1, -1]
+
+    loc_preds, obj_scores = zip(*(_detach(box) for box in boxes))
+    return list(loc_preds), list(obj_scores)
+
+
 def resolve_enclosing_bbox(bboxes: Union[List[BoundingBox], np.ndarray]) -> Union[BoundingBox, np.ndarray]:
     """Compute enclosing bbox either from:
 
@@ -64,18 +87,18 @@ def resolve_enclosing_bbox(bboxes: Union[List[BoundingBox], np.ndarray]) -> Unio
     ----
         bboxes: boxes in one of the following formats:
 
-            - an array of boxes: (*, 5), where boxes have this shape:
-            (xmin, ymin, xmax, ymax, score)
+            - an array of boxes: (*, 4), where boxes have this shape:
+            (xmin, ymin, xmax, ymax)
 
             - a list of BoundingBox
 
     Returns:
     -------
-        a (1, 5) array (enclosing boxarray), or a BoundingBox
+        a (1, 4) array (enclosing boxarray), or a BoundingBox
     """
     if isinstance(bboxes, np.ndarray):
-        xmin, ymin, xmax, ymax, score = np.split(bboxes, 5, axis=1)
-        return np.array([xmin.min(), ymin.min(), xmax.max(), ymax.max(), score.mean()])
+        xmin, ymin, xmax, ymax = np.split(bboxes, 4, axis=1)
+        return np.array([xmin.min(), ymin.min(), xmax.max(), ymax.max()])
     else:
         x, y = zip(*[point for box in bboxes for point in box])
         return (min(x), min(y)), (max(x), max(y))
@@ -88,21 +111,21 @@ def resolve_enclosing_rbbox(rbboxes: List[np.ndarray], intermed_size: int = 1024
     ----
         rbboxes: boxes in one of the following formats:
 
-            - an array of boxes: (*, 5), where boxes have this shape:
-            (xmin, ymin, xmax, ymax, score)
+            - an array of boxes: (*, 4, 2), where boxes have this shape:
+            (x1, y1), (x2, y2), (x3, y3), (x4, y4)
 
             - a list of BoundingBox
         intermed_size: size of the intermediate image
 
     Returns:
     -------
-        a (1, 5) array (enclosing boxarray), or a BoundingBox
+        a (4, 2) array (enclosing rotated box)
     """
     cloud: np.ndarray = np.concatenate(rbboxes, axis=0)
     # Convert to absolute for minAreaRect
     cloud *= intermed_size
     rect = cv2.minAreaRect(cloud.astype(np.int32))
-    return cv2.boxPoints(rect) / intermed_size  # type: ignore[operator]
+    return cv2.boxPoints(rect) / intermed_size  # type: ignore[return-value]
 
 
 def rotate_abs_points(points: np.ndarray, angle: float = 0.0) -> np.ndarray:
@@ -232,7 +255,7 @@ def rotate_boxes(
 
     Args:
     ----
-        loc_preds: (N, 5) or (N, 4, 2) array of RELATIVE boxes
+        loc_preds: (N, 4) or (N, 4, 2) array of RELATIVE boxes
         angle: angle between -90 and +90 degrees
         orig_shape: shape of the origin image
         min_angle: minimum angle to rotate boxes
@@ -320,7 +343,7 @@ def rotate_image(
             # Pad height
             else:
                 h_pad, w_pad = int(rot_img.shape[1] * image.shape[0] / image.shape[1] - rot_img.shape[0]), 0
-            rot_img = np.pad(rot_img, ((h_pad // 2, h_pad - h_pad // 2), (w_pad // 2, w_pad - w_pad // 2), (0, 0)))
+            rot_img = np.pad(rot_img, ((h_pad // 2, h_pad - h_pad // 2), (w_pad // 2, w_pad - w_pad // 2), (0, 0)))  # type: ignore[assignment]
         if preserve_origin_shape:
             # rescale
             rot_img = cv2.resize(rot_img, image.shape[:-1][::-1], interpolation=cv2.INTER_LINEAR)
@@ -453,4 +476,4 @@ def extract_rcrops(
         )
         for idx in range(_boxes.shape[0])
     ]
-    return crops
+    return crops  # type: ignore[return-value]

doctr/utils/metrics.py

@@ -5,16 +5,14 @@
 
 from typing import Dict, List, Optional, Tuple
 
-import cv2
 import numpy as np
+from anyascii import anyascii
 from scipy.optimize import linear_sum_assignment
-from unidecode import unidecode
+from shapely.geometry import Polygon
 
