dataeval 0.84.0__py3-none-any.whl → 1.0.0__py3-none-any.whl

dataeval/utils/data/_dataset.py

@@ -52,10 +52,12 @@ def _validate_data(
 
 
 def _find_max(arr: ArrayLike) -> Any:
-    if isinstance(arr[0], (Iterable, Sequence, Array)):
-        return max([_find_max(x) for x in arr])  # type: ignore
-    else:
-        return max(arr)
+    if isinstance(arr, (Iterable, Sequence, Array)):
+        if isinstance(arr[0], (Iterable, Sequence, Array)):
+            return max([_find_max(x) for x in arr])  # type: ignore
+        else:
+            return max(arr)
+    return arr
 
 
 _TLabels = TypeVar("_TLabels", Sequence[int], Sequence[Sequence[int]])

dataeval/utils/data/collate.py

@@ -4,6 +4,8 @@ Collate functions used with a PyTorch DataLoader to load data from MAITE complia
 
 from __future__ import annotations
 
+__all__ = ["list_collate_fn", "numpy_collate_fn", "torch_collate_fn"]
+
 from typing import Any, Iterable, Sequence, TypeVar
 
 import numpy as np

dataeval/utils/datasets/__init__.py

@@ -0,0 +1,17 @@
+"""Provides access to common Computer Vision datasets."""
+
+from dataeval.utils.datasets._cifar10 import CIFAR10
+from dataeval.utils.datasets._milco import MILCO
+from dataeval.utils.datasets._mnist import MNIST
+from dataeval.utils.datasets._ships import Ships
+from dataeval.utils.datasets._voc import VOCDetection, VOCDetectionTorch, VOCSegmentation
+
+__all__ = [
+    "MNIST",
+    "Ships",
+    "CIFAR10",
+    "MILCO",
+    "VOCDetection",
+    "VOCDetectionTorch",
+    "VOCSegmentation",
+]

dataeval/utils/{data/datasets → datasets}/_base.py

@@ -6,9 +6,9 @@ from abc import abstractmethod
 from pathlib import Path
 from typing import TYPE_CHECKING, Any, Generic, Iterator, Literal, NamedTuple, Sequence, TypeVar
 
-from dataeval.utils.data.datasets._fileio import _ensure_exists
-from dataeval.utils.data.datasets._mixin import BaseDatasetMixin
-from dataeval.utils.data.datasets._types import (
+from dataeval.utils.datasets._fileio import _ensure_exists
+from dataeval.utils.datasets._mixin import BaseDatasetMixin
+from dataeval.utils.datasets._types import (
     AnnotatedDataset,
     DatasetMetadata,
     ImageClassificationDataset,
@@ -19,9 +19,12 @@ from dataeval.utils.data.datasets._types import (
 )
 
 if TYPE_CHECKING:
-    from dataeval.typing import Transform
+    from dataeval.typing import Array, Transform
+
+    _TArray = TypeVar("_TArray", bound=Array)
+else:
+    _TArray = TypeVar("_TArray")
 
-_TArray = TypeVar("_TArray")
 _TTarget = TypeVar("_TTarget")
 _TRawTarget = TypeVar("_TRawTarget", list[int], list[str])
 
@@ -51,9 +54,9 @@ class BaseDataset(AnnotatedDataset[tuple[_TArray, _TTarget, dict[str, Any]]], Ge
     def __init__(
         self,
         root: str | Path,
-        download: bool = False,
-        image_set: Literal["train", "val", "test", "base"] = "train",
+        image_set: Literal["train", "val", "test", "operational", "base"] = "train",
         transforms: Transform[_TArray] | Sequence[Transform[_TArray]] | None = None,
+        download: bool = False,
         verbose: bool = False,
     ) -> None:
         self._root: Path = root.absolute() if isinstance(root, Path) else Path(root).absolute()

dataeval/utils/{data/datasets → datasets}/_cifar10.py

@@ -9,8 +9,8 @@ import numpy as np
 from numpy.typing import NDArray
 from PIL import Image
 
