python-doctr 0.9.0__py3-none-any.whl → 0.11.0__py3-none-any.whl

doctr/datasets/generator/base.py

@@ -1,10 +1,11 @@
-# Copyright (C) 2021-2024, Mindee.
+# Copyright (C) 2021-2025, Mindee.
 
 # This program is licensed under the Apache License 2.0.
 # See LICENSE or go to <https://opensource.org/licenses/Apache-2.0> for full license details.
 
 import random
-from typing import Any, Callable, List, Optional, Tuple, Union
+from collections.abc import Callable
+from typing import Any
 
 from PIL import Image, ImageDraw
 
@@ -17,14 +18,13 @@ from ..datasets import AbstractDataset
 def synthesize_text_img(
     text: str,
     font_size: int = 32,
-    font_family: Optional[str] = None,
-    background_color: Optional[Tuple[int, int, int]] = None,
-    text_color: Optional[Tuple[int, int, int]] = None,
+    font_family: str | None = None,
+    background_color: tuple[int, int, int] | None = None,
+    text_color: tuple[int, int, int] | None = None,
 ) -> Image.Image:
     """Generate a synthetic text image
 
     Args:
-    ----
         text: the text to render as an image
         font_size: the size of the font
         font_family: the font family (has to be installed on your system)
@@ -32,7 +32,6 @@ def synthesize_text_img(
         text_color: text color on the final image
 
     Returns:
-    -------
         PIL image of the text
     """
     background_color = (0, 0, 0) if background_color is None else background_color
@@ -61,9 +60,9 @@ class _CharacterGenerator(AbstractDataset):
         vocab: str,
         num_samples: int,
         cache_samples: bool = False,
-        font_family: Optional[Union[str, List[str]]] = None,
-        img_transforms: Optional[Callable[[Any], Any]] = None,
-        sample_transforms: Optional[Callable[[Any, Any], Tuple[Any, Any]]] = None,
+        font_family: str | list[str] | None = None,
+        img_transforms: Callable[[Any], Any] | None = None,
+        sample_transforms: Callable[[Any, Any], tuple[Any, Any]] | None = None,
     ) -> None:
         self.vocab = vocab
         self._num_samples = num_samples
@@ -78,7 +77,7 @@ class _CharacterGenerator(AbstractDataset):
         self.img_transforms = img_transforms
         self.sample_transforms = sample_transforms
 
-        self._data: List[Image.Image] = []
+        self._data: list[Image.Image] = []
         if cache_samples:
             self._data = [
                 (synthesize_text_img(char, font_family=font), idx)  # type: ignore[misc]
@@ -89,7 +88,7 @@ class _CharacterGenerator(AbstractDataset):
     def __len__(self) -> int:
         return self._num_samples
 
-    def _read_sample(self, index: int) -> Tuple[Any, int]:
+    def _read_sample(self, index: int) -> tuple[Any, int]:
         # Samples are already cached
         if len(self._data) > 0:
             idx = index % len(self._data)
@@ -110,9 +109,9 @@ class _WordGenerator(AbstractDataset):
         max_chars: int,
         num_samples: int,
         cache_samples: bool = False,
-        font_family: Optional[Union[str, List[str]]] = None,
-        img_transforms: Optional[Callable[[Any], Any]] = None,
-        sample_transforms: Optional[Callable[[Any, Any], Tuple[Any, Any]]] = None,
+        font_family: str | list[str] | None = None,
+        img_transforms: Callable[[Any], Any] | None = None,
+        sample_transforms: Callable[[Any, Any], tuple[Any, Any]] | None = None,
     ) -> None:
         self.vocab = vocab
         self.wordlen_range = (min_chars, max_chars)
@@ -128,7 +127,7 @@ class _WordGenerator(AbstractDataset):
         self.img_transforms = img_transforms
         self.sample_transforms = sample_transforms
 
-        self._data: List[Image.Image] = []
+        self._data: list[Image.Image] = []
         if cache_samples:
             _words = [self._generate_string(*self.wordlen_range) for _ in range(num_samples)]
             self._data = [
@@ -143,7 +142,7 @@ class _WordGenerator(AbstractDataset):
     def __len__(self) -> int:
         return self._num_samples
 