 __all__ = [
     "TextMatch",
     "box_iou",
-    "box_ioa",
-    "mask_iou",
     "polygon_iou",
     "nms",
     "LocalizationConfusion",
@@ -34,16 +32,16 @@ def string_match(word1: str, word2: str) -> Tuple[bool, bool, bool, bool]:
     Returns:
     -------
         a tuple with booleans specifying respectively whether the raw strings, their lower-case counterparts, their
-            unidecode counterparts and their lower-case unidecode counterparts match
+            anyascii counterparts and their lower-case anyascii counterparts match
     """
     raw_match = word1 == word2
     caseless_match = word1.lower() == word2.lower()
-    unidecode_match = unidecode(word1) == unidecode(word2)
+    anyascii_match = anyascii(word1) == anyascii(word2)
 
     # Warning: the order is important here otherwise the pair ("EUR", "€") cannot be matched
-    unicase_match = unidecode(word1).lower() == unidecode(word2).lower()
+    unicase_match = anyascii(word1).lower() == anyascii(word2).lower()
 
-    return raw_match, caseless_match, unidecode_match, unicase_match
+    return raw_match, caseless_match, anyascii_match, unicase_match
 
 
 class TextMatch:
@@ -94,10 +92,10 @@ class TextMatch:
             raise AssertionError("prediction size does not match with ground-truth labels size")
 
         for gt_word, pred_word in zip(gt, pred):
-            _raw, _caseless, _unidecode, _unicase = string_match(gt_word, pred_word)
+            _raw, _caseless, _anyascii, _unicase = string_match(gt_word, pred_word)
             self.raw += int(_raw)
             self.caseless += int(_caseless)
-            self.unidecode += int(_unidecode)
+            self.anyascii += int(_anyascii)
             self.unicase += int(_unicase)
 
         self.total += len(gt)
@@ -107,8 +105,8 @@ class TextMatch:
 
         Returns
         -------
-            a dictionary with the exact match score for the raw data, its lower-case counterpart, its unidecode
-            counterpart and its lower-case unidecode counterpart
+            a dictionary with the exact match score for the raw data, its lower-case counterpart, its anyascii
+            counterpart and its lower-case anyascii counterpart
         """
         if self.total == 0:
             raise AssertionError("you need to update the metric before getting the summary")
@@ -116,14 +114,14 @@ class TextMatch:
         return dict(
             raw=self.raw / self.total,
             caseless=self.caseless / self.total,
-            unidecode=self.unidecode / self.total,
+            anyascii=self.anyascii / self.total,
             unicase=self.unicase / self.total,
         )
 
     def reset(self) -> None:
         self.raw = 0
         self.caseless = 0
-        self.unidecode = 0
+        self.anyascii = 0
         self.unicase = 0
         self.total = 0
 
@@ -158,66 +156,7 @@ def box_iou(boxes_1: np.ndarray, boxes_2: np.ndarray) -> np.ndarray:
     return iou_mat
 
