python-doctr 0.10.0__py3-none-any.whl → 0.11.0__py3-none-any.whl

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
@@ -28,7 +28,6 @@ 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
@@ -71,7 +70,7 @@ class IC03(VisionDataset):
             )
 
         self.train = train
-        self.data: List[Tuple[Union[str, np.ndarray], Union[str, Dict[str, Any], np.ndarray]]] = []
+        self.data: list[tuple[str | np.ndarray, str | dict[str, Any] | np.ndarray]] = []
         np_dtype = np.float32
 
         # Load xml data
@@ -81,7 +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

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
@@ -33,7 +33,6 @@ 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)
@@ -66,12 +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], np.ndarray]]] = []
+        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")
 

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
@@ -30,7 +30,6 @@ 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
@@ -70,10 +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], np.ndarray]]] = []
+        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]
 

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
@@ -40,7 +40,6 @@ 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
@@ -73,7 +72,7 @@ class IMGUR5K(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[Union[str, Path, np.ndarray], Union[str, Dict[str, Any], np.ndarray]]] = []
+        self.data: list[tuple[str | Path | np.ndarray, str | dict[str, Any] | np.ndarray]] = []
         self.train = train
         np_dtype = np.float32
 
@@ -96,7 +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]
 

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)
 

doctr/datasets/sroie.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
@@ -29,7 +29,6 @@ class SROIE(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
@@ -74,10 +73,12 @@ class SROIE(VisionDataset):
         self.train = train
 
         tmp_root = os.path.join(self.root, "images")
-        self.data: List[Tuple[Union[str, np.ndarray], Union[str, Dict[str, Any], np.ndarray]]] = []
+        self.data: list[tuple[str | np.ndarray, str | dict[str, Any] | np.ndarray]] = []
         np_dtype = np.float32
 
-        for img_path in tqdm(iterable=os.listdir(tmp_root), desc="Unpacking SROIE", total=len(os.listdir(tmp_root))):
+        for img_path in tqdm(
+            iterable=os.listdir(tmp_root), desc="Preparing and Loading SROIE", total=len(os.listdir(tmp_root))
+        ):
             # File existence check
             if not os.path.exists(os.path.join(tmp_root, img_path)):
                 raise FileNotFoundError(f"unable to locate {os.path.join(tmp_root, img_path)}")

doctr/datasets/svhn.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 h5py
 import numpy as np
@@ -28,7 +28,6 @@ class SVHN(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
@@ -72,7 +71,7 @@ class SVHN(VisionDataset):
             )
 
         self.train = train
-        self.data: List[Tuple[Union[str, np.ndarray], Union[str, Dict[str, Any], np.ndarray]]] = []
+        self.data: list[tuple[str | np.ndarray, str | dict[str, Any] | np.ndarray]] = []
         np_dtype = np.float32
 
         tmp_root = os.path.join(self.root, "train" if train else "test")
@@ -81,7 +80,9 @@ class SVHN(VisionDataset):
         with h5py.File(os.path.join(tmp_root, "digitStruct.mat"), "r") as f:
             img_refs = f["digitStruct/name"]
             box_refs = f["digitStruct/bbox"]
-            for img_ref, box_ref in tqdm(iterable=zip(img_refs, box_refs), desc="Unpacking SVHN", total=len(img_refs)):
+            for img_ref, box_ref in tqdm(
+                iterable=zip(img_refs, box_refs), desc="Preparing and Loading SVHN", total=len(img_refs)
+            ):
                 # convert ascii matrix to string
                 img_name = "".join(map(chr, f[img_ref[0]][()].flatten()))
 

doctr/datasets/svt.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
@@ -28,7 +28,6 @@ class SVT(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
@@ -62,7 +61,7 @@ class SVT(VisionDataset):
             )
 
         self.train = train
-        self.data: List[Tuple[Union[str, np.ndarray], Union[str, Dict[str, Any], np.ndarray]]] = []
+        self.data: list[tuple[str | np.ndarray, str | dict[str, Any] | np.ndarray]] = []
         np_dtype = np.float32
 
         # Load xml data
@@ -74,7 +73,7 @@ class SVT(VisionDataset):
         )
         xml_root = xml_tree.getroot()
 
-        for image in tqdm(iterable=xml_root, desc="Unpacking SVT", total=len(xml_root)):
+        for image in tqdm(iterable=xml_root, desc="Preparing and Loading SVT", total=len(xml_root)):
             name, _, _, _resolution, rectangles = image
 
             # File existence check

doctr/datasets/synthtext.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 glob
 import os
-from typing import Any, Dict, List, Tuple, Union
+from typing import Any
 
 import numpy as np
 from PIL import Image
@@ -31,7 +31,6 @@ class SynthText(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
@@ -65,7 +64,7 @@ class SynthText(VisionDataset):
             )
 
         self.train = train
-        self.data: List[Tuple[Union[str, np.ndarray], Union[str, Dict[str, Any], np.ndarray]]] = []
+        self.data: list[tuple[str | np.ndarray, str | dict[str, Any] | np.ndarray]] = []
         np_dtype = np.float32
 
         # Load mat data
@@ -91,7 +90,7 @@ class SynthText(VisionDataset):
         del mat_data
 
         for img_path, word_boxes, txt in tqdm(
-            iterable=zip(paths, boxes, labels), desc="Unpacking SynthText", total=len(paths)
+            iterable=zip(paths, boxes, labels), desc="Preparing and Loading SynthText", total=len(paths)
         ):
             # File existence check
             if not os.path.exists(os.path.join(tmp_root, img_path[0])):