Merge branch 'main' into models/convnext

Author: datumbox

mypy.ini

@@ -117,3 +117,7 @@ ignore_missing_imports = True
 [mypy-torchdata.*]
 
 ignore_missing_imports = True
+
+[mypy-h5py.*]
+
+ignore_missing_imports = True

test/test_datasets.py

@@ -2281,11 +2281,6 @@ def inject_fake_data(self, tmpdir: str, config):
 class SUN397TestCase(datasets_utils.ImageDatasetTestCase):
     DATASET_CLASS = datasets.SUN397
 
-    ADDITIONAL_CONFIGS = datasets_utils.combinations_grid(
-        split=("train", "test"),
-        partition=(1, 10, None),
-    )
-
     def inject_fake_data(self, tmpdir: str, config):
         data_dir = pathlib.Path(tmpdir) / "SUN397"
         data_dir.mkdir()
@@ -2308,18 +2303,7 @@ def inject_fake_data(self, tmpdir: str, config):
         with open(data_dir / "ClassName.txt", "w") as file:
             file.writelines("\n".join(f"/{cls[0]}/{cls}" for cls in sampled_classes))
 
-        if config["partition"] is not None:
-            num_samples = max(len(im_paths) // (2 if config["split"] == "train" else 3), 1)
-
-            with open(data_dir / f"{config['split'].title()}ing_{config['partition']:02d}.txt", "w") as file:
-                file.writelines(
-                    "\n".join(
-                        f"/{f_path.relative_to(data_dir).as_posix()}"
-                        for f_path in random.choices(im_paths, k=num_samples)
-                    )
-                )
-        else:
-            num_samples = len(im_paths)
+        num_samples = len(im_paths)
 
         return num_samples
 
@@ -2397,17 +2381,17 @@ class GTSRBTestCase(datasets_utils.ImageDatasetTestCase):
     DATASET_CLASS = datasets.GTSRB
     FEATURE_TYPES = (PIL.Image.Image, int)
 
-    ADDITIONAL_CONFIGS = datasets_utils.combinations_grid(train=(True, False))
+    ADDITIONAL_CONFIGS = datasets_utils.combinations_grid(split=("train", "test"))
 
     def inject_fake_data(self, tmpdir: str, config):
-        root_folder = os.path.join(tmpdir, "GTSRB")
+        root_folder = os.path.join(tmpdir, "gtsrb")
         os.makedirs(root_folder, exist_ok=True)
 
         # Train data
-        train_folder = os.path.join(root_folder, "Training")
+        train_folder = os.path.join(root_folder, "GTSRB", "Training")
         os.makedirs(train_folder, exist_ok=True)
 
-        num_examples = 3
+        num_examples = 3 if config["split"] == "train" else 4
         classes = ("00000", "00042", "00012")
         for class_idx in classes:
             datasets_utils.create_image_folder(
@@ -2419,7 +2403,7 @@ def inject_fake_data(self, tmpdir: str, config):
 
         total_number_of_examples = num_examples * len(classes)
         # Test data
-        test_folder = os.path.join(root_folder, "Final_Test", "Images")
+        test_folder = os.path.join(root_folder, "GTSRB", "Final_Test", "Images")
         os.makedirs(test_folder, exist_ok=True)
 
         with open(os.path.join(root_folder, "GT-final_test.csv"), "w") as csv_file:

test/test_prototype_models.py

@@ -97,7 +97,7 @@ def test_naming_conventions(model_fn):
 )
 @run_if_test_with_prototype
 def test_schema_meta_validation(model_fn):
-    classification_fields = ["size", "categories", "acc@1", "acc@5"]
+    classification_fields = ["size", "categories", "acc@1", "acc@5", "min_size"]
     defaults = {
         "all": ["task", "architecture", "publication_year", "interpolation", "recipe", "num_params"],
         "models": classification_fields,

torchvision/datasets/clevr.py

@@ -34,7 +34,7 @@ def __init__(
         split: str = "train",
         transform: Optional[Callable] = None,
         target_transform: Optional[Callable] = None,
-        download: bool = True,
+        download: bool = False,
     ) -> None:
         self._split = verify_str_arg(split, "split", ("train", "val", "test"))
         super().__init__(root, transform=transform, target_transform=target_transform)

torchvision/datasets/country211.py

@@ -32,7 +32,7 @@ def __init__(
         split: str = "train",
         transform: Optional[Callable] = None,
         target_transform: Optional[Callable] = None,
-        download: bool = True,
+        download: bool = False,
     ) -> None:
         self._split = verify_str_arg(split, "split", ("train", "valid", "test"))
 

torchvision/datasets/dtd.py

@@ -21,12 +21,12 @@ class DTD(VisionDataset):
                 The partition only changes which split each image belongs to. Thus, regardless of the selected
                 partition, combining all splits will result in all images.
 