-from dataeval.utils.data.datasets._base import BaseICDataset, DataLocation
-from dataeval.utils.data.datasets._mixin import BaseDatasetNumpyMixin
+from dataeval.utils.datasets._base import BaseICDataset, DataLocation
+from dataeval.utils.datasets._mixin import BaseDatasetNumpyMixin
 
 if TYPE_CHECKING:
     from dataeval.typing import Transform
@@ -27,13 +27,13 @@ class CIFAR10(BaseICDataset[NDArray[Any]], BaseDatasetNumpyMixin):
     ----------
     root : str or pathlib.Path
         Root directory of dataset where the ``mnist`` folder exists.
-    download : bool, default False
-        If True, downloads the dataset from the internet and puts it in root directory.
-        Class checks to see if data is already downloaded to ensure it does not create a duplicate download.
     image_set : "train", "test" or "base", default "train"
         If "base", returns all of the data to allow the user to create their own splits.
     transforms : Transform, Sequence[Transform] or None, default None
         Transform(s) to apply to the data.
+    download : bool, default False
+        If True, downloads the dataset from the internet and puts it in root directory.
+        Class checks to see if data is already downloaded to ensure it does not create a duplicate download.
     verbose : bool, default False
         If True, outputs print statements.
 
@@ -43,16 +43,16 @@ class CIFAR10(BaseICDataset[NDArray[Any]], BaseDatasetNumpyMixin):
         Location of the folder containing the data.
     image_set : "train", "test" or "base"
         The selected image set from the dataset.
+    transforms : Sequence[Transform]
+        The transforms to be applied to the data.
+    size : int
+        The size of the dataset.
     index2label : dict[int, str]
         Dictionary which translates from class integers to the associated class strings.
     label2index : dict[str, int]
         Dictionary which translates from class strings to the associated class integers.
     metadata : DatasetMetadata
         Typed dictionary containing dataset metadata, such as `id` which returns the dataset class name.
-    transforms : Sequence[Transform]
-        The transforms to be applied to the data.
-    size : int
-        The size of the dataset.
     """
 
     _resources = [
@@ -80,16 +80,16 @@ class CIFAR10(BaseICDataset[NDArray[Any]], BaseDatasetNumpyMixin):
     def __init__(
         self,
         root: str | Path,
-        download: bool = False,
         image_set: Literal["train", "test", "base"] = "train",
         transforms: Transform[NDArray[Any]] | Sequence[Transform[NDArray[Any]]] | None = None,
+        download: bool = False,
         verbose: bool = False,
     ) -> None:
         super().__init__(
             root,
-            download,
             image_set,
             transforms,
+            download,
             verbose,
         )
 

dataeval/utils/{data/datasets → datasets}/_milco.py

@@ -3,12 +3,12 @@ from __future__ import annotations
 __all__ = []
 
 from pathlib import Path
-from typing import TYPE_CHECKING, Any, Sequence
+from typing import TYPE_CHECKING, Any, Literal, Sequence
 
 from numpy.typing import NDArray
 
-from dataeval.utils.data.datasets._base import BaseODDataset, DataLocation
-from dataeval.utils.data.datasets._mixin import BaseDatasetNumpyMixin
+from dataeval.utils.datasets._base import BaseODDataset, DataLocation
+from dataeval.utils.datasets._mixin import BaseDatasetNumpyMixin
 
 if TYPE_CHECKING:
     from dataeval.typing import Transform
@@ -16,21 +16,20 @@ if TYPE_CHECKING:
 
 class MILCO(BaseODDataset[NDArray[Any]], BaseDatasetNumpyMixin):
     """
-    A side-scan sonar dataset focused on mine (object) detection.
+    A side-scan sonar dataset focused on mine-like object detection.
 
     The dataset comes from the paper
     `Side-scan sonar imaging data of underwater vehicles for mine detection <https://doi.org/10.1016/j.dib.2024.110132>`_
     by N.P. Santos et. al. (2024).
 
-    This class only accesses a portion of the above dataset due to size constraints.
     The full dataset contains 1170 side-scan sonar images collected using a 900-1800 kHz Marine Sonic
     dual frequency side-scan sonar of a Teledyne Marine Gavia Autonomous Underwater Vehicle.
     All the images were carefully analyzed and annotated, including the image coordinates of the
     Bounding Box (BB) of the detected objects divided into NOn-Mine-like BOttom Objects (NOMBO)
     and MIne-Like COntacts (MILCO) classes.
 