-    def _read_sample(self, index: int) -> Tuple[Any, str]:
+    def _read_sample(self, index: int) -> tuple[Any, str]:
         # Samples are already cached
         if len(self._data) > 0:
             pil_img, target = self._data[index]  # type: ignore[misc]

doctr/datasets/generator/pytorch.py

@@ -1,4 +1,4 @@
-# Copyright (C) 2021-2024, Mindee.
+# Copyright (C) 2021-2025, Mindee.
 
 # This program is licensed under the Apache License 2.0.
 # See LICENSE or go to <https://opensource.org/licenses/Apache-2.0> for full license details.
@@ -18,7 +18,6 @@ class CharacterGenerator(_CharacterGenerator):
     >>> img, target = ds[0]
 
     Args:
-    ----
         vocab: vocabulary to take the character from
         num_samples: number of samples that will be generated iterating over the dataset
         cache_samples: whether generated images should be cached firsthand
@@ -40,7 +39,6 @@ class WordGenerator(_WordGenerator):
     >>> img, target = ds[0]
 
     Args:
-    ----
         vocab: vocabulary to take the character from
         min_chars: minimum number of characters in a word
         max_chars: maximum number of characters in a word

doctr/datasets/generator/tensorflow.py

@@ -1,4 +1,4 @@
-# Copyright (C) 2021-2024, Mindee.
+# Copyright (C) 2021-2025, Mindee.
 
 # This program is licensed under the Apache License 2.0.
 # See LICENSE or go to <https://opensource.org/licenses/Apache-2.0> for full license details.
@@ -18,7 +18,6 @@ class CharacterGenerator(_CharacterGenerator):
     >>> img, target = ds[0]
 
     Args:
-    ----
         vocab: vocabulary to take the character from
         num_samples: number of samples that will be generated iterating over the dataset
         cache_samples: whether generated images should be cached firsthand
@@ -46,7 +45,6 @@ class WordGenerator(_WordGenerator):
     >>> img, target = ds[0]
 
     Args:
-    ----
         vocab: vocabulary to take the character from
         min_chars: minimum number of characters in a word
         max_chars: maximum number of characters in a word

doctr/datasets/ic03.py

@@ -1,10 +1,10 @@
-# Copyright (C) 2021-2024, Mindee.
+# Copyright (C) 2021-2025, Mindee.
 
 # This program is licensed under the Apache License 2.0.
 # See LICENSE or go to <https://opensource.org/licenses/Apache-2.0> for full license details.
 
 import os
-from typing import Any, Dict, List, Tuple, Union
+from typing import Any
 
 import defusedxml.ElementTree as ET
 import numpy as np
@@ -28,10 +28,10 @@ class IC03(VisionDataset):
     >>> img, target = train_set[0]
 
     Args:
-    ----
         train: whether the subset should be the training one
         use_polygons: whether polygons should be considered as rotated bounding box (instead of straight ones)
         recognition_task: whether the dataset should be used for recognition task
+        detection_task: whether the dataset should be used for detection task
         **kwargs: keyword arguments from `VisionDataset`.
     """
 
@@ -51,6 +51,7 @@ class IC03(VisionDataset):
         train: bool = True,
         use_polygons: bool = False,
         recognition_task: bool = False,
+        detection_task: bool = False,
         **kwargs: Any,
     ) -> None:
         url, sha256, file_name = self.TRAIN if train else self.TEST
@@ -62,8 +63,14 @@ class IC03(VisionDataset):
             pre_transforms=convert_target_to_relative if not recognition_task else None,
             **kwargs,
         )
+        if recognition_task and detection_task:
+            raise ValueError(
+                "`recognition_task` and `detection_task` cannot be set to True simultaneously. "
+                + "To get the whole dataset with boxes and labels leave both parameters to False."
+            )
+
         self.train = train
-        self.data: List[Tuple[Union[str, np.ndarray], Union[str, Dict[str, Any]]]] = []
+        self.data: list[tuple[str | np.ndarray, str | dict[str, Any] | np.ndarray]] = []
         np_dtype = np.float32
 
