[prototype] Clean up `features` area (#6834)

* Clean ups on `features` area

* remove unncessary imports

torchvision/prototype/features/__init__.py

 from ._bounding_box import BoundingBox, BoundingBoxFormat
 from ._encoded import EncodedData, EncodedImage
 from ._feature import _Feature, FillType, FillTypeJIT, InputType, InputTypeJIT, is_simple_tensor
-from ._image import (
-    ColorSpace,
-    Image,
-    ImageType,
-    ImageTypeJIT,
-    LegacyImageType,
-    LegacyImageTypeJIT,
-    TensorImageType,
-    TensorImageTypeJIT,
-)
+from ._image import ColorSpace, Image, ImageType, ImageTypeJIT, TensorImageType, TensorImageTypeJIT
 from ._label import Label, OneHotLabel
 from ._mask import Mask
-from ._video import (
-    LegacyVideoType,
-    LegacyVideoTypeJIT,
-    TensorVideoType,
-    TensorVideoTypeJIT,
-    Video,
-    VideoType,
-    VideoTypeJIT,
-)
+from ._video import TensorVideoType, TensorVideoTypeJIT, Video, VideoType, VideoTypeJIT

torchvision/prototype/features/_bounding_box.py

@@ -61,18 +61,6 @@ class BoundingBox(_Feature):
     def __repr__(self, *, tensor_contents: Any = None) -> str:  # type: ignore[override]
         return self._make_repr(format=self.format, spatial_size=self.spatial_size)
 
-    def to_format(self, format: Union[str, BoundingBoxFormat]) -> BoundingBox:
-        if isinstance(format, str):
-            format = BoundingBoxFormat.from_str(format.upper())
-
-        return BoundingBox.wrap_like(
-            self,
-            self._F.convert_format_bounding_box(
-                self.as_subclass(torch.Tensor), old_format=self.format, new_format=format
-            ),
-            format=format,
-        )
-
     def horizontal_flip(self) -> BoundingBox:
         output = self._F.horizontal_flip_bounding_box(
             self.as_subclass(torch.Tensor), format=self.format, spatial_size=self.spatial_size

torchvision/prototype/features/_image.py

 from __future__ import annotations
 
 import warnings
-from typing import Any, cast, List, Optional, Tuple, Union
+from typing import Any, List, Optional, Tuple, Union
 
 import PIL.Image
 import torch
@@ -104,7 +104,7 @@ class Image(_Feature):
 
     @property
     def spatial_size(self) -> Tuple[int, int]:
-        return cast(Tuple[int, int], tuple(self.shape[-2:]))
+        return tuple(self.shape[-2:])  # type: ignore[return-value]
 
     @property
     def num_channels(self) -> int:
@@ -285,7 +285,5 @@ class Image(_Feature):
 
 ImageType = Union[torch.Tensor, PIL.Image.Image, Image]
 ImageTypeJIT = torch.Tensor
-LegacyImageType = Union[torch.Tensor, PIL.Image.Image]
-LegacyImageTypeJIT = torch.Tensor
 TensorImageType = Union[torch.Tensor, Image]
 TensorImageTypeJIT = torch.Tensor

torchvision/prototype/features/_mask.py

 from __future__ import annotations
 
-from typing import Any, cast, List, Optional, Tuple, Union
+from typing import Any, List, Optional, Tuple, Union
 
 import torch
 from torchvision.transforms import InterpolationMode
@@ -34,7 +34,7 @@ class Mask(_Feature):
 
     @property
     def spatial_size(self) -> Tuple[int, int]:
-        return cast(Tuple[int, int], tuple(self.shape[-2:]))
+        return tuple(self.shape[-2:])  # type: ignore[return-value]
 
     def horizontal_flip(self) -> Mask:
         output = self._F.horizontal_flip_mask(self.as_subclass(torch.Tensor))

torchvision/prototype/features/_video.py

 from __future__ import annotations
 
 import warnings
-from typing import Any, cast, List, Optional, Tuple, Union
+from typing import Any, List, Optional, Tuple, Union
 
 import torch
 from torchvision.transforms.functional import InterpolationMode
@@ -56,7 +56,7 @@ class Video(_Feature):
 
     @property
     def spatial_size(self) -> Tuple[int, int]:
-        return cast(Tuple[int, int], tuple(self.shape[-2:]))
+        return tuple(self.shape[-2:])  # type: ignore[return-value]
 
     @property
     def num_channels(self) -> int:
@@ -237,7 +237,5 @@ class Video(_Feature):
 
 VideoType = Union[torch.Tensor, Video]
 VideoTypeJIT = torch.Tensor
-LegacyVideoType = torch.Tensor
-LegacyVideoTypeJIT = torch.Tensor
 TensorVideoType = Union[torch.Tensor, Video]
 TensorVideoTypeJIT = torch.Tensor

torchvision/prototype/transforms/functional/_deprecated.py

@@ -23,8 +23,8 @@ def to_grayscale(inpt: PIL.Image.Image, num_output_channels: int = 1) -> PIL.Ima
 
 
 def rgb_to_grayscale(
-    inpt: Union[features.LegacyImageTypeJIT, features.LegacyVideoTypeJIT], num_output_channels: int = 1
-) -> Union[features.LegacyImageTypeJIT, features.LegacyVideoTypeJIT]:
+    inpt: Union[features.ImageTypeJIT, features.VideoTypeJIT], num_output_channels: int = 1
+) -> Union[features.ImageTypeJIT, features.VideoTypeJIT]:
     if not torch.jit.is_scripting() and isinstance(inpt, (features.Image, features.Video)):
         inpt = inpt.as_subclass(torch.Tensor)
         old_color_space = None

torchvision/prototype/transforms/functional/_misc.py

@@ -16,9 +16,7 @@ def normalize_image_tensor(
         raise TypeError(f"Input tensor should be a float tensor. Got {image.dtype}.")
 
     if image.ndim < 3:
-        raise ValueError(
-            f"Expected tensor to be a tensor image of size (..., C, H, W). Got tensor.size() = {image.size()}"
-        )
+        raise ValueError(f"Expected tensor to be a tensor image of size (..., C, H, W). Got {image.shape}.")
 
     if isinstance(std, (tuple, list)):
         divzero = not all(std)