maite-datasets 0.0.5__tar.gz → 0.0.7__tar.gz

{maite_datasets-0.0.5 → maite_datasets-0.0.7}/.gitignore

@@ -9,6 +9,10 @@ wheels/
 # Virtual environments
 .venv
 
+# Downloaded data
+.data
+
 # Test output
 .nox/
-output/
+output/
+.coverage

maite_datasets-0.0.7/PKG-INFO

@@ -0,0 +1,181 @@
+Metadata-Version: 2.4
+Name: maite-datasets
+Version: 0.0.7
+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
+License-File: LICENSE
+Classifier: Development Status :: 4 - Beta
+Classifier: Framework :: Pytest
+Classifier: License :: OSI Approved :: MIT License
+Classifier: Operating System :: OS Independent
+Classifier: Programming Language :: Python :: 3 :: Only
+Classifier: Programming Language :: Python :: 3.10
+Classifier: Programming Language :: Python :: 3.11
+Classifier: Programming Language :: Python :: 3.12
+Classifier: Programming Language :: Python :: 3.13
+Requires-Python: >=3.10
+Requires-Dist: defusedxml>=0.7.1
+Requires-Dist: maite<0.9,>=0.7
+Requires-Dist: numpy>=1.24.2
+Requires-Dist: pillow>=10.3.0
+Requires-Dist: requests>=2.32.3
+Requires-Dist: typing-extensions>=4.12
+Provides-Extra: tqdm
+Requires-Dist: tqdm>=4.66; extra == 'tqdm'
+Description-Content-Type: text/markdown
+
+# MAITE Datasets
+
+MAITE Datasets are a collection of public datasets wrapped in a [MAITE](https://mit-ll-ai-technology.github.io/maite/) compliant format.
+
+## Installation
+
+To install and use `maite-datasets` you can use pip:
+
+```bash
+pip install maite-datasets
+```
+
+For status bar indicators when downloading, you can include the extra `tqdm` when installing:
+
+```bash
+pip install maite-datasets[tqdm]
+```
+
+## Available Downloadable Datasets
+
+| Task           | Dataset          | Description                                                         |
+|----------------|------------------|---------------------------------------------------------------------|
+| Classification | CIFAR10          | [CIFAR10](https://www.cs.toronto.edu/~kriz/cifar.html) dataset.     |
+| Classification | MNIST            | A dataset of hand-written digits.                                   |
+| Classification | Ships            | A dataset that focuses on identifying ships from satellite images.  |
+| Detection      | AntiUAVDetection | A UAV detection dataset in natural images with varying backgrounds. |
+| Detection      | MILCO            | A side-scan sonar dataset focused on mine-like object detection.    |
+| Detection      | Seadrone         | A UAV dataset focused on open water object detection.               |
+| Detection      | VOCDetection     | [Pascal VOC](http://host.robots.ox.ac.uk/pascal/VOC/) dataset.      |
+
+### Usage
+
+Here is an example of how to import MNIST for usage with your workflow.
+
+```python
+>>> from maite_datasets.image_classification import MNIST
+
+>>> mnist = MNIST(root="data", download=True)
+>>> print(mnist)
+MNIST Dataset
+-------------
+    Corruption: None
+    Transforms: []
+    Image_set: train
+    Metadata: {'id': 'MNIST_train', 'index2label': {0: 'zero', 1: 'one', 2: 'two', 3: 'three', 4: 'four', 5: 'five', 6: 'six', 7: 'seven', 8: 'eight', 9: 'nine'}, 'split': 'train'}
+    Path: /home/user/maite-datasets/data/mnist
+    Size: 60000
+
+>>> print("tuple("+", ".join([str(type(t)) for t in mnist[0]])+")")
+tuple(<class 'numpy.ndarray'>, <class 'numpy.ndarray'>, <class 'dict'>)
+```
+
+## Dataset Wrappers
+
+Wrappers provide a way to convert datasets to allow usage of tools within specific backend frameworks.
+
+### Torchvision
+
+`TorchvisionWrapper` is a convenience class that wraps any of the datasets and provides the capability to apply
+`torchvision` transforms to the dataset.
+
+**NOTE:** `TorchvisionWrapper` requires _torch_ and _torchvision_ to be installed.
+
+```python
+>>> from maite_datasets.object_detection import MILCO
+
+>>> milco = MILCO(root="data", download=True)
+>>> print(milco)
+MILCO Dataset
+-------------
+    Transforms: []
+    Image Set: train
+    Metadata: {'id': 'MILCO_train', 'index2label': {0: 'MILCO', 1: 'NOMBO'}, 'split': 'train'}