 
-def box_ioa(boxes_1: np.ndarray, boxes_2: np.ndarray) -> np.ndarray:
-    """Computes the IoA (intersection over area) between two sets of bounding boxes:
-    ioa(i, j) = inter(i, j) / area(i)
-
-    Args:
-    ----
-        boxes_1: bounding boxes of shape (N, 4) in format (xmin, ymin, xmax, ymax)
-        boxes_2: bounding boxes of shape (M, 4) in format (xmin, ymin, xmax, ymax)
-
-    Returns:
-    -------
-        the IoA matrix of shape (N, M)
-    """
-    ioa_mat: np.ndarray = np.zeros((boxes_1.shape[0], boxes_2.shape[0]), dtype=np.float32)
-
-    if boxes_1.shape[0] > 0 and boxes_2.shape[0] > 0:
-        l1, t1, r1, b1 = np.split(boxes_1, 4, axis=1)
-        l2, t2, r2, b2 = np.split(boxes_2, 4, axis=1)
-
-        left = np.maximum(l1, l2.T)
-        top = np.maximum(t1, t2.T)
-        right = np.minimum(r1, r2.T)
-        bot = np.minimum(b1, b2.T)
-
-        intersection = np.clip(right - left, 0, np.Inf) * np.clip(bot - top, 0, np.Inf)
-        area = (r1 - l1) * (b1 - t1)
-        ioa_mat = intersection / area
-
-    return ioa_mat
-
-
-def mask_iou(masks_1: np.ndarray, masks_2: np.ndarray) -> np.ndarray:
-    """Computes the IoU between two sets of boolean masks
-
-    Args:
-    ----
-        masks_1: boolean masks of shape (N, H, W)
-        masks_2: boolean masks of shape (M, H, W)
-
-    Returns:
-    -------
-        the IoU matrix of shape (N, M)
-    """
-    if masks_1.shape[1:] != masks_2.shape[1:]:
-        raise AssertionError("both boolean masks should have the same spatial shape")
-
-    iou_mat: np.ndarray = np.zeros((masks_1.shape[0], masks_2.shape[0]), dtype=np.float32)
-
-    if masks_1.shape[0] > 0 and masks_2.shape[0] > 0:
-        axes = tuple(range(2, masks_1.ndim + 1))
-        intersection = np.logical_and(masks_1[:, None, ...], masks_2[None, ...]).sum(axis=axes)
-        union = np.logical_or(masks_1[:, None, ...], masks_2[None, ...]).sum(axis=axes)
-        iou_mat = intersection / union
-
-    return iou_mat
-
-
-def polygon_iou(
-    polys_1: np.ndarray, polys_2: np.ndarray, mask_shape: Tuple[int, int], use_broadcasting: bool = False
-) -> np.ndarray:
+def polygon_iou(polys_1: np.ndarray, polys_2: np.ndarray) -> np.ndarray:
     """Computes the IoU between two sets of rotated bounding boxes
 
     Args:
@@ -234,80 +173,18 @@ def polygon_iou(
     if polys_1.ndim != 3 or polys_2.ndim != 3:
         raise AssertionError("expects boxes to be in format (N, 4, 2)")
 
-    iou_mat: np.ndarray = np.zeros((polys_1.shape[0], polys_2.shape[0]), dtype=np.float32)
-
-    if polys_1.shape[0] > 0 and polys_2.shape[0] > 0:
-        if use_broadcasting:
-            masks_1 = rbox_to_mask(polys_1, shape=mask_shape)
-            masks_2 = rbox_to_mask(polys_2, shape=mask_shape)
-            iou_mat = mask_iou(masks_1, masks_2)
-        else:
-            # Save memory by doing the computation for each pair
-            for idx, b1 in enumerate(polys_1):
-                m1 = _rbox_to_mask(b1, mask_shape)
-                for _idx, b2 in enumerate(polys_2):
-                    m2 = _rbox_to_mask(b2, mask_shape)
-                    iou_mat[idx, _idx] = np.logical_and(m1, m2).sum() / np.logical_or(m1, m2).sum()
-
-    return iou_mat
+    iou_mat = np.zeros((polys_1.shape[0], polys_2.shape[0]), dtype=np.float32)
 
+    shapely_polys_1 = [Polygon(poly) for poly in polys_1]
+    shapely_polys_2 = [Polygon(poly) for poly in polys_2]
 
-def _rbox_to_mask(box: np.ndarray, shape: Tuple[int, int]) -> np.ndarray:
-    """Converts a rotated bounding box to a boolean mask
+    for i, poly1 in enumerate(shapely_polys_1):
+        for j, poly2 in enumerate(shapely_polys_2):
+            intersection_area = poly1.intersection(poly2).area
+            union_area = poly1.area + poly2.area - intersection_area
+            iou_mat[i, j] = intersection_area / union_area
 
