maite-datasets 0.0.7__py3-none-any.whl → 0.0.8__py3-none-any.whl

maite_datasets/_base.py

@@ -8,20 +8,22 @@ from abc import abstractmethod
 from collections import namedtuple
 from collections.abc import Iterator, Sequence
 from pathlib import Path
-from typing import Any, Callable, Generic, Literal, NamedTuple, TypeVar, cast
+from typing import Any, Callable, Generic, Literal, NamedTuple, Protocol, TypeVar, cast
 
 import numpy as np
 from maite.protocols import DatasetMetadata, DatumMetadata
+from maite.protocols import image_classification as ic
+from maite.protocols import object_detection as od
 from numpy.typing import NDArray
 from PIL import Image
 
 from maite_datasets._fileio import _ensure_exists
 from maite_datasets.protocols import Array
 
-_T = TypeVar("_T")
 _T_co = TypeVar("_T_co", covariant=True)
 _TArray = TypeVar("_TArray", bound=Array)
 _TTarget = TypeVar("_TTarget")
+_TODTarget = TypeVar("_TODTarget", bound=od.ObjectDetectionTarget)
 _TRawTarget = TypeVar(
     "_TRawTarget",
     Sequence[int],
@@ -30,8 +32,7 @@ _TRawTarget = TypeVar(
 )
 _TAnnotation = TypeVar("_TAnnotation", int, str, tuple[list[int], list[list[float]]])
 
-
-ObjectDetectionTarget = namedtuple("ObjectDetectionTarget", ["boxes", "labels", "scores"])
+ObjectDetectionTargetTuple = namedtuple("ObjectDetectionTargetTuple", ["boxes", "labels", "scores"])
 
 
 class BaseDatasetMixin(Generic[_TArray]):
@@ -249,6 +250,7 @@ class BaseICDataset(
     BaseDownloadedDataset[_TArray, _TArray, list[int], int],
     BaseDatasetMixin[_TArray],
     BaseDataset[_TArray, _TArray],
+    ic.Dataset,
 ):
     """
     Base class for image classification datasets.
@@ -278,9 +280,10 @@ class BaseICDataset(
 
 
 class BaseODDataset(
-    BaseDownloadedDataset[_TArray, ObjectDetectionTarget, _TRawTarget, _TAnnotation],
+    BaseDownloadedDataset[_TArray, _TODTarget, _TRawTarget, _TAnnotation],
     BaseDatasetMixin[_TArray],
-    BaseDataset[_TArray, ObjectDetectionTarget],
+    BaseDataset[_TArray, _TODTarget],
+    od.Dataset,
 ):
     """
     Base class for object detection datasets.
@@ -288,7 +291,7 @@ class BaseODDataset(
 
     _bboxes_per_size: bool = False
 
-    def __getitem__(self, index: int) -> tuple[_TArray, ObjectDetectionTarget, DatumMetadata]:
+    def __getitem__(self, index: int) -> tuple[_TArray, _TODTarget, DatumMetadata]:
         """
         Args
         ----
@@ -310,7 +313,9 @@ class BaseODDataset(
         if self._bboxes_per_size and boxes:
             boxes = boxes * np.asarray([[img_size[1], img_size[2], img_size[1], img_size[2]]])
         # Create the Object Detection Target
-        target = ObjectDetectionTarget(self._as_array(boxes), self._as_array(labels), self._one_hot_encode(labels))
+        target = ObjectDetectionTargetTuple(self._as_array(boxes), self._as_array(labels), self._one_hot_encode(labels))
+        # Cast target explicitly to ODTarget as namedtuple does not provide any typing metadata
+        target = cast(_TODTarget, target)
 
         img_metadata = {key: val[index] for key, val in self._datum_metadata.items()}
         img_metadata = img_metadata | additional_metadata
@@ -324,6 +329,15 @@ class BaseODDataset(
 NumpyArray = NDArray[np.floating[Any]] | NDArray[np.integer[Any]]
 