-        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.
         transform (callable, optional): A function/transform that  takes in a 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. Default is False.
     """
 
     _URL = "https://www.robots.ox.ac.uk/~vgg/data/dtd/download/dtd-r1.0.1.tar.gz"
@@ -37,9 +37,9 @@ def __init__(
         root: str,
         split: str = "train",
         partition: int = 1,
-        download: bool = True,
         transform: Optional[Callable] = None,
         target_transform: Optional[Callable] = None,
+        download: bool = False,
     ) -> None:
         self._split = verify_str_arg(split, "split", ("train", "val", "test"))
         if not isinstance(partition, int) and not (1 <= partition <= 10):

torchvision/datasets/eurosat.py

@@ -1,5 +1,5 @@
 import os
-from typing import Any
+from typing import Callable, Optional
 
 from .folder import ImageFolder
 from .utils import download_and_extract_archive
@@ -10,23 +10,21 @@ class EuroSAT(ImageFolder):
 
     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.
+        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.
     """
 
-    url = "https://madm.dfki.de/files/sentinel/EuroSAT.zip"
-    md5 = "c8fa014336c82ac7804f0398fcb19387"
-
     def __init__(
         self,
         root: str,
+        transform: Optional[Callable] = None,
+        target_transform: Optional[Callable] = None,
         download: bool = False,
-        **kwargs: Any,
     ) -> None:
         self.root = os.path.expanduser(root)
         self._base_folder = os.path.join(self.root, "eurosat")
@@ -38,7 +36,7 @@ def __init__(
         if not self._check_exists():
             raise RuntimeError("Dataset not found. You can use download=True to download it")
 
-        super().__init__(self._data_folder, **kwargs)
+        super().__init__(self._data_folder, transform=transform, target_transform=target_transform)
         self.root = os.path.expanduser(root)
 
     def __len__(self) -> int:
@@ -53,4 +51,8 @@ def download(self) -> None:
             return
 
         os.makedirs(self._base_folder, exist_ok=True)
-        download_and_extract_archive(self.url, download_root=self._base_folder, md5=self.md5)
+        download_and_extract_archive(
+            "https://madm.dfki.de/files/sentinel/EuroSAT.zip",
+            download_root=self._base_folder,
+            md5="c8fa014336c82ac7804f0398fcb19387",
+        )

torchvision/datasets/fgvc_aircraft.py

@@ -26,15 +26,15 @@ class FGVCAircraft(VisionDataset):
         root (string): Root directory of the FGVC Aircraft dataset.
         split (string, optional): The dataset split, supports ``train``, ``val``,
             ``trainval`` and ``test``.
-        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.
         annotation_level (str, optional): The annotation level, supports ``variant``,
             ``family`` and ``manufacturer``.
         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.
     """
 
     _URL = "https://www.robots.ox.ac.uk/~vgg/data/fgvc-aircraft/archives/fgvc-aircraft-2013b.tar.gz"
@@ -43,10 +43,10 @@ def __init__(
         self,
         root: str,
         split: str = "trainval",
-        download: bool = False,
         annotation_level: str = "variant",
         transform: Optional[Callable] = None,
         target_transform: Optional[Callable] = None,
+        download: bool = False,
     ) -> None:
         super().__init__(root, transform=transform, target_transform=target_transform)
         self._split = verify_str_arg(split, "split", ("train", "val", "trainval", "test"))

torchvision/datasets/flowers102.py

@@ -24,12 +24,12 @@ class Flowers102(VisionDataset):
     Args:
         root (string): Root directory of the dataset.
         split (string, optional): The dataset split, supports ``"train"`` (default), ``"val"``, or ``"test"``.
-        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.
         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.
     """
 
     _download_url_prefix = "https://www.robots.ox.ac.uk/~vgg/data/flowers/102/"
@@ -44,9 +44,9 @@ def __init__(
         self,
         root: str,
         split: str = "train",
-        download: bool = True,
         transform: Optional[Callable] = None,
         target_transform: Optional[Callable] = None,
+        download: bool = False,
     ) -> None:
         super().__init__(root, transform=transform, target_transform=target_transform)
         self._split = verify_str_arg(split, "split", ("train", "val", "test"))

torchvision/datasets/food101.py

@@ -24,6 +24,9 @@ class Food101(VisionDataset):
         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. Default is False.
     """
 
     _URL = "http://data.vision.ee.ethz.ch/cvl/food-101.tar.gz"
@@ -33,9 +36,9 @@ def __init__(
         self,
         root: str,
         split: str = "train",
-        download: bool = True,
         transform: Optional[Callable] = None,
         target_transform: Optional[Callable] = None,
+        download: bool = False,
     ) -> None:
         super().__init__(root, transform=transform, target_transform=target_transform)
         self._split = verify_str_arg(split, "split", ("train", "test"))