Restored fill default value to None

vfdev-5 · vfdev-5 · commit 4a0cec5143db · 2022-07-08T16:02:59.000+02:00
Updated code according to the review
diff --git a/test/test_prototype_transforms.py b/test/test_prototype_transforms.py
@@ -72,6 +72,7 @@ class TestSmoke:
         transforms.ConvertImageDtype(),
         transforms.RandomHorizontalFlip(),
         transforms.Pad(5),
+        transforms.RandomZoomOut(),
     )
     def test_common(self, transform, input):
         transform(input)
diff --git a/torchvision/prototype/features/_bounding_box.py b/torchvision/prototype/features/_bounding_box.py
@@ -130,7 +130,7 @@ def resized_crop(
     def pad(
         self,
         padding: Union[int, Sequence[int]],
-        fill: Union[int, float, Sequence[int], Sequence[float]] = 0,
+        fill: Optional[Union[int, float, Sequence[int], Sequence[float]]] = None,
         padding_mode: str = "constant",
     ) -> BoundingBox:
         from torchvision.prototype.transforms import functional as _F
@@ -160,7 +160,7 @@ def rotate(
         angle: float,
         interpolation: InterpolationMode = InterpolationMode.NEAREST,
         expand: bool = False,
-        fill: Union[int, float, Sequence[int], Sequence[float]] = 0,
+        fill: Optional[Union[int, float, Sequence[int], Sequence[float]]] = None,
         center: Optional[List[float]] = None,
     ) -> BoundingBox:
         from torchvision.prototype.transforms import functional as _F
@@ -180,7 +180,7 @@ def affine(
         scale: float,
         shear: List[float],
         interpolation: InterpolationMode = InterpolationMode.NEAREST,
-        fill: Union[int, float, Sequence[int], Sequence[float]] = 0,
+        fill: Optional[Union[int, float, Sequence[int], Sequence[float]]] = None,
         center: Optional[List[float]] = None,
     ) -> BoundingBox:
         from torchvision.prototype.transforms import functional as _F
@@ -201,7 +201,7 @@ def perspective(
         self,
         perspective_coeffs: List[float],
         interpolation: InterpolationMode = InterpