Merge branch 'main' into improved-affine

Author: vfdev-5

docs/source/datasets.rst

@@ -41,6 +41,7 @@ You can also create your own datasets using the provided :ref:`base classes <bas
     Country211
     DTD
     EMNIST
+    EuroSAT
     FakeData
     FashionMNIST
     FER2013
@@ -74,6 +75,7 @@ You can also create your own datasets using the provided :ref:`base classes <bas
     SBU
     SEMEION
     Sintel
+    StanfordCars
     STL10
     SUN397
     SVHN

docs/source/index.rst

@@ -31,13 +31,13 @@ architectures, and common image transformations for computer vision.
    :maxdepth: 2
    :caption: Package Reference
 
-   datasets
    transforms
    models
-   feature_extraction
+   datasets
+   utils
    ops
    io
-   utils
+   feature_extraction
 
 .. toctree::
    :maxdepth: 1

test/test_datasets.py

@@ -2169,6 +2169,27 @@ def inject_fake_data(self, tmpdir, config):
         return num_sequences * (num_examples_per_sequence - 1)
 
 
+class EuroSATTestCase(datasets_utils.ImageDatasetTestCase):
+    DATASET_CLASS = datasets.EuroSAT
+    FEATURE_TYPES = (PIL.Image.Image, int)
+
+    def inject_fake_data(self, tmpdir, config):
+        data_folder = os.path.join(tmpdir, "eurosat", "2750")
+        os.makedirs(data_folder)
+
+        num_examples_per_class = 3
+        classes = ("AnnualCrop", "Forest")
+        for cls in classes:
+            datasets_utils.create_image_folder(
+                root=data_folder,
+                name=cls,
+                file_name_fn=lambda idx: f"{cls}_{idx}.jpg",
+                num_examples=num_examples_per_class,
+            )
+
+        return len(classes) * num_examples_per_class
+
+
 class Food101TestCase(datasets_utils.ImageDatasetTestCase):
     DATASET_CLASS = datasets.Food101
     FEATURE_TYPES = (PIL.Image.Image, int)
@@ -2514,6 +2535,50 @@ def _meta_to_split_and_classification_ann(self, meta, idx):
         return (image_id, class_id, species, breed_id)
 
 
+class StanfordCarsTestCase(datasets_utils.ImageDatasetTestCase):
+    DATASET_CLASS = datasets.StanfordCars
+    REQUIRED_PACKAGES = ("scipy",)
+    ADDITIONAL_CONFIGS = datasets_utils.combinations_grid(split=("train", "test"))
+
+    def inject_fake_data(self, tmpdir, config):
+        import scipy.io as io
+        from numpy.core.records import fromarrays
+
+        num_examples = {"train": 5, "test": 7}[config["split"]]
+        num_classes = 3
+        base_folder = pathlib.Path(tmpdir) / "stanford_cars"
+
+        devkit = base_folder / "devkit"
+        devkit.mkdir(parents=True)
+
+        if config["split"] == "train":
+            images_folder_name = "cars_train"
+            annotations_mat_path = devkit / "cars_train_annos.mat"
+        else:
+            images_folder_name = "cars_test"
+            annotations_mat_path = base_folder / "cars_test_annos_withlabels.mat"
+
+        datasets_utils.create_image_folder(
+            root=base_folder,
+            name=images_folder_name,
+            file_name_fn=lambda image_index: f"{image_index:5d}.jpg",
+            num_examples=num_examples,
+        )
+
+        classes = np.random.randint(1, num_classes + 1, num_examples, dtype=np.uint8)
+        fnames = [f"{i:5d}.jpg" for i in range(num_examples)]
+        rec_array = fromarrays(
+            [classes, fnames],
+            names=["class", "fname"],
+        )
+        io.savemat(annotations_mat_path, {"annotations": rec_array})
+
+        random_class_names = ["random_name"] * num_classes
+        io.savemat(devkit / "cars_meta.mat", {"class_names": random_class_names})
+
+        return num_examples
+
+
 class Country211TestCase(datasets_utils.ImageDatasetTestCase):
     DATASET_CLASS = datasets.Country211
 