+    Path: /home/user/maite-datasets/data/milco
+    Size: 261
+
+>>> print(f"type={milco[0][0].__class__.__name__}, shape={milco[0][0].shape}")
+type=ndarray, shape=(3, 1024, 1024)
+
+>>> print(milco[0][1].boxes[0])
+[ 75. 217. 130. 247.]
+
+>>> from maite_datasets.wrappers import TorchvisionWrapper
+>>> from torchvision.transforms.v2 import Resize
+
+>>> milco_torch = TorchvisionWrapper(milco, transforms=Resize(224))
+>>> print(milco_torch)
+Torchvision Wrapped MILCO Dataset
+---------------------------
+    Transforms: Resize(size=[224], interpolation=InterpolationMode.BILINEAR, antialias=True)
+
+MILCO Dataset
+-------------
+    Transforms: []
+    Image Set: train
+    Metadata: {'id': 'MILCO_train', 'index2label': {0: 'MILCO', 1: 'NOMBO'}, 'split': 'train'}
+    Path: /home/user/maite-datasets/data/milco
+    Size: 261
+
+>>> print(f"type={milco_torch[0][0].__class__.__name__}, shape={milco_torch[0][0].shape}")
+type=Image, shape=torch.Size([3, 224, 224])
+
+>>> print(milco_torch[0][1].boxes[0])
+tensor([16.4062, 47.4688, 28.4375, 54.0312], dtype=torch.float64)
+```
+
+## Dataset Adapters
+
+Adapters provide a way to read in datasets from other popular formats.
+
+### Huggingface
+
+Hugging face datasets can be adapted into MAITE compliant format using the `from_huggingface` adapter.
+
+```python
+>>> from datasets import load_dataset
+>>> from maite_datasets.adapters import from_huggingface
+
+>>> cppe5 = load_dataset("cppe-5")
+>>> m_cppe5 = from_huggingface(cppe5["train"])
+>>> print(m_cppe5)
+HFObjectDetection Dataset
+-------------------------
+    Source: Dataset({
+    features: ['image_id', 'image', 'width', 'height', 'objects'],
+    num_rows: 1000
+})
+    Metadata: {'id': 'cppe-5', 'index2label': {0: 'Coverall', 1: 'Face_Shield', 2: 'Gloves', 3: 'Goggles', 4: 'Mask'}, 'description': '', 'citation': '', 'homepage': '', 'license': '', 'features': {'image_id': Value('int64'), 'image': Image(mode=None, decode=True), 'width': Value('int32'), 'height': Value('int32'), 'objects': {'id': List(Value('int64')), 'area': List(Value('int64')), 'bbox': List(List(Value('float32'), length=4)), 'category': List(ClassLabel(names=['Coverall', 'Face_Shield', 'Gloves', 'Goggles', 'Mask']))}}, 'post_processed': None, 'supervised_keys': None, 'builder_name': 'parquet', 'dataset_name': 'cppe-5', 'config_name': 'default', 'version': 0.0.0, 'splits': {'train': SplitInfo(name='train', num_bytes=240478590, num_examples=1000, shard_lengths=None, dataset_name='cppe-5'), 'test': SplitInfo(name='test', num_bytes=4172706, num_examples=29, shard_lengths=None, dataset_name='cppe-5')}, 'download_checksums': {'hf://datasets/cppe-5@66f6a5efd474e35bd7cb94bf15dea27d4c6ad3f8/data/train-00000-of-00001.parquet': {'num_bytes': 237015519, 'checksum': None}, 'hf://datasets/cppe-5@66f6a5efd474e35bd7cb94bf15dea27d4c6ad3f8/data/test-00000-of-00001.parquet': {'num_bytes': 4137134, 'checksum': None}}, 'download_size': 241152653, 'post_processing_size': None, 'dataset_size': 244651296, 'size_in_bytes': 485803949}
+
+>>> image = m_cppe5[0][0]
+>>> print(f"type={image.__class__.__name__}, shape={image.shape}")
+type=ndarray, shape=(3, 663, 943)
+
+>>> target = m_cppe5[0][1]
+>>> print(f"box={target.boxes[0]}, label={target.labels[0]}")
+box=[302.0, 109.0, 73.0, 52.0], label=4
+
+>>> print(m_cppe5[0][2])
+{'id': [114, 115, 116, 117], 'image_id': 15, 'width': 943, 'height': 663, 'area': [3796, 1596, 152768, 81002]}
+```
+
+## Additional Information
+
+For more information on the MAITE protocol, check out their [documentation](https://mit-ll-ai-technology.github.io/maite/).
+
+## Acknowledgement
+
+### CDAO Funding Acknowledgement
+
+This material is based upon work supported by the Chief Digital and Artificial
+Intelligence Office under Contract No. W519TC-23-9-2033. The views and
+conclusions contained herein are those of the author(s) and should not be
+interpreted as necessarily representing the official policies or endorsements,
+either expressed or implied, of the U.S. Government.