         # Load xml data
@@ -73,7 +80,7 @@ class IC03(VisionDataset):
         xml_tree = ET.parse(os.path.join(tmp_root, "words.xml"))
         xml_root = xml_tree.getroot()
 
-        for image in tqdm(iterable=xml_root, desc="Unpacking IC03", total=len(xml_root)):
+        for image in tqdm(iterable=xml_root, desc="Preparing and Loading IC03", total=len(xml_root)):
             name, _resolution, rectangles = image
 
             # File existence check
@@ -117,6 +124,8 @@ class IC03(VisionDataset):
                     for crop, label in zip(crops, labels):
                         if crop.shape[0] > 0 and crop.shape[1] > 0 and len(label) > 0:
                             self.data.append((crop, label))
+                elif detection_task:
+                    self.data.append((name.text, boxes))
                 else:
                     self.data.append((name.text, dict(boxes=boxes, labels=labels)))
 

doctr/datasets/ic13.py

@@ -1,4 +1,4 @@
-# Copyright (C) 2021-2024, Mindee.
+# Copyright (C) 2021-2025, Mindee.
 
 # This program is licensed under the Apache License 2.0.
 # See LICENSE or go to <https://opensource.org/licenses/Apache-2.0> for full license details.
@@ -6,7 +6,7 @@
 import csv
 import os
 from pathlib import Path
-from typing import Any, Dict, List, Tuple, Union
+from typing import Any
 
 import numpy as np
 from tqdm import tqdm
@@ -33,11 +33,11 @@ class IC13(AbstractDataset):
     >>> img, target = test_set[0]
 
     Args:
-    ----
         img_folder: folder with all the images of the dataset
         label_folder: folder with all annotation files for the images
         use_polygons: whether polygons should be considered as rotated bounding box (instead of straight ones)
         recognition_task: whether the dataset should be used for recognition task
+        detection_task: whether the dataset should be used for detection task
         **kwargs: keyword arguments from `AbstractDataset`.
     """
 
@@ -47,11 +47,17 @@ class IC13(AbstractDataset):
         label_folder: str,
         use_polygons: bool = False,
         recognition_task: bool = False,
+        detection_task: bool = False,
         **kwargs: Any,
     ) -> None:
         super().__init__(
             img_folder, pre_transforms=convert_target_to_relative if not recognition_task else None, **kwargs
         )
+        if recognition_task and detection_task:
+            raise ValueError(
+                "`recognition_task` and `detection_task` cannot be set to True simultaneously. "
+                + "To get the whole dataset with boxes and labels leave both parameters to False."
+            )
 
         # File existence check
         if not os.path.exists(label_folder) or not os.path.exists(img_folder):
@@ -59,12 +65,12 @@ class IC13(AbstractDataset):
                 f"unable to locate {label_folder if not os.path.exists(label_folder) else img_folder}"
             )
 
-        self.data: List[Tuple[Union[Path, np.ndarray], Union[str, Dict[str, Any]]]] = []
+        self.data: list[tuple[Path | np.ndarray, str | dict[str, Any] | np.ndarray]] = []
         np_dtype = np.float32
 
         img_names = os.listdir(img_folder)
 
-        for img_name in tqdm(iterable=img_names, desc="Unpacking IC13", total=len(img_names)):
+        for img_name in tqdm(iterable=img_names, desc="Preparing and Loading IC13", total=len(img_names)):
             img_path = Path(img_folder, img_name)
             label_path = Path(label_folder, "gt_" + Path(img_name).stem + ".txt")
 
@@ -95,5 +101,7 @@ class IC13(AbstractDataset):
                 crops = crop_bboxes_from_image(img_path=img_path, geoms=box_targets)
                 for crop, label in zip(crops, labels):
                     self.data.append((crop, label))
+            elif detection_task:
+                self.data.append((img_path, box_targets))
             else:
                 self.data.append((img_path, dict(boxes=box_targets, labels=labels)))

doctr/datasets/iiit5k.py

@@ -1,10 +1,10 @@
-# Copyright (C) 2021-2024, Mindee.
+# Copyright (C) 2021-2025, Mindee.
 