 
+class NumpyObjectDetectionTarget(od.ObjectDetectionTarget, Protocol):
+    @property
+    def boxes(self) -> NumpyArray: ...
+    @property
+    def labels(self) -> NumpyArray: ...
+    @property
+    def scores(self) -> NumpyArray: ...
+
+
 class BaseDatasetNumpyMixin(BaseDatasetMixin[NumpyArray]):
     def _as_array(self, raw: list[Any]) -> NumpyArray:
         return np.asarray(raw)
@@ -347,8 +361,8 @@ NumpyImageClassificationDatumTransform = Callable[
     tuple[NumpyArray, NumpyArray, DatumMetadata],
 ]
 NumpyObjectDetectionDatumTransform = Callable[
-    [tuple[NumpyArray, ObjectDetectionTarget, DatumMetadata]],
-    tuple[NumpyArray, ObjectDetectionTarget, DatumMetadata],
+    [tuple[NumpyArray, NumpyObjectDetectionTarget, DatumMetadata]],
+    tuple[NumpyArray, NumpyObjectDetectionTarget, DatumMetadata],
 ]
 NumpyImageClassificationTransform = NumpyImageTransform | NumpyImageClassificationDatumTransform
 NumpyObjectDetectionTransform = NumpyImageTransform | NumpyObjectDetectionDatumTransform

maite_datasets/adapters/_huggingface.py

@@ -10,7 +10,7 @@ import maite.protocols.object_detection as od
 import numpy as np
 from maite.protocols import DatasetMetadata, DatumMetadata
 
-from maite_datasets._base import BaseDataset, NumpyArray, ObjectDetectionTarget
+from maite_datasets._base import BaseDataset, NumpyArray, ObjectDetectionTargetTuple
 from maite_datasets.protocols import HFArray, HFClassLabel, HFDataset, HFImage, HFList, HFValue
 from maite_datasets.wrappers._torch import TTarget
 
@@ -135,7 +135,7 @@ class HFImageClassificationDataset(HFBaseDataset[NumpyArray], ic.Dataset):
 
         # Enhanced metadata with validation
         self.metadata: DatasetMetadata = DatasetMetadata(
-            id=self._metadata_id, index2label=dict(enumerate(label_feature.names), **self._metadata_dict)
+            id=self._metadata_id, index2label=dict(enumerate(label_feature.names)), **self._metadata_dict
         )
 
     def __getitem__(self, index: int) -> tuple[NumpyArray, NumpyArray, DatumMetadata]:
@@ -157,7 +157,7 @@ class HFImageClassificationDataset(HFBaseDataset[NumpyArray], ic.Dataset):
         return image, one_hot_label, datum_metadata
 
 
-class HFObjectDetectionDataset(HFBaseDataset[ObjectDetectionTarget], od.Dataset):
+class HFObjectDetectionDataset(HFBaseDataset[ObjectDetectionTargetTuple], od.Dataset):
     """Wraps a Hugging Face dataset to comply with the ObjectDetectionDataset protocol."""
 
     def __init__(self, hf_dataset: HFDataset, image_key: str, objects_key: str, bbox_key: str, label_key: str) -> None:
@@ -225,7 +225,7 @@ class HFObjectDetectionDataset(HFBaseDataset[ObjectDetectionTarget], od.Dataset)
 
         return label_feature
 
-    def __getitem__(self, index: int) -> tuple[NumpyArray, ObjectDetectionTarget, DatumMetadata]:
+    def __getitem__(self, index: int) -> tuple[NumpyArray, ObjectDetectionTargetTuple, DatumMetadata]:
         if not 0 <= index < len(self.source):
             raise IndexError(f"Index {index} out of range for dataset of size {len(self.source)}")
 
@@ -237,7 +237,7 @@ class HFObjectDetectionDataset(HFBaseDataset[ObjectDetectionTarget], od.Dataset)
         boxes = objects[self._bbox_key]
         labels = objects[self._label_key]
         scores = np.zeros_like(labels, dtype=np.float32)
-        target = ObjectDetectionTarget(boxes, labels, scores)
+        target = ObjectDetectionTargetTuple(boxes, labels, scores)
 
         # Process metadata
         datum_metadata = self._get_base_metadata(index)

maite_datasets/object_detection/_antiuav.py

@@ -13,11 +13,12 @@ from maite_datasets._base import (
     BaseODDataset,
     DataLocation,
     NumpyArray,
+    NumpyObjectDetectionTarget,
     NumpyObjectDetectionTransform,
 )
 