maite_datasets-0.0.7/README.md

@@ -0,0 +1,154 @@
+# MAITE Datasets
+
+MAITE Datasets are a collection of public datasets wrapped in a [MAITE](https://mit-ll-ai-technology.github.io/maite/) compliant format.
+
+## Installation
+
+To install and use `maite-datasets` you can use pip:
+
+```bash
+pip install maite-datasets
+```
+
+For status bar indicators when downloading, you can include the extra `tqdm` when installing:
+
+```bash
+pip install maite-datasets[tqdm]
+```
+
+## Available Downloadable Datasets
+
+| Task           | Dataset          | Description                                                         |
+|----------------|------------------|---------------------------------------------------------------------|
+| Classification | CIFAR10          | [CIFAR10](https://www.cs.toronto.edu/~kriz/cifar.html) dataset.     |
+| Classification | MNIST            | A dataset of hand-written digits.                                   |
+| Classification | Ships            | A dataset that focuses on identifying ships from satellite images.  |
+| Detection      | AntiUAVDetection | A UAV detection dataset in natural images with varying backgrounds. |
+| Detection      | MILCO            | A side-scan sonar dataset focused on mine-like object detection.    |
+| Detection      | Seadrone         | A UAV dataset focused on open water object detection.               |
+| Detection      | VOCDetection     | [Pascal VOC](http://host.robots.ox.ac.uk/pascal/VOC/) dataset.      |
+
+### Usage
+
+Here is an example of how to import MNIST for usage with your workflow.
+
+```python
+>>> from maite_datasets.image_classification import MNIST
+
+>>> mnist = MNIST(root="data", download=True)
+>>> print(mnist)
+MNIST Dataset
+-------------
+    Corruption: None
+    Transforms: []
+    Image_set: train
+    Metadata: {'id': 'MNIST_train', 'index2label': {0: 'zero', 1: 'one', 2: 'two', 3: 'three', 4: 'four', 5: 'five', 6: 'six', 7: 'seven', 8: 'eight', 9: 'nine'}, 'split': 'train'}
+    Path: /home/user/maite-datasets/data/mnist
+    Size: 60000
+
+>>> print("tuple("+", ".join([str(type(t)) for t in mnist[0]])+")")
+tuple(<class 'numpy.ndarray'>, <class 'numpy.ndarray'>, <class 'dict'>)
+```
+
+## Dataset Wrappers
+
+Wrappers provide a way to convert datasets to allow usage of tools within specific backend frameworks.
+
+### Torchvision
+
+`TorchvisionWrapper` is a convenience class that wraps any of the datasets and provides the capability to apply
+`torchvision` transforms to the dataset.
+
+**NOTE:** `TorchvisionWrapper` requires _torch_ and _torchvision_ to be installed.
+
+```python
+>>> from maite_datasets.object_detection import MILCO
+
+>>> milco = MILCO(root="data", download=True)
+>>> print(milco)
+MILCO Dataset
+-------------
+    Transforms: []
+    Image Set: train
+    Metadata: {'id': 'MILCO_train', 'index2label': {0: 'MILCO', 1: 'NOMBO'}, 'split': 'train'}
+    Path: /home/user/maite-datasets/data/milco
+    Size: 261
+
+>>> print(f"type={milco[0][0].__class__.__name__}, shape={milco[0][0].shape}")
+type=ndarray, shape=(3, 1024, 1024)
+
+>>> print(milco[0][1].boxes[0])
+[ 75. 217. 130. 247.]
+
+>>> from maite_datasets.wrappers import TorchvisionWrapper
+>>> from torchvision.transforms.v2 import Resize
+
+>>> milco_torch = TorchvisionWrapper(milco, transforms=Resize(224))
+>>> print(milco_torch)
+Torchvision Wrapped MILCO Dataset
+---------------------------
+    Transforms: Resize(size=[224], interpolation=InterpolationMode.BILINEAR, antialias=True)