 # This program is licensed under the Apache License 2.0.
 # See LICENSE or go to <https://opensource.org/licenses/Apache-2.0> for full license details.
 
 import os
-from typing import Any, Dict, List, Tuple, Union
+from typing import Any
 
 import numpy as np
 import scipy.io as sio
@@ -30,10 +30,10 @@ class IIIT5K(VisionDataset):
     >>> img, target = train_set[0]
 
     Args:
-    ----
         train: whether the subset should be the training one
         use_polygons: whether polygons should be considered as rotated bounding box (instead of straight ones)
         recognition_task: whether the dataset should be used for recognition task
+        detection_task: whether the dataset should be used for detection task
         **kwargs: keyword arguments from `VisionDataset`.
     """
 
@@ -45,6 +45,7 @@ class IIIT5K(VisionDataset):
         train: bool = True,
         use_polygons: bool = False,
         recognition_task: bool = False,
+        detection_task: bool = False,
         **kwargs: Any,
     ) -> None:
         super().__init__(
@@ -55,6 +56,12 @@ class IIIT5K(VisionDataset):
             pre_transforms=convert_target_to_relative if not recognition_task else None,
             **kwargs,
         )
+        if recognition_task and detection_task:
+            raise ValueError(
+                "`recognition_task` and `detection_task` cannot be set to True simultaneously. "
+                + "To get the whole dataset with boxes and labels leave both parameters to False."
+            )
+
         self.train = train
 
         # Load mat data
@@ -62,10 +69,12 @@ class IIIT5K(VisionDataset):
         mat_file = "trainCharBound" if self.train else "testCharBound"
         mat_data = sio.loadmat(os.path.join(tmp_root, f"{mat_file}.mat"))[mat_file][0]
 
-        self.data: List[Tuple[Union[str, np.ndarray], Union[str, Dict[str, Any]]]] = []
+        self.data: list[tuple[str | np.ndarray, str | dict[str, Any] | np.ndarray]] = []
         np_dtype = np.float32
 
-        for img_path, label, box_targets in tqdm(iterable=mat_data, desc="Unpacking IIIT5K", total=len(mat_data)):
+        for img_path, label, box_targets in tqdm(
+            iterable=mat_data, desc="Preparing and Loading IIIT5K", total=len(mat_data)
+        ):
             _raw_path = img_path[0]
             _raw_label = label[0]
 
@@ -73,24 +82,26 @@ class IIIT5K(VisionDataset):
             if not os.path.exists(os.path.join(tmp_root, _raw_path)):
                 raise FileNotFoundError(f"unable to locate {os.path.join(tmp_root, _raw_path)}")
 
+            if use_polygons:
+                # (x, y) coordinates of top left, top right, bottom right, bottom left corners
+                box_targets = [
+                    [
+                        [box[0], box[1]],
+                        [box[0] + box[2], box[1]],
+                        [box[0] + box[2], box[1] + box[3]],
+                        [box[0], box[1] + box[3]],
+                    ]
+                    for box in box_targets
+                ]
+            else:
+                # xmin, ymin, xmax, ymax
+                box_targets = [[box[0], box[1], box[0] + box[2], box[1] + box[3]] for box in box_targets]
+
             if recognition_task:
                 self.data.append((_raw_path, _raw_label))
+            elif detection_task:
+                self.data.append((_raw_path, np.asarray(box_targets, dtype=np_dtype)))
             else:
-                if use_polygons:
-                    # (x, y) coordinates of top left, top right, bottom right, bottom left corners
-                    box_targets = [
-                        [
-                            [box[0], box[1]],
-                            [box[0] + box[2], box[1]],
-                            [box[0] + box[2], box[1] + box[3]],
-                            [box[0], box[1] + box[3]],
-                        ]
-                        for box in box_targets
-                    ]
-                else:
-                    # xmin, ymin, xmax, ymax
-                    box_targets = [[box[0], box[1], box[0] + box[2], box[1] + box[3]] for box in box_targets]
-
                 # label are casted to list where each char corresponds to the character's bounding box
                 self.data.append((
                     _raw_path,

doctr/datasets/iiithws.py

@@ -1,11 +1,11 @@
-# Copyright (C) 2021-2024, Mindee.
+# Copyright (C) 2021-2025, Mindee.
 