-    This dataset is consists of 261 images (120 images from 2015, 93 images from 2017, and 48 images from 2021).
-    In these 261 images, there are 315 MILCO objects, and 175 NOMBO objects.
+    This dataset is consists of 345 images from 2010, 120 images from 2015, 93 images from 2017, 564 images from 2018,
+    and 48 images from 2021). In these 1170 images, there are 432 MILCO objects, and 235 NOMBO objects.
     The class “0” corresponds to a MILCO object and the class “1” corresponds to a NOMBO object.
     The raw BB coordinates provided in the downloaded text files are (x, y, w, h),
     given as percentages of the image (x_BB = x/img_width, y_BB = y/img_height, etc.).
@@ -40,11 +39,17 @@ class MILCO(BaseODDataset[NDArray[Any]], BaseDatasetNumpyMixin):
     ----------
     root : str or pathlib.Path
         Root directory of dataset where the ``milco`` folder exists.
+    image_set: "train", "operational", or "base", default "train"
+        If "train", then the images from 2015, 2017 and 2021 are selected,
+        resulting in 315 MILCO objects and 177 NOMBO objects.
+        If "operational", then the images from 2010 and 2018 are selected,
+        resulting in 117 MILCO objects and 58 NOMBO objects.
+        If "base", then the full dataset is selected.
+    transforms : Transform, Sequence[Transform] or None, default None
+        Transform(s) to apply to the data.
     download : bool, default False
         If True, downloads the dataset from the internet and puts it in root directory.
         Class checks to see if data is already downloaded to ensure it does not create a duplicate download.
-    transforms : Transform, Sequence[Transform] or None, default None
-        Transform(s) to apply to the data.
     verbose : bool, default False
         If True, outputs print statements.
 
@@ -52,8 +57,8 @@ class MILCO(BaseODDataset[NDArray[Any]], BaseDatasetNumpyMixin):
     ----------
     path : pathlib.Path
         Location of the folder containing the data.
-    image_set : "base"
-        The base image set is the only available image set for the MILCO dataset.
+    image_set : "train", "operational" or "base"
+        The selected image set from the dataset.
     index2label : dict[int, str]
         Dictionary which translates from class integers to the associated class strings.
     label2index : dict[str, int]
@@ -64,6 +69,10 @@ class MILCO(BaseODDataset[NDArray[Any]], BaseDatasetNumpyMixin):
         The transforms to be applied to the data.
     size : int
         The size of the dataset.
+
+    Note
+    ----
+    Data License: `CC BY 4.0 <https://creativecommons.org/licenses/by/4.0/>`_
     """
 
     _resources = [
@@ -85,6 +94,18 @@ class MILCO(BaseODDataset[NDArray[Any]], BaseDatasetNumpyMixin):
             md5=True,
             checksum="b84749b21fa95a4a4c7de3741db78bc7",
         ),
+        DataLocation(
+            url="https://figshare.com/ndownloader/files/43169008",
+            filename="2010.zip",
+            md5=True,
+            checksum="43347a0cc383c0d3dbe0d24ae56f328d",
+        ),
+        DataLocation(
+            url="https://figshare.com/ndownloader/files/43169011",
+            filename="2018.zip",
+            md5=True,
+            checksum="25d091044a10c78674fedad655023e3b",
+        ),
     ]
 
     index2label: dict[int, str] = {
@@ -95,15 +116,16 @@ class MILCO(BaseODDataset[NDArray[Any]], BaseDatasetNumpyMixin):
     def __init__(
         self,
         root: str | Path,
-        download: bool = False,
+        image_set: Literal["train", "operational", "base"] = "train",
         transforms: Transform[NDArray[Any]] | Sequence[Transform[NDArray[Any]]] | None = None,
+        download: bool = False,
         verbose: bool = False,
     ) -> None:
         super().__init__(
             root,
-            download,
-            "base",
+            image_set,
             transforms,
+            download,
             verbose,
         )
 
@@ -112,10 +134,16 @@ class MILCO(BaseODDataset[NDArray[Any]], BaseDatasetNumpyMixin):
         targets: list[str] = []
         datum_metadata: dict[str, list[Any]] = {}
         metadata_list: list[dict[str, Any]] = []
+        image_sets: dict[str, list[int]] = {
+            "base": list(range(len(self._resources))),
+            "train": list(range(3)),
+            "operational": list(range(3, len(self._resources))),
+        }
 