torchvision/datasets/__init__.py

@@ -7,6 +7,7 @@
 from .coco import CocoCaptions, CocoDetection
 from .country211 import Country211
 from .dtd import DTD
+from .eurosat import EuroSAT
 from .fakedata import FakeData
 from .fer2013 import FER2013
 from .fgvc_aircraft import FGVCAircraft
@@ -31,6 +32,7 @@
 from .sbd import SBDataset
 from .sbu import SBU
 from .semeion import SEMEION
+from .stanford_cars import StanfordCars
 from .stl10 import STL10
 from .sun397 import SUN397
 from .svhn import SVHN
@@ -55,6 +57,7 @@
     "QMNIST",
     "MNIST",
     "KMNIST",
+    "StanfordCars",
     "STL10",
     "SUN397",
     "SVHN",
@@ -98,4 +101,5 @@
     "OxfordIIITPet",
     "Country211",
     "FGVCAircraft",
+    "EuroSAT",
 )

torchvision/datasets/eurosat.py

@@ -0,0 +1,56 @@
+import os
+from typing import Any
+
+from .folder import ImageFolder
+from .utils import download_and_extract_archive
+
+
+class EuroSAT(ImageFolder):
+    """RGB version of the `EuroSAT <https://github.com/phelber/eurosat>`_ Dataset.
+
+    Args:
+        root (string): Root directory of dataset where ``root/eurosat`` exists.
+        download (bool, optional): If True, downloads the dataset from the internet and
+            puts it in root directory. If dataset is already downloaded, it is not
+            downloaded again. Default is False.
+        transform (callable, optional): A function/transform that  takes in an PIL image
+            and returns a transformed version. E.g, ``transforms.RandomCrop``
+        target_transform (callable, optional): A function/transform that takes in the
+            target and transforms it.
+    """
+
+    url = "https://madm.dfki.de/files/sentinel/EuroSAT.zip"
+    md5 = "c8fa014336c82ac7804f0398fcb19387"
+
+    def __init__(
+        self,
+        root: str,
+        download: bool = False,
+        **kwargs: Any,
+    ) -> None:
+        self.root = os.path.expanduser(root)
+        self._base_folder = os.path.join(self.root, "eurosat")
+        self._data_folder = os.path.join(self._base_folder, "2750")
+
+        if download:
+            self.download()
+
+        if not self._check_exists():
+            raise RuntimeError("Dataset not found. You can use download=True to download it")
+
+        super().__init__(self._data_folder, **kwargs)
+        self.root = os.path.expanduser(root)
+
+    def __len__(self) -> int:
+        return len(self.samples)
+
+    def _check_exists(self) -> bool:
+        return os.path.exists(self._data_folder)
+
+    def download(self) -> None:
+
+        if self._check_exists():
+            return
+
+        os.makedirs(self._base_folder, exist_ok=True)
+        download_and_extract_archive(self.url, download_root=self._base_folder, md5=self.md5)