 # This program is licensed under the Apache License 2.0.
 # See LICENSE or go to <https://opensource.org/licenses/Apache-2.0> for full license details.
 
 import os
 from random import sample
-from typing import Any, List, Tuple
+from typing import Any
 
 from tqdm import tqdm
 
@@ -32,7 +32,6 @@ class IIITHWS(AbstractDataset):
     >>> img, target = test_set[0]
 
     Args:
-    ----
         img_folder: folder with all the images of the dataset
         label_path: path to the file with the labels
         train: whether the subset should be the training one
@@ -52,7 +51,7 @@ class IIITHWS(AbstractDataset):
         if not os.path.exists(label_path) or not os.path.exists(img_folder):
             raise FileNotFoundError(f"unable to locate {label_path if not os.path.exists(label_path) else img_folder}")
 
-        self.data: List[Tuple[str, str]] = []
+        self.data: list[tuple[str, str]] = []
         self.train = train
 
         with open(label_path) as f:
@@ -64,7 +63,7 @@ class IIITHWS(AbstractDataset):
         set_slice = slice(train_samples) if self.train else slice(train_samples, None)
 
         for annotation in tqdm(
-            iterable=annotations[set_slice], desc="Unpacking IIITHWS", total=len(annotations[set_slice])
+            iterable=annotations[set_slice], desc="Preparing and Loading IIITHWS", total=len(annotations[set_slice])
         ):
             img_path, label = annotation.split()[0:2]
             img_path = os.path.join(img_folder, img_path)

doctr/datasets/imgur5k.py

@@ -1,4 +1,4 @@
-# Copyright (C) 2021-2024, Mindee.
+# Copyright (C) 2021-2025, Mindee.
 
 # This program is licensed under the Apache License 2.0.
 # See LICENSE or go to <https://opensource.org/licenses/Apache-2.0> for full license details.
@@ -7,7 +7,7 @@ import glob
 import json
 import os
 from pathlib import Path
-from typing import Any, Dict, List, Tuple, Union
+from typing import Any
 
 import cv2
 import numpy as np
@@ -40,12 +40,12 @@ class IMGUR5K(AbstractDataset):
     >>> img, target = test_set[0]
 
     Args:
-    ----
         img_folder: folder with all the images of the dataset
         label_path: path to the annotations file of the dataset
         train: whether the subset should be the training one
         use_polygons: whether polygons should be considered as rotated bounding box (instead of straight ones)
         recognition_task: whether the dataset should be used for recognition task
+        detection_task: whether the dataset should be used for detection task
         **kwargs: keyword arguments from `AbstractDataset`.
     """
 
@@ -56,17 +56,23 @@ class IMGUR5K(AbstractDataset):
         train: bool = True,
         use_polygons: bool = False,
         recognition_task: bool = False,
+        detection_task: bool = False,
         **kwargs: Any,
     ) -> None:
         super().__init__(
             img_folder, pre_transforms=convert_target_to_relative if not recognition_task else None, **kwargs
         )
+        if recognition_task and detection_task:
+            raise ValueError(
+                "`recognition_task` and `detection_task` cannot be set to True simultaneously. "
+                + "To get the whole dataset with boxes and labels leave both parameters to False."
+            )
 
         # File existence check
         if not os.path.exists(label_path) or not os.path.exists(img_folder):
             raise FileNotFoundError(f"unable to locate {label_path if not os.path.exists(label_path) else img_folder}")
 