 
-class AntiUAVDetection(BaseODDataset[NumpyArray, list[str], str], BaseDatasetNumpyMixin):
+class AntiUAVDetection(BaseODDataset[NumpyArray, NumpyObjectDetectionTarget, list[str], str], BaseDatasetNumpyMixin):
     """
     A UAV detection dataset focused on detecting UAVs in natural images against large variation in backgrounds.
 

maite_datasets/object_detection/_coco.py

@@ -11,7 +11,7 @@ import numpy as np
 from maite.protocols import DatasetMetadata, DatumMetadata
 from PIL import Image
 
-from maite_datasets._base import BaseDataset, ObjectDetectionTarget
+from maite_datasets._base import BaseDataset, ObjectDetectionTargetTuple
 from maite_datasets._reader import BaseDatasetReader
 
 
@@ -269,7 +269,7 @@ class COCODataset(BaseDataset):
             scores = np.empty(0, dtype=np.float32)
             annotation_metadata = []
 
-        target = ObjectDetectionTarget(boxes, labels, scores)
+        target = ObjectDetectionTargetTuple(boxes, labels, scores)
 
         # Create comprehensive datum metadata
         datum_metadata = DatumMetadata(

maite_datasets/object_detection/_milco.py

@@ -11,11 +11,12 @@ from maite_datasets._base import (
     BaseODDataset,
     DataLocation,
     NumpyArray,
+    NumpyObjectDetectionTarget,
     NumpyObjectDetectionTransform,
 )
 
 
-class MILCO(BaseODDataset[NumpyArray, list[str], str], BaseDatasetNumpyMixin):
+class MILCO(BaseODDataset[NumpyArray, NumpyObjectDetectionTarget, list[str], str], BaseDatasetNumpyMixin):
     """
     A side-scan sonar dataset focused on mine-like object detection.
 

maite_datasets/object_detection/_seadrone.py

@@ -12,6 +12,7 @@ from maite_datasets._base import (
     BaseODDataset,
     DataLocation,
     NumpyArray,
+    NumpyObjectDetectionTarget,
     NumpyObjectDetectionTransform,
 )
 from maite_datasets._fileio import _ensure_exists
@@ -20,6 +21,7 @@ from maite_datasets._fileio import _ensure_exists
 class SeaDrone(
     BaseODDataset[
         NumpyArray,
+        NumpyObjectDetectionTarget,
         list[tuple[list[int], list[list[float]]]],
         tuple[list[int], list[list[float]]],
     ],

maite_datasets/object_detection/_voc.py

@@ -16,8 +16,8 @@ from maite_datasets._base import (
     BaseODDataset,
     DataLocation,
     NumpyArray,
+    NumpyObjectDetectionTarget,
     NumpyObjectDetectionTransform,
-    ObjectDetectionTarget,
     _ensure_exists,
 )
 
@@ -46,7 +46,7 @@ VOCClassStringMap = Literal[
 TVOCClassMap = TypeVar("TVOCClassMap", VOCClassStringMap, int, list[VOCClassStringMap], list[int])
 
 
-class BaseVOCDataset(BaseDownloadedDataset[NumpyArray, ObjectDetectionTarget, list[str], str]):
+class BaseVOCDataset(BaseDownloadedDataset[NumpyArray, NumpyObjectDetectionTarget, list[str], str]):
     _resources = [
         DataLocation(
             url="https://data.brainchip.com/dataset-mirror/voc/VOCtrainval_11-May-2012.tar",
@@ -431,7 +431,7 @@ class BaseVOCDataset(BaseDownloadedDataset[NumpyArray, ObjectDetectionTarget, li
 
 class VOCDetection(
     BaseVOCDataset,
-    BaseODDataset[NumpyArray, list[str], str],
+    BaseODDataset[NumpyArray, NumpyObjectDetectionTarget, list[str], str],
     BaseDatasetNumpyMixin,
 ):
     """

maite_datasets/object_detection/_yolo.py

@@ -12,7 +12,7 @@ import numpy as np
 from maite.protocols import DatasetMetadata, DatumMetadata
 from PIL import Image
 