torchvision/datasets/stanford_cars.py

@@ -0,0 +1,121 @@
+import pathlib
+from typing import Callable, Optional, Any, Tuple
+
+from PIL import Image
+
+from .utils import download_and_extract_archive, download_url, verify_str_arg
+from .vision import VisionDataset
+
+
+class StanfordCars(VisionDataset):
+    """`Stanford Cars <https://ai.stanford.edu/~jkrause/cars/car_dataset.html>`_ Dataset
+
+    The Cars dataset contains 16,185 images of 196 classes of cars. The data is
+    split into 8,144 training images and 8,041 testing images, where each class
+    has been split roughly in a 50-50 split
+
+    .. note::
+
+        This class needs `scipy <https://docs.scipy.org/doc/>`_ to load target files from `.mat` format.
+
+    Args:
+        root (string): Root directory of dataset
+        split (string, optional): The dataset split, supports ``"train"`` (default) or ``"test"``.
+        transform (callable, optional): A function/transform that  takes in an PIL image
+            and returns a transformed version. E.g, ``transforms.RandomCrop``
+        target_transform (callable, optional): A function/transform that takes in the
+            target and transforms it.
+        download (bool, optional): If True, downloads the dataset from the internet and
+            puts it in root directory. If dataset is already downloaded, it is not
+            downloaded again."""
+
+    def __init__(
+        self,
+        root: str,
+        split: str = "train",
+        transform: Optional[Callable] = None,
+        target_transform: Optional[Callable] = None,
+        download: bool = False,
+    ) -> None:
+
+        try:
+            import scipy.io as sio
+        except ImportError:
+            raise RuntimeError("Scipy is not found. This dataset needs to have scipy installed: pip install scipy")
+
+        super().__init__(root, transform=transform, target_transform=target_transform)
+
+        self._split = verify_str_arg(split, "split", ("train", "test"))
+        self._base_folder = pathlib.Path(root) / "stanford_cars"
+        devkit = self._base_folder / "devkit"
+
+        if self._split == "train":
+            self._annotations_mat_path = devkit / "cars_train_annos.mat"
+            self._images_base_path = self._base_folder / "cars_train"
+        else:
+            self._annotations_mat_path = self._base_folder / "cars_test_annos_withlabels.mat"
+            self._images_base_path = self._base_folder / "cars_test"
+
+        if download:
+            self.download()
+
+        if not self._check_exists():
+            raise RuntimeError("Dataset not found. You can use download=True to download it")
+
+        self._samples = [
+            (
+                str(self._images_base_path / annotation["fname"]),
+                annotation["class"] - 1,  # Original target mapping  starts from 1, hence -1
+            )
+            for annotation in sio.loadmat(self._annotations_mat_path, squeeze_me=True)["annotations"]
+        ]
+
+        self.classes = sio.loadmat(str(devkit / "cars_meta.mat"), squeeze_me=True)["class_names"].tolist()
+        self.class_to_idx = {cls: i for i, cls in enumerate(self.classes)}
+
+    def __len__(self) -> int:
+        return len(self._samples)
+
+    def __getitem__(self, idx: int) -> Tuple[Any, Any]:
+        """Returns pil_image and class_id for given index"""
+        image_path, target = self._samples[idx]
+        pil_image = Image.open(image_path).convert("RGB")
+
+        if self.transform is not None:
+            pil_image = self.transform(pil_image)
+        if self.target_transform is not None:
+            target = self.target_transform(target)
+        return pil_image, target
+
+    def download(self) -> None:
+        if self._check_exists():
+            return
+
+        download_and_extract_archive(
+            url="https://ai.stanford.edu/~jkrause/cars/car_devkit.tgz",
+            download_root=str(self._base_folder),
+            md5="c3b158d763b6e2245038c8ad08e45376",
+        )
+        if self._split == "train":
+            download_and_extract_archive(
+                url="https://ai.stanford.edu/~jkrause/car196/cars_train.tgz",
+                download_root=str(self._base_folder),
+                md5="065e5b463ae28d29e77c1b4b166cfe61",
+            )
+        else:
+            download_and_extract_archive(
+                url="https://ai.stanford.edu/~jkrause/car196/cars_test.tgz",
+                download_root=str(self._base_folder),
+                md5="4ce7ebf6a94d07f1952d94dd34c4d501",
+            )
+            download_url(
+                url="https://ai.stanford.edu/~jkrause/car196/cars_test_annos_withlabels.mat",
+                root=str(self._base_folder),
+                md5="b0a2b23655a3edd16d84508592a98d10",
+            )
+
+    def _check_exists(self) -> bool:
+        if not (self._base_folder / "devkit").is_dir():
+            return False
+
+        return self._annotations_mat_path.exists() and self._images_base_path.is_dir()