         # Load the data
-        for resource in self._resources:
-            self._resource = resource
+        resource_indices = image_sets[self.image_set]
+        for idx in resource_indices:
+            self._resource = self._resources[idx]
             filepath, target, metadata = super()._load_data()
             filepaths.extend(filepath)
             targets.extend(target)

dataeval/utils/{data/datasets → datasets}/_mnist.py

@@ -8,8 +8,8 @@ from typing import TYPE_CHECKING, Any, Literal, Sequence, TypeVar
 import numpy as np
 from numpy.typing import NDArray
 
-from dataeval.utils.data.datasets._base import BaseICDataset, DataLocation
-from dataeval.utils.data.datasets._mixin import BaseDatasetNumpyMixin
+from dataeval.utils.datasets._base import BaseICDataset, DataLocation
+from dataeval.utils.datasets._mixin import BaseDatasetNumpyMixin
 
 if TYPE_CHECKING:
     from dataeval.typing import Transform
@@ -49,9 +49,6 @@ class MNIST(BaseICDataset[NDArray[Any]], BaseDatasetNumpyMixin):
     ----------
     root : str or pathlib.Path
         Root directory of dataset where the ``mnist`` folder exists.
-    download : bool, default False
-        If True, downloads the dataset from the internet and puts it in root directory.
-        Class checks to see if data is already downloaded to ensure it does not create a duplicate download.
     image_set : "train", "test" or "base", default "train"
         If "base", returns all of the data to allow the user to create their own splits.
     corruption : "identity", "shot_noise", "impulse_noise", "glass_blur", "motion_blur", \
@@ -60,6 +57,9 @@ class MNIST(BaseICDataset[NDArray[Any]], BaseDatasetNumpyMixin):
         Corruption to apply to the data.
     transforms : Transform, Sequence[Transform] or None, default None
         Transform(s) to apply to the data.
+    download : bool, default False
+        If True, downloads the dataset from the internet and puts it in root directory.
+        Class checks to see if data is already downloaded to ensure it does not create a duplicate download.
     verbose : bool, default False
         If True, outputs print statements.
 
@@ -81,6 +81,10 @@ class MNIST(BaseICDataset[NDArray[Any]], BaseDatasetNumpyMixin):
         The transforms to be applied to the data.
     size : int
         The size of the dataset.
+    
+    Note
+    ----
+    Data License: `CC BY 4.0 <https://creativecommons.org/licenses/by/4.0/>`_ for corruption dataset
     """
 
     _resources = [
@@ -114,10 +118,10 @@ class MNIST(BaseICDataset[NDArray[Any]], BaseDatasetNumpyMixin):
     def __init__(
         self,
         root: str | Path,
-        download: bool = False,
         image_set: Literal["train", "test", "base"] = "train",
         corruption: CorruptionStringMap | None = None,
         transforms: Transform[NDArray[Any]] | Sequence[Transform[NDArray[Any]]] | None = None,
+        download: bool = False,
         verbose: bool = False,
     ) -> None:
         self.corruption = corruption
@@ -127,9 +131,9 @@ class MNIST(BaseICDataset[NDArray[Any]], BaseDatasetNumpyMixin):
 
         super().__init__(
             root,
-            download,
             image_set,
             transforms,
+            download,
             verbose,
         )
 

dataeval/utils/{data/datasets → datasets}/_ships.py

@@ -8,8 +8,8 @@ from typing import TYPE_CHECKING, Any, Sequence
 import numpy as np
 from numpy.typing import NDArray
 
-from dataeval.utils.data.datasets._base import BaseICDataset, DataLocation
-from dataeval.utils.data.datasets._mixin import BaseDatasetNumpyMixin
+from dataeval.utils.datasets._base import BaseICDataset, DataLocation
+from dataeval.utils.datasets._mixin import BaseDatasetNumpyMixin
 
 if TYPE_CHECKING:
     from dataeval.typing import Transform
@@ -31,11 +31,11 @@ class Ships(BaseICDataset[NDArray[Any]], BaseDatasetNumpyMixin):
     ----------
     root : str or pathlib.Path
         Root directory of dataset where the ``shipdataset`` folder exists.
+    transforms : Transform, Sequence[Transform] or None, default None
+        Transform(s) to apply to the data.
     download : bool, default False
         If True, downloads the dataset from the internet and puts it in root directory.
         Class checks to see if data is already downloaded to ensure it does not create a duplicate download.
-    transforms : Transform, Sequence[Transform] or None, default None
-        Transform(s) to apply to the data.
     verbose : bool, default False
         If True, outputs print statements.
 