-from maite_datasets._base import BaseDataset, ObjectDetectionTarget
+from maite_datasets._base import BaseDataset, ObjectDetectionTargetTuple
 from maite_datasets._reader import BaseDatasetReader
 
 
@@ -297,7 +297,7 @@ class YOLODataset(BaseDataset):
             labels = np.empty(0, dtype=np.int64)
             scores = np.empty(0, dtype=np.float32)
 
-        target = ObjectDetectionTarget(boxes, labels, scores)
+        target = ObjectDetectionTargetTuple(boxes, labels, scores)
 
         # Create comprehensive datum metadata
         datum_metadata = DatumMetadata(

maite_datasets/protocols.py

@@ -3,7 +3,7 @@ Common type protocols used for interoperability.
 """
 
 from collections.abc import Iterable, Iterator, Mapping, Sequence
-from typing import Any, Protocol, overload, runtime_checkable
+from typing import Any, Generic, Protocol, TypeVar, overload, runtime_checkable
 
 
 @runtime_checkable
@@ -23,6 +23,17 @@ class Array(Protocol):
     def __len__(self) -> int: ...
 
 
+TBoxes = TypeVar("TBoxes", Array, Sequence)
+TLabels = TypeVar("TLabels", Array, Sequence)
+TScores = TypeVar("TScores", Array, Sequence)
+
+
+class GenericObjectDetectionTarget(Generic[TBoxes, TLabels, TScores], Protocol):
+    boxes: TBoxes
+    labels: TLabels
+    scores: TScores
+
+
 @runtime_checkable
 class HFDatasetInfo(Protocol):
     @property

maite_datasets/wrappers/_torch.py

@@ -1,21 +1,31 @@
 from __future__ import annotations
 
-from typing import Any, Callable, Generic, TypeAlias, TypeVar, cast, overload
+from typing import Any, Callable, Generic, Protocol, TypeAlias, TypeVar, cast, overload
 
 import torch
 from maite.protocols import DatasetMetadata, DatumMetadata
-from maite.protocols.object_detection import ObjectDetectionTarget as _ObjectDetectionTarget
+from maite.protocols.object_detection import ObjectDetectionTarget
 from torch import Tensor
 from torchvision.tv_tensors import BoundingBoxes, Image
 
-from maite_datasets._base import BaseDataset, ObjectDetectionTarget
+from maite_datasets._base import BaseDataset, ObjectDetectionTargetTuple
 from maite_datasets.protocols import Array
 
 TArray = TypeVar("TArray", bound=Array)
 TTarget = TypeVar("TTarget")
 
+
+class TorchvisionObjectDetectionTarget(Protocol):
+    @property
+    def boxes(self) -> BoundingBoxes: ...
+    @property
+    def labels(self) -> Tensor: ...
+    @property
+    def scores(self) -> Tensor: ...
+
+
 TorchvisionImageClassificationDatum: TypeAlias = tuple[Image, Tensor, DatumMetadata]
-TorchvisionObjectDetectionDatum: TypeAlias = tuple[Image, ObjectDetectionTarget, DatumMetadata]
+TorchvisionObjectDetectionDatum: TypeAlias = tuple[Image, ObjectDetectionTargetTuple, DatumMetadata]
 
 
 class TorchvisionWrapper(Generic[TArray, TTarget]):
@@ -62,9 +72,9 @@ class TorchvisionWrapper(Generic[TArray, TTarget]):
     @overload
     def __getitem__(
         self: TorchvisionWrapper[TArray, TTarget], index: int
-    ) -> tuple[Image, ObjectDetectionTarget, DatumMetadata]: ...
+    ) -> tuple[Image, TorchvisionObjectDetectionTarget, DatumMetadata]: ...
 