-    Args:
-    ----
-        box: rotated bounding box of shape (4, 2)
-        shape: spatial shapes of the output masks
-
-    Returns:
-    -------
-        the boolean mask of the specified shape
-    """
-    mask: np.ndarray = np.zeros(shape, dtype=np.uint8)
-    # Get absolute coords
-    if not np.issubdtype(box.dtype, np.integer):
-        abs_box = box.copy()
-        abs_box[:, 0] = abs_box[:, 0] * shape[1]
-        abs_box[:, 1] = abs_box[:, 1] * shape[0]
-        abs_box = abs_box.round().astype(int)
-    else:
-        abs_box = box
-        abs_box[2:] = abs_box[2:] + 1
-    cv2.fillPoly(mask, [abs_box - 1], 1.0)  # type: ignore[call-overload]
-
-    return mask.astype(bool)
-
-
-def rbox_to_mask(boxes: np.ndarray, shape: Tuple[int, int]) -> np.ndarray:
-    """Converts rotated bounding boxes to boolean masks
-
-    Args:
-    ----
-        boxes: rotated bounding boxes of shape (N, 4, 2)
-        shape: spatial shapes of the output masks
-
-    Returns:
-    -------
-        the boolean masks of shape (N, H, W)
-    """
-    masks: np.ndarray = np.zeros((boxes.shape[0], *shape), dtype=np.uint8)
-
-    if boxes.shape[0] > 0:
-        # Get absolute coordinates
-        if not np.issubdtype(boxes.dtype, np.integer):
-            abs_boxes = boxes.copy()
-            abs_boxes[:, :, 0] = abs_boxes[:, :, 0] * shape[1]
-            abs_boxes[:, :, 1] = abs_boxes[:, :, 1] * shape[0]
-            abs_boxes = abs_boxes.round().astype(int)
-        else:
-            abs_boxes = boxes
-            abs_boxes[:, 2:] = abs_boxes[:, 2:] + 1
-
-        # TODO: optimize slicing to improve vectorization
-        for idx, _box in enumerate(abs_boxes):
-            cv2.fillPoly(masks[idx], [_box - 1], 1.0)  # type: ignore[call-overload]
-    return masks.astype(bool)
+    return iou_mat
 
 
 def nms(boxes: np.ndarray, thresh: float = 0.5) -> List[int]:
@@ -386,21 +263,15 @@ class LocalizationConfusion:
     ----
         iou_thresh: minimum IoU to consider a pair of prediction and ground truth as a match
         use_polygons: if set to True, predictions and targets will be expected to have rotated format
-        mask_shape: if use_polygons is True, describes the spatial shape of the image used
-        use_broadcasting: if use_polygons is True, use broadcasting for IoU computation by consuming more memory
     """
 
     def __init__(
         self,
         iou_thresh: float = 0.5,
         use_polygons: bool = False,
-        mask_shape: Tuple[int, int] = (1024, 1024),
-        use_broadcasting: bool = True,
     ) -> None:
         self.iou_thresh = iou_thresh
         self.use_polygons = use_polygons
-        self.mask_shape = mask_shape
-        self.use_broadcasting = use_broadcasting
         self.reset()
 
     def update(self, gts: np.ndarray, preds: np.ndarray) -> None:
@@ -414,7 +285,7 @@ class LocalizationConfusion:
         if preds.shape[0] > 0:
             # Compute IoU
             if self.use_polygons:
-                iou_mat = polygon_iou(gts, preds, self.mask_shape, self.use_broadcasting)
+                iou_mat = polygon_iou(gts, preds)
             else:
                 iou_mat = box_iou(gts, preds)
             self.tot_iou += float(iou_mat.max(axis=0).sum())
@@ -441,7 +312,7 @@ class LocalizationConfusion:
         precision = self.matches / self.num_preds if self.num_preds > 0 else None
 
         # mean IoU
-        mean_iou = self.tot_iou / self.num_preds if self.num_preds > 0 else None
+        mean_iou = round(self.tot_iou / self.num_preds, 2) if self.num_preds > 0 else None
 
         return recall, precision, mean_iou
 
@@ -492,21 +363,15 @@ class OCRMetric:
     ----
         iou_thresh: minimum IoU to consider a pair of prediction and ground truth as a match
         use_polygons: if set to True, predictions and targets will be expected to have rotated format
-        mask_shape: if use_polygons is True, describes the spatial shape of the image used
-        use_broadcasting: if use_polygons is True, use broadcasting for IoU computation by consuming more memory
     """
 
     def __init__(
         self,
         iou_thresh: float = 0.5,
         use_polygons: bool = False,
-        mask_shape: Tuple[int, int] = (1024, 1024),
-        use_broadcasting: bool = True,
     ) -> None:
         self.iou_thresh = iou_thresh
         self.use_polygons = use_polygons
-        self.mask_shape = mask_shape
-        self.use_broadcasting = use_broadcasting
         self.reset()
 
     def update(
@@ -533,7 +398,7 @@ class OCRMetric:
         # Compute IoU
         if pred_boxes.shape[0] > 0:
             if self.use_polygons:
-                iou_mat = polygon_iou(gt_boxes, pred_boxes, self.mask_shape, self.use_broadcasting)
+                iou_mat = polygon_iou(gt_boxes, pred_boxes)
             else:
                 iou_mat = box_iou(gt_boxes, pred_boxes)
 