+
+MILCO Dataset
+-------------
+    Transforms: []
+    Image Set: train
+    Metadata: {'id': 'MILCO_train', 'index2label': {0: 'MILCO', 1: 'NOMBO'}, 'split': 'train'}
+    Path: /home/user/maite-datasets/data/milco
+    Size: 261
+
+>>> print(f"type={milco_torch[0][0].__class__.__name__}, shape={milco_torch[0][0].shape}")
+type=Image, shape=torch.Size([3, 224, 224])
+
+>>> print(milco_torch[0][1].boxes[0])
+tensor([16.4062, 47.4688, 28.4375, 54.0312], dtype=torch.float64)
+```
+
+## Dataset Adapters
+
+Adapters provide a way to read in datasets from other popular formats.
+
+### Huggingface
+
+Hugging face datasets can be adapted into MAITE compliant format using the `from_huggingface` adapter.
+
+```python
+>>> from datasets import load_dataset
+>>> from maite_datasets.adapters import from_huggingface
+
+>>> cppe5 = load_dataset("cppe-5")
+>>> m_cppe5 = from_huggingface(cppe5["train"])
+>>> print(m_cppe5)
+HFObjectDetection Dataset
+-------------------------
+    Source: Dataset({
+    features: ['image_id', 'image', 'width', 'height', 'objects'],
+    num_rows: 1000
+})
+    Metadata: {'id': 'cppe-5', 'index2label': {0: 'Coverall', 1: 'Face_Shield', 2: 'Gloves', 3: 'Goggles', 4: 'Mask'}, 'description': '', 'citation': '', 'homepage': '', 'license': '', 'features': {'image_id': Value('int64'), 'image': Image(mode=None, decode=True), 'width': Value('int32'), 'height': Value('int32'), 'objects': {'id': List(Value('int64')), 'area': List(Value('int64')), 'bbox': List(List(Value('float32'), length=4)), 'category': List(ClassLabel(names=['Coverall', 'Face_Shield', 'Gloves', 'Goggles', 'Mask']))}}, 'post_processed': None, 'supervised_keys': None, 'builder_name': 'parquet', 'dataset_name': 'cppe-5', 'config_name': 'default', 'version': 0.0.0, 'splits': {'train': SplitInfo(name='train', num_bytes=240478590, num_examples=1000, shard_lengths=None, dataset_name='cppe-5'), 'test': SplitInfo(name='test', num_bytes=4172706, num_examples=29, shard_lengths=None, dataset_name='cppe-5')}, 'download_checksums': {'hf://datasets/cppe-5@66f6a5efd474e35bd7cb94bf15dea27d4c6ad3f8/data/train-00000-of-00001.parquet': {'num_bytes': 237015519, 'checksum': None}, 'hf://datasets/cppe-5@66f6a5efd474e35bd7cb94bf15dea27d4c6ad3f8/data/test-00000-of-00001.parquet': {'num_bytes': 4137134, 'checksum': None}}, 'download_size': 241152653, 'post_processing_size': None, 'dataset_size': 244651296, 'size_in_bytes': 485803949}
+
+>>> image = m_cppe5[0][0]
+>>> print(f"type={image.__class__.__name__}, shape={image.shape}")
+type=ndarray, shape=(3, 663, 943)
+
+>>> target = m_cppe5[0][1]
+>>> print(f"box={target.boxes[0]}, label={target.labels[0]}")
+box=[302.0, 109.0, 73.0, 52.0], label=4
+
+>>> print(m_cppe5[0][2])
+{'id': [114, 115, 116, 117], 'image_id': 15, 'width': 943, 'height': 663, 'area': [3796, 1596, 152768, 81002]}
+```
+
+## Additional Information
+
+For more information on the MAITE protocol, check out their [documentation](https://mit-ll-ai-technology.github.io/maite/).
+
+## Acknowledgement
+
+### CDAO Funding Acknowledgement
+
+This material is based upon work supported by the Chief Digital and Artificial
+Intelligence Office under Contract No. W519TC-23-9-2033. The views and
+conclusions contained herein are those of the author(s) and should not be
+interpreted as necessarily representing the official policies or endorsements,
+either expressed or implied, of the U.S. Government.