@@ -55,6 +55,10 @@ class Ships(BaseICDataset[NDArray[Any]], BaseDatasetNumpyMixin):
         The transforms to be applied to the data.
     size : int
         The size of the dataset.
+
+    Note
+    ----
+    Data License: `CC BY-SA 4.0 <https://creativecommons.org/licenses/by-sa/4.0/>`_
     """
 
     _resources = [
@@ -74,15 +78,15 @@ class Ships(BaseICDataset[NDArray[Any]], BaseDatasetNumpyMixin):
     def __init__(
         self,
         root: str | Path,
-        download: bool = False,
         transforms: Transform[NDArray[Any]] | Sequence[Transform[NDArray[Any]]] | None = None,
+        download: bool = False,
         verbose: bool = False,
     ) -> None:
         super().__init__(
             root,
-            download,
             "base",
             transforms,
+            download,
             verbose,
         )
         self._scenes: list[str] = self._load_scenes()

dataeval/utils/{data/datasets → datasets}/_voc.py

@@ -9,21 +9,20 @@ import torch
 from defusedxml.ElementTree import parse
 from numpy.typing import NDArray
 
-from dataeval.utils.data.datasets._base import (
+from dataeval.utils.datasets._base import (
     BaseDataset,
     BaseODDataset,
     BaseSegDataset,
     DataLocation,
+    _TArray,
+    _TTarget,
 )
-from dataeval.utils.data.datasets._mixin import BaseDatasetNumpyMixin, BaseDatasetTorchMixin
-from dataeval.utils.data.datasets._types import ObjectDetectionTarget, SegmentationTarget
+from dataeval.utils.datasets._mixin import BaseDatasetNumpyMixin, BaseDatasetTorchMixin
+from dataeval.utils.datasets._types import ObjectDetectionTarget, SegmentationTarget
 
 if TYPE_CHECKING:
     from dataeval.typing import Transform
 
-_TArray = TypeVar("_TArray")
-_TTarget = TypeVar("_TTarget")
-
 VOCClassStringMap = Literal[
     "aeroplane",
     "bicycle",
@@ -121,19 +120,19 @@ class BaseVOCDataset(BaseDataset[_TArray, _TTarget, list[str]]):
     def __init__(
         self,
         root: str | Path,
-        year: Literal["2007", "2008", "2009", "2010", "2011", "2012"] = "2012",
         image_set: Literal["train", "val", "test", "base"] = "train",
-        download: bool = False,
+        year: Literal["2007", "2008", "2009", "2010", "2011", "2012"] = "2012",
         transforms: Transform[_TArray] | Sequence[Transform[_TArray]] | None = None,
+        download: bool = False,
         verbose: bool = False,
     ) -> None:
         self.year = year
         self._resource_index = self._get_year_image_set_index(year, image_set)
         super().__init__(
             root,
-            download,
             image_set,
             transforms,
+            download,
             verbose,
         )
 
@@ -191,10 +190,14 @@ class BaseVOCDataset(BaseDataset[_TArray, _TTarget, list[str]]):
         for entry in data:
             file_name = Path(entry).name
             file_stem = Path(entry).stem
-            # Remove file extension and split by "_"
-            parts = file_stem.split("_")
-            file_meta["year"].append(parts[0])
-            file_meta["image_id"].append(parts[1])
+            if self.year != "2007":
+                # Remove file extension and split by "_"
+                parts = file_stem.split("_")
+                file_meta["year"].append(parts[0])
+                file_meta["image_id"].append(parts[1])
+            else:
+                file_meta["year"].append(self.year)
+                file_meta["image_id"].append(file_stem)
             file_meta["mask_path"].append(str(seg_folder / file_name))
             annotations.append(str(ann_folder / file_stem) + ".xml")
 
@@ -250,9 +253,6 @@ class VOCDetection(
     ----------
     root : str or pathlib.Path
         Root directory of dataset where the ``vocdataset`` folder exists.
-    download : bool, default False
-        If True, downloads the dataset from the internet and puts it in root directory.
-        Class checks to see if data is already downloaded to ensure it does not create a duplicate download.
     image_set : "train", "val", "test", or "base", default "train"
         If "test", then dataset year must be "2007".
         If "base", then the combined dataset of "train" and "val" is returned.
@@ -260,6 +260,9 @@ class VOCDetection(
         The dataset year.
     transforms : Transform, Sequence[Transform] or None, default None
         Transform(s) to apply to the data.
+    download : bool, default False
+        If True, downloads the dataset from the internet and puts it in root directory.
+        Class checks to see if data is already downloaded to ensure it does not create a duplicate download.
     verbose : bool, default False
         If True, outputs print statements.
 