-    def __getitem__(self, index: int) -> tuple[Image, Tensor | ObjectDetectionTarget, DatumMetadata]:
+    def __getitem__(self, index: int) -> tuple[Image, Tensor | TorchvisionObjectDetectionTarget, DatumMetadata]:
         """Get item with torch tensor conversion."""
         image, target, metadata = self._dataset[index]
 
@@ -78,14 +88,14 @@ class TorchvisionWrapper(Generic[TArray, TTarget]):
             torch_datum = self._transform((torch_image, torch_target, metadata))
             return cast(TorchvisionImageClassificationDatum, torch_datum)
 
-        if isinstance(target, _ObjectDetectionTarget):
+        if isinstance(target, ObjectDetectionTarget):
             # Object detection case
             torch_boxes = BoundingBoxes(
                 torch.tensor(target.boxes), format="XYXY", canvas_size=(torch_image.shape[-2], torch_image.shape[-1])
             )  # type: ignore
             torch_labels = torch.tensor(target.labels, dtype=torch.int64)
             torch_scores = torch.tensor(target.scores, dtype=torch.float32)
-            torch_target = ObjectDetectionTarget(torch_boxes, torch_labels, torch_scores)
+            torch_target = ObjectDetectionTargetTuple(torch_boxes, torch_labels, torch_scores)
             torch_datum = self._transform((torch_image, torch_target, metadata))
             return cast(TorchvisionObjectDetectionDatum, torch_datum)
 

{maite_datasets-0.0.7.dist-info → maite_datasets-0.0.8.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: maite-datasets
-Version: 0.0.7
+Version: 0.0.8
 Summary: A collection of Image Classification and Object Detection task datasets conforming to the MAITE protocol.
 Author-email: Andrew Weng <andrew.weng@ariacoustics.com>, Ryan Wood <ryan.wood@ariacoustics.com>, Shaun Jullens <shaun.jullens@ariacoustics.com>
 License-Expression: MIT