{maite_datasets-0.0.5 → maite_datasets-0.0.7}/pyproject.toml

@@ -2,10 +2,11 @@
 name = "maite-datasets"
 description = "A collection of Image Classification and Object Detection task datasets conforming to the MAITE protocol."
 readme = "README.md"
-requires-python = ">=3.9"
+requires-python = ">=3.10"
 dynamic = ["version"]
 dependencies = [
     "defusedxml>=0.7.1",
+    "maite>=0.7,<0.9",
     "numpy>=1.24.2",
     "pillow>=10.3.0",
     "requests>=2.32.3",
@@ -23,10 +24,10 @@ classifiers = [
    "Operating System :: OS Independent",
    "License :: OSI Approved :: MIT License",
    "Programming Language :: Python :: 3 :: Only",
-   "Programming Language :: Python :: 3.9",
    "Programming Language :: Python :: 3.10",
    "Programming Language :: Python :: 3.11",
    "Programming Language :: Python :: 3.12",
+   "Programming Language :: Python :: 3.13",
 ]
 
 [project.optional-dependencies]
@@ -36,35 +37,44 @@ tqdm = [
 
 [dependency-groups]
 base = [
-  "nox[uv]>=2025.5.1",
+  "nox>=2025.5.1",
+  "nox-uv>=0.6.2",
+  "uv>=0.8.0",
+]
+more = [
   "torch>=2.2.0",
-  "uv>=0.7.8",
+  "torchvision>=0.17.0",
+  "tqdm>=4.66",
 ]
 lint = [
+  { include-group = "base" },
   "ruff>=0.11",
   "codespell[toml]>=2.3",
 ]
 test = [
   { include-group = "base" },
+  { include-group = "more" },
   "pytest>=8.3",
   "pytest-cov>=6.1",
   "coverage[toml]>=7.6",
 ]
 type = [
   { include-group = "base" },
+  { include-group = "more" },
   "pyright[nodejs]>=1.1.400",
 ]
 dev = [
   { include-group = "base" },
+  { include-group = "more" },
   { include-group = "lint" },
   { include-group = "test" },
   { include-group = "type" },
+  "ipykernel>=6.30.0",
 ]
 
 [tool.uv.sources]
-torch = [
-  { index = "pytorch-cpu" },
-]
+torch = [{ index = "pytorch-cpu" }]
+torchvision = [{ index = "pytorch-cpu" }]
 
 [[tool.uv.index]]
 name = "pytorch-cpu"
@@ -108,6 +118,14 @@ line-length = 120
 indent-width = 4
 target-version = "py39"
 
+[tool.ruff.lint]
+select = ["A", "ANN", "C4", "C90", "E", "F", "I", "NPY", "S", "SIM", "RET", "RUF100", "UP"]
+ignore = ["ANN401", "NPY002"]
+fixable = ["ALL"]
+unfixable = []
+dummy-variable-rgx = "^(_+|(_+[a-zA-Z0-9_]*[a-zA-Z0-9]+?))$"
+per-file-ignores = { "!src/*" = ["ANN", "S", "RET"]}
+
 [tool.ruff.lint.isort]
 known-first-party = ["maite_datasets"]
 

{maite_datasets-0.0.5 → maite_datasets-0.0.7}/src/maite_datasets/__init__.py

@@ -1,11 +1,9 @@
 """Module for MAITE compliant Computer Vision datasets."""
 
 from maite_datasets._builder import to_image_classification_dataset, to_object_detection_dataset
-from maite_datasets._collate import collate_as_torch, collate_as_numpy, collate_as_list
+from maite_datasets._collate import collate_as_list, collate_as_numpy, collate_as_torch
+from maite_datasets._reader import create_dataset_reader
 from maite_datasets._validate import validate_dataset
-from maite_datasets._reader._factory import create_dataset_reader
-from maite_datasets._reader._coco import COCODatasetReader
-from maite_datasets._reader._yolo import YOLODatasetReader
 
 __all__ = [
     "collate_as_list",
@@ -15,6 +13,4 @@ __all__ = [
     "to_image_classification_dataset",
     "to_object_detection_dataset",
     "validate_dataset",
-    "COCODatasetReader",
-    "YOLODatasetReader",
 ]