@@ -267,6 +270,8 @@ class VOCDetection(
     ----------
     path : pathlib.Path
         Location of the folder containing the data.
+    year : "2007", "2008", "2009", "2010", "2011" or "2012"
+        The selected dataset year.
     image_set : "train", "val", "test" or "base"
         The selected image set from the dataset.
     index2label : dict[int, str]
@@ -279,6 +284,10 @@ class VOCDetection(
         The transforms to be applied to the data.
     size : int
         The size of the dataset.
+
+    Note
+    ----
+    Data License: `Flickr Terms of Use <http://www.flickr.com/terms.gne?legacy=1>`_
     """
 
 
@@ -294,9 +303,6 @@ class VOCDetectionTorch(
     ----------
     root : str or pathlib.Path
         Root directory of dataset where the ``vocdataset`` folder exists.
-    download : bool, default False
-        If True, downloads the dataset from the internet and puts it in root directory.
-        Class checks to see if data is already downloaded to ensure it does not create a duplicate download.
     image_set : "train", "val", "test", or "base", default "train"
         If "test", then dataset year must be "2007".
         If "base", then the combined dataset of "train" and "val" is returned.
@@ -304,6 +310,9 @@ class VOCDetectionTorch(
         The dataset year.
     transforms : Transform, Sequence[Transform] or None, default None
         Transform(s) to apply to the data.
+    download : bool, default False
+        If True, downloads the dataset from the internet and puts it in root directory.
+        Class checks to see if data is already downloaded to ensure it does not create a duplicate download.
     verbose : bool, default False
         If True, outputs print statements.
 
@@ -311,6 +320,8 @@ class VOCDetectionTorch(
     ----------
     path : pathlib.Path
         Location of the folder containing the data.
+    year : "2007", "2008", "2009", "2010", "2011" or "2012"
+        The selected dataset year.
     image_set : "train", "val", "test" or "base"
         The selected image set from the dataset.
     index2label : dict[int, str]
@@ -323,6 +334,10 @@ class VOCDetectionTorch(
         The transforms to be applied to the data.
     size : int
         The size of the dataset.
+
+    Note
+    ----
+    Data License: `Flickr Terms of Use <http://www.flickr.com/terms.gne?legacy=1>`_
     """
 
 
@@ -338,9 +353,6 @@ class VOCSegmentation(
     ----------
     root : str or pathlib.Path
         Root directory of dataset where the ``vocdataset`` folder exists.
-    download : bool, default False
-        If True, downloads the dataset from the internet and puts it in root directory.
-        Class checks to see if data is already downloaded to ensure it does not create a duplicate download.
     image_set : "train", "val", "test", or "base", default "train"
         If "test", then dataset year must be "2007".
         If "base", then the combined dataset of "train" and "val" is returned.
@@ -348,6 +360,9 @@ class VOCSegmentation(
         The dataset year.
     transforms : Transform, Sequence[Transform] or None, default None
         Transform(s) to apply to the data.
+    download : bool, default False
+        If True, downloads the dataset from the internet and puts it in root directory.
+        Class checks to see if data is already downloaded to ensure it does not create a duplicate download.
     verbose : bool, default False
         If True, outputs print statements.
 
@@ -355,6 +370,8 @@ class VOCSegmentation(
     ----------
     path : pathlib.Path
         Location of the folder containing the data.
+    year : "2007", "2008", "2009", "2010", "2011" or "2012"
+        The selected dataset year.
     image_set : "train", "val", "test" or "base"
         The selected image set from the dataset.
     index2label : dict[int, str]
@@ -367,6 +384,10 @@ class VOCSegmentation(
         The transforms to be applied to the data.
     size : int
         The size of the dataset.
+
+    Note
+    ----
+    Data License: `Flickr Terms of Use <http://www.flickr.com/terms.gne?legacy=1>`_
     """
 
     def _load_data(self) -> tuple[list[str], list[str], dict[str, list[Any]]]: