[misc] Update header year & clearer built-in datasets progress bar msg

mindee · Jan 6, 2025 · 779eaab · 779eaab
1 parent e6bf82d
commit 779eaab
Show file tree

Hide file tree

Showing 166 changed files with 197 additions and 179 deletions.
diff --git a/.github/verify_pr_labels.py b/.github/verify_pr_labels.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.

diff --git a/api/app/config.py b/api/app/config.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.

diff --git a/api/app/main.py b/api/app/main.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.

diff --git a/api/app/routes/detection.py b/api/app/routes/detection.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.

diff --git a/api/app/routes/kie.py b/api/app/routes/kie.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.

diff --git a/api/app/routes/ocr.py b/api/app/routes/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.

diff --git a/api/app/routes/recognition.py b/api/app/routes/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.

diff --git a/api/app/schemas.py b/api/app/schemas.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.

diff --git a/api/app/utils.py b/api/app/utils.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.

diff --git a/api/app/vision.py b/api/app/vision.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.

diff --git a/demo/app.py b/demo/app.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.

diff --git a/demo/backend/pytorch.py b/demo/backend/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.

diff --git a/demo/backend/tensorflow.py b/demo/backend/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.

diff --git a/docs/source/conf.py b/docs/source/conf.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.

diff --git a/doctr/contrib/artefacts.py b/doctr/contrib/artefacts.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.

diff --git a/doctr/contrib/base.py b/doctr/contrib/base.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.

diff --git a/doctr/datasets/cord.py b/doctr/datasets/cord.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.
@@ -76,7 +76,9 @@ def __init__(
         self.data: list[tuple[str | np.ndarray, str | dict[str, Any] | np.ndarray]] = []
         self.train = train
         np_dtype = np.float32
-        for img_path in tqdm(iterable=os.listdir(tmp_root), desc="Unpacking CORD", total=len(os.listdir(tmp_root))):
+        for img_path in tqdm(
+            iterable=os.listdir(tmp_root), desc="Preparing and Loading CORD", 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)}")

diff --git a/doctr/datasets/datasets/base.py b/doctr/datasets/datasets/base.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.

diff --git a/doctr/datasets/datasets/pytorch.py b/doctr/datasets/datasets/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.

diff --git a/doctr/datasets/datasets/tensorflow.py b/doctr/datasets/datasets/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.

diff --git a/doctr/datasets/detection.py b/doctr/datasets/detection.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.

diff --git a/doctr/datasets/doc_artefacts.py b/doctr/datasets/doc_artefacts.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.

diff --git a/doctr/datasets/funsd.py b/doctr/datasets/funsd.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.
@@ -71,7 +71,9 @@ def __init__(
         # # list images
         tmp_root = os.path.join(self.root, subfolder, "images")
         self.data: list[tuple[str | np.ndarray, str | dict[str, Any] | np.ndarray]] = []
-        for img_path in tqdm(iterable=os.listdir(tmp_root), desc="Unpacking FUNSD", total=len(os.listdir(tmp_root))):
+        for img_path in tqdm(
+            iterable=os.listdir(tmp_root), desc="Preparing and Loading FUNSD", 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)}")

diff --git a/doctr/datasets/generator/base.py b/doctr/datasets/generator/base.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.

diff --git a/doctr/datasets/generator/pytorch.py b/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.

diff --git a/doctr/datasets/generator/tensorflow.py b/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.

diff --git a/doctr/datasets/ic03.py b/doctr/datasets/ic03.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.
@@ -80,7 +80,7 @@ def __init__(
         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

diff --git a/doctr/datasets/ic13.py b/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.
@@ -70,7 +70,7 @@ def __init__(
 
         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")
 

diff --git a/doctr/datasets/iiit5k.py b/doctr/datasets/iiit5k.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.
@@ -72,7 +72,9 @@ def __init__(
         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]
 

diff --git a/doctr/datasets/iiithws.py b/doctr/datasets/iiithws.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.
@@ -63,7 +63,7 @@ def __init__(
         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)

diff --git a/doctr/datasets/imgur5k.py b/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.
@@ -95,7 +95,9 @@ def __init__(
         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]
 

diff --git a/doctr/datasets/loader.py b/doctr/datasets/loader.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.

diff --git a/doctr/datasets/mjsynth.py b/doctr/datasets/mjsynth.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.
@@ -94,7 +94,9 @@ def __init__(
         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()

diff --git a/doctr/datasets/ocr.py b/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.

diff --git a/doctr/datasets/orientation.py b/doctr/datasets/orientation.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.

diff --git a/doctr/datasets/recognition.py b/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.

diff --git a/doctr/datasets/sroie.py b/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.
@@ -76,7 +76,9 @@ def __init__(
         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)}")

diff --git a/doctr/datasets/svhn.py b/doctr/datasets/svhn.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.
@@ -80,7 +80,9 @@ def __init__(
         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()))
 

diff --git a/doctr/datasets/svt.py b/doctr/datasets/svt.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.
@@ -73,7 +73,7 @@ def __init__(
         )
         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

diff --git a/doctr/datasets/synthtext.py b/doctr/datasets/synthtext.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.
@@ -90,7 +90,7 @@ def __init__(
         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])):

diff --git a/doctr/datasets/utils.py b/doctr/datasets/utils.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.

diff --git a/doctr/datasets/vocabs.py b/doctr/datasets/vocabs.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.

diff --git a/doctr/datasets/wildreceipt.py b/doctr/datasets/wildreceipt.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.
@@ -9,6 +9,7 @@
 from typing import Any
 
 import numpy as np
+from tqdm import tqdm
 
 from .datasets import AbstractDataset
 from .utils import convert_target_to_relative, crop_bboxes_from_image
@@ -79,7 +80,10 @@ def __init__(
         json_strings = data.strip().split("\n")
         box: list[float] | np.ndarray
         _targets = []
-        for json_string in json_strings:
+
+        for json_string in tqdm(
+            iterable=json_strings, desc="Preparing and Loading WILDRECEIPT", total=len(json_strings)
+        ):
             json_data = json.loads(json_string)
             img_path = json_data["file_name"]
             annotations = json_data["annotations"]