@@ -544,10 +409,10 @@ class OCRMetric:
             is_kept = iou_mat[gt_indices, pred_indices] >= self.iou_thresh
             # String comparison
             for gt_idx, pred_idx in zip(gt_indices[is_kept], pred_indices[is_kept]):
-                _raw, _caseless, _unidecode, _unicase = string_match(gt_labels[gt_idx], pred_labels[pred_idx])
+                _raw, _caseless, _anyascii, _unicase = string_match(gt_labels[gt_idx], pred_labels[pred_idx])
                 self.raw_matches += int(_raw)
                 self.caseless_matches += int(_caseless)
-                self.unidecode_matches += int(_unidecode)
+                self.anyascii_matches += int(_anyascii)
                 self.unicase_matches += int(_unicase)
 
         self.num_gts += gt_boxes.shape[0]
@@ -564,7 +429,7 @@ class OCRMetric:
         recall = dict(
             raw=self.raw_matches / self.num_gts if self.num_gts > 0 else None,
             caseless=self.caseless_matches / self.num_gts if self.num_gts > 0 else None,
-            unidecode=self.unidecode_matches / self.num_gts if self.num_gts > 0 else None,
+            anyascii=self.anyascii_matches / self.num_gts if self.num_gts > 0 else None,
             unicase=self.unicase_matches / self.num_gts if self.num_gts > 0 else None,
         )
 
@@ -572,12 +437,12 @@ class OCRMetric:
         precision = dict(
             raw=self.raw_matches / self.num_preds if self.num_preds > 0 else None,
             caseless=self.caseless_matches / self.num_preds if self.num_preds > 0 else None,
-            unidecode=self.unidecode_matches / self.num_preds if self.num_preds > 0 else None,
+            anyascii=self.anyascii_matches / self.num_preds if self.num_preds > 0 else None,
             unicase=self.unicase_matches / self.num_preds if self.num_preds > 0 else None,
         )
 
         # mean IoU (overall detected boxes)
-        mean_iou = self.tot_iou / self.num_preds if self.num_preds > 0 else None
+        mean_iou = round(self.tot_iou / self.num_preds, 2) if self.num_preds > 0 else None
 
         return recall, precision, mean_iou
 
@@ -587,7 +452,7 @@ class OCRMetric:
         self.tot_iou = 0.0
         self.raw_matches = 0
         self.caseless_matches = 0
-        self.unidecode_matches = 0
+        self.anyascii_matches = 0
         self.unicase_matches = 0
 
 
@@ -631,21 +496,15 @@ class DetectionMetric:
     ----
         iou_thresh: minimum IoU to consider a pair of prediction and ground truth as a match
         use_polygons: if set to True, predictions and targets will be expected to have rotated format
-        mask_shape: if use_polygons is True, describes the spatial shape of the image used
-        use_broadcasting: if use_polygons is True, use broadcasting for IoU computation by consuming more memory
     """
 
     def __init__(
         self,
         iou_thresh: float = 0.5,
         use_polygons: bool = False,
-        mask_shape: Tuple[int, int] = (1024, 1024),
-        use_broadcasting: bool = True,
     ) -> None:
         self.iou_thresh = iou_thresh
         self.use_polygons = use_polygons
-        self.mask_shape = mask_shape
-        self.use_broadcasting = use_broadcasting
         self.reset()
 
     def update(
@@ -672,7 +531,7 @@ class DetectionMetric:
         # Compute IoU
         if pred_boxes.shape[0] > 0:
             if self.use_polygons:
-                iou_mat = polygon_iou(gt_boxes, pred_boxes, self.mask_shape, self.use_broadcasting)
+                iou_mat = polygon_iou(gt_boxes, pred_boxes)
             else:
                 iou_mat = box_iou(gt_boxes, pred_boxes)
 
@@ -701,7 +560,7 @@ class DetectionMetric:
         precision = self.num_matches / self.num_preds if self.num_preds > 0 else None
 
         # mean IoU (overall detected boxes)
-        mean_iou = self.tot_iou / self.num_preds if self.num_preds > 0 else None
+        mean_iou = round(self.tot_iou / self.num_preds, 2) if self.num_preds > 0 else None
 
         return recall, precision, mean_iou