-        self.data: List[Tuple[Union[str, Path, np.ndarray], Union[str, Dict[str, Any]]]] = []
+        self.data: list[tuple[str | Path | np.ndarray, str | dict[str, Any] | np.ndarray]] = []
         self.train = train
         np_dtype = np.float32
 
@@ -89,7 +95,9 @@ class IMGUR5K(AbstractDataset):
         with open(label_path) as f:
             annotation_file = json.load(f)
 
-        for img_name in tqdm(iterable=img_names[set_slice], desc="Unpacking IMGUR5K", total=len(img_names[set_slice])):
+        for img_name in tqdm(
+            iterable=img_names[set_slice], desc="Preparing and Loading IMGUR5K", total=len(img_names[set_slice])
+        ):
             img_path = Path(img_folder, img_name)
             img_id = img_name.split(".")[0]
 
@@ -132,6 +140,8 @@ class IMGUR5K(AbstractDataset):
                                 tmp_img = Image.fromarray(crop)
                                 tmp_img.save(os.path.join(reco_folder_path, f"{reco_images_counter}.png"))
                                 reco_images_counter += 1
+                elif detection_task:
+                    self.data.append((img_path, np.asarray(box_targets, dtype=np_dtype)))
                 else:
                     self.data.append((img_path, dict(boxes=np.asarray(box_targets, dtype=np_dtype), labels=labels)))
 

doctr/datasets/loader.py

@@ -1,10 +1,10 @@
-# Copyright (C) 2021-2024, Mindee.
+# Copyright (C) 2021-2025, Mindee.
 
 # This program is licensed under the Apache License 2.0.
 # See LICENSE or go to <https://opensource.org/licenses/Apache-2.0> for full license details.
 
 import math
-from typing import Callable, Optional
+from collections.abc import Callable
 
 import numpy as np
 import tensorflow as tf
@@ -16,12 +16,10 @@ def default_collate(samples):
     """Collate multiple elements into batches
 
     Args:
-    ----
         samples: list of N tuples containing M elements
 
     Returns:
-    -------
-        Tuple of M sequences contianing N elements each
+        tuple of M sequences contianing N elements each
     """
     batch_data = zip(*samples)
 
@@ -40,7 +38,6 @@ class DataLoader:
     >>> images, targets = next(train_iter)
 
     Args:
-    ----
         dataset: the dataset
         shuffle: whether the samples should be shuffled before passing it to the iterator
         batch_size: number of elements in each batch
@@ -54,7 +51,7 @@ class DataLoader:
         shuffle: bool = True,
         batch_size: int = 1,
         drop_last: bool = False,
-        collate_fn: Optional[Callable] = None,
+        collate_fn: Callable | None = None,
     ) -> None:
         self.dataset = dataset
         self.shuffle = shuffle

doctr/datasets/mjsynth.py

@@ -1,10 +1,10 @@
-# Copyright (C) 2021-2024, Mindee.
+# Copyright (C) 2021-2025, Mindee.
 
 # This program is licensed under the Apache License 2.0.
 # See LICENSE or go to <https://opensource.org/licenses/Apache-2.0> for full license details.
 
 import os
-from typing import Any, List, Tuple
+from typing import Any
 
 from tqdm import tqdm
 
@@ -30,7 +30,6 @@ class MJSynth(AbstractDataset):
     >>> img, target = test_set[0]
 
     Args:
-    ----
         img_folder: folder with all the images of the dataset
         label_path: path to the file with the labels
         train: whether the subset should be the training one
@@ -86,7 +85,7 @@ class MJSynth(AbstractDataset):
         if not os.path.exists(label_path) or not os.path.exists(img_folder):
             raise FileNotFoundError(f"unable to locate {label_path if not os.path.exists(label_path) else img_folder}")
 
-        self.data: List[Tuple[str, str]] = []
+        self.data: list[tuple[str, str]] = []
         self.train = train
 
         with open(label_path) as f:
@@ -95,7 +94,9 @@ class MJSynth(AbstractDataset):
         train_samples = int(len(img_paths) * 0.9)
         set_slice = slice(train_samples) if self.train else slice(train_samples, None)
 