{maite_datasets-0.0.7.dist-info → maite_datasets-0.0.8.dist-info}/RECORD

@@ -1,28 +1,28 @@
 maite_datasets/__init__.py,sha256=Z_HyAe08HaHMjzZS2afFumBXYFRFj0ny5ZAIp0hcj4w,569
-maite_datasets/_base.py,sha256=VEd4ipHPAOCbz4Zm8zdI2yQwQ_x9O4Wq01xoZ2QvNYo,12366
+maite_datasets/_base.py,sha256=6-RG3VJfpNEC7luNGCPpqyIQ5FlWeYRSm_bfo1PXdUQ,12924
 maite_datasets/_builder.py,sha256=MnCh6z5hSINlzBnK_pdbgI5zSg5d1uq4UvXt3cjn9hs,9820
 maite_datasets/_collate.py,sha256=pwUnmrbJH5olFjSwF-ZkGdfopTWUUlwmq0d5KzERcy8,4052
 maite_datasets/_fileio.py,sha256=7S-hF3xU60AdcsPsfYR7rjbeGZUlv3JjGEZhGJOxGYU,5622
 maite_datasets/_reader.py,sha256=tJqsjfXaK-mrs0Ed4BktombFMmNwCur35W7tuYCflKM,5569
 maite_datasets/_validate.py,sha256=Uokbolmv1uSv98sph44HON0HEieeK3s2mqbPMP1d5xs,6948
-maite_datasets/protocols.py,sha256=8NPD2AdYXiz2i9TQwS_kdpboFeYMad3G7peuh2c9GZc,2153
+maite_datasets/protocols.py,sha256=PcIVJzUc5com_pmhzh0CPb0IkrmFof6WtUQXm7_6Vko,2450
 maite_datasets/py.typed,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 maite_datasets/adapters/__init__.py,sha256=PDMdvRqLVS7x6ghJ_xUBD5Ebq5HrV5k3p4TqK2_6Gt8,191
-maite_datasets/adapters/_huggingface.py,sha256=bmAz9Pssqfma1hzgTM4wtoLKnWAozkxNUzREGBYYTyM,16179
+maite_datasets/adapters/_huggingface.py,sha256=dZa2guKeto-oKMM9J_TaI4DSPK18u7PvK3AsHQp3eQc,16199
 maite_datasets/image_classification/__init__.py,sha256=pcZojkdsiMoLgY4mKjoQY6WyEwiGYHxNrAGpnvn3zsY,308
 maite_datasets/image_classification/_cifar10.py,sha256=rrkJZ70NBYOSGxligXyakVxNOyGAglN6PaGQazuWNO4,8453
 maite_datasets/image_classification/_mnist.py,sha256=9isgdi-YXgs6nXoh1j8uOgh4_sIhBIky72Vyl866rTE,8192
 maite_datasets/image_classification/_ships.py,sha256=nWhte8592lpybhQCCdgT36LnuMQ0PRJWlDxT5-IPUtk,5137
 maite_datasets/object_detection/__init__.py,sha256=171KT_X6I4YGy18G240N_-ZsKvXJ6YqcBDzkhTiBj2E,587
-maite_datasets/object_detection/_antiuav.py,sha256=B20JrbouDM1o5f1ct9Zfbkks8NaVqYrxu5x-rBZvGx8,8265
-maite_datasets/object_detection/_coco.py,sha256=3abRQJ9ATcZOeqK-4pnMfr-pv7aGcRum88SRlLLXTzk,10309
-maite_datasets/object_detection/_milco.py,sha256=brxxYs5ak0vEpOSd2IW5AMMVkuadVmXCJBFPvXTmNlo,7928
-maite_datasets/object_detection/_seadrone.py,sha256=JdHL0eRZoe7pXVInOq5Xpnz3-vgeBxbO25oTYgGZ44o,271213
-maite_datasets/object_detection/_voc.py,sha256=vgRn-sa_r2-hxwpM3veRZQMcWyqJz9OGalABOccZeow,19589
-maite_datasets/object_detection/_yolo.py,sha256=Luojzhanh6AK949910jN0yTpy8zwF5_At6nThj3Zw9Q,11867
+maite_datasets/object_detection/_antiuav.py,sha256=8b_AlX5xb5Fu02pG-dldFrHtVZLZzb6ZyGGYj-b7Lt0,8325
+maite_datasets/object_detection/_coco.py,sha256=vTPQmLSgIM7lNb2PEaCrs1fK7_82j3tXFQQ3A5e0dlM,10319
+maite_datasets/object_detection/_milco.py,sha256=aX10PbWjIFyajS5ibGA219fZd7tZTkAlvpThoTZpxtM,7988
+maite_datasets/object_detection/_seadrone.py,sha256=wKcyKQhcvNj5NrLMOD-9KdGaTaBnE6F9uif_J-PKNug,271281
+maite_datasets/object_detection/_voc.py,sha256=CDFgSpbQZgpSq51CKd9twIUHr6l_GAViVGpmFUNX0Dg,19627
+maite_datasets/object_detection/_yolo.py,sha256=GIa43Ec_542N7PRo0XngV-Npw3n4yoIND3tI7vas3u0,11877
 maite_datasets/wrappers/__init__.py,sha256=6uI0ztOB2IlMWln9JkVke4OhU2HQ8i6YCaCNq_q5qb0,225
-maite_datasets/wrappers/_torch.py,sha256=nPWeBtam6EPZf9BGbrFqKlyWfyzOpX_zpLFZBTnA2Vg,4458
-maite_datasets-0.0.7.dist-info/METADATA,sha256=L4UmetVfmJBFDtDWo2yElwBt47VY__euzWgDgaWgkzs,7845
-maite_datasets-0.0.7.dist-info/WHEEL,sha256=qtCwoSJWgHk21S1Kb4ihdzI2rlJ1ZKaIurTj_ngOhyQ,87
-maite_datasets-0.0.7.dist-info/licenses/LICENSE,sha256=6h3J3R-ajGHh_isDSftzS5_jJjB9HH4TaI0vU-VscaY,1082
-maite_datasets-0.0.7.dist-info/RECORD,,
+maite_datasets/wrappers/_torch.py,sha256=gYcAdrarcX_DiV51MD1cpOa9YAZGEmWblJEyyLS7rRs,4687
+maite_datasets-0.0.8.dist-info/METADATA,sha256=1srwva41Dtqwda2AGc0GwnjQs9f-sFMVSLaMrVQJv7Q,7845
+maite_datasets-0.0.8.dist-info/WHEEL,sha256=qtCwoSJWgHk21S1Kb4ihdzI2rlJ1ZKaIurTj_ngOhyQ,87
+maite_datasets-0.0.8.dist-info/licenses/LICENSE,sha256=6h3J3R-ajGHh_isDSftzS5_jJjB9HH4TaI0vU-VscaY,1082
+maite_datasets-0.0.8.dist-info/RECORD,,