-        for path in tqdm(iterable=img_paths[set_slice], desc="Unpacking MJSynth", total=len(img_paths[set_slice])):
+        for path in tqdm(
+            iterable=img_paths[set_slice], desc="Preparing and Loading MJSynth", total=len(img_paths[set_slice])
+        ):
             if path not in self.BLACKLIST:
                 label = path.split("_")[1]
                 img_path = os.path.join(img_folder, path[2:]).strip()

doctr/datasets/ocr.py

@@ -1,4 +1,4 @@
-# Copyright (C) 2021-2024, Mindee.
+# Copyright (C) 2021-2025, Mindee.
 
 # This program is licensed under the Apache License 2.0.
 # See LICENSE or go to <https://opensource.org/licenses/Apache-2.0> for full license details.
@@ -6,7 +6,7 @@
 import json
 import os
 from pathlib import Path
-from typing import Any, Dict, List, Tuple
+from typing import Any
 
 import numpy as np
 
@@ -24,7 +24,6 @@ class OCRDataset(AbstractDataset):
     >>> img, target = train_set[0]
 
     Args:
-    ----
         img_folder: local path to image folder (all jpg at the root)
         label_file: local path to the label file
         use_polygons: whether polygons should be considered as rotated bounding box (instead of straight ones)
@@ -41,7 +40,7 @@ class OCRDataset(AbstractDataset):
         super().__init__(img_folder, **kwargs)
 
         # List images
-        self.data: List[Tuple[str, Dict[str, Any]]] = []
+        self.data: list[tuple[str, dict[str, Any]]] = []
         np_dtype = np.float32
         with open(label_file, "rb") as f:
             data = json.load(f)

doctr/datasets/orientation.py

@@ -1,10 +1,10 @@
-# Copyright (C) 2021-2024, Mindee.
+# Copyright (C) 2021-2025, Mindee.
 
 # This program is licensed under the Apache License 2.0.
 # See LICENSE or go to <https://opensource.org/licenses/Apache-2.0> for full license details.
 
 import os
-from typing import Any, List, Tuple
+from typing import Any
 
 import numpy as np
 
@@ -21,7 +21,6 @@ class OrientationDataset(AbstractDataset):
     >>> img, target = train_set[0]
 
     Args:
-    ----
         img_folder: folder with all the images of the dataset
         **kwargs: keyword arguments from `AbstractDataset`.
     """
@@ -37,4 +36,4 @@ class OrientationDataset(AbstractDataset):
         )
 
         # initialize dataset with 0 degree rotation targets
-        self.data: List[Tuple[str, np.ndarray]] = [(img_name, np.array([0])) for img_name in os.listdir(self.root)]
+        self.data: list[tuple[str, np.ndarray]] = [(img_name, np.array([0])) for img_name in os.listdir(self.root)]

doctr/datasets/recognition.py

@@ -1,4 +1,4 @@
-# Copyright (C) 2021-2024, Mindee.
+# Copyright (C) 2021-2025, Mindee.
 
 # This program is licensed under the Apache License 2.0.
 # See LICENSE or go to <https://opensource.org/licenses/Apache-2.0> for full license details.
@@ -6,7 +6,7 @@
 import json
 import os
 from pathlib import Path
-from typing import Any, List, Tuple
+from typing import Any
 
 from .datasets import AbstractDataset
 
@@ -22,7 +22,6 @@ class RecognitionDataset(AbstractDataset):
     >>> img, target = train_set[0]
 
     Args:
-    ----
         img_folder: path to the images folder
         labels_path: pathe to the json file containing all labels (character sequences)
         **kwargs: keyword arguments from `AbstractDataset`.
@@ -36,7 +35,7 @@ class RecognitionDataset(AbstractDataset):
     ) -> None:
         super().__init__(img_folder, **kwargs)
 
-        self.data: List[Tuple[str, str]] = []
+        self.data: list[tuple[str, str]] = []
         with open(labels_path, encoding="utf-8") as f:
             labels = json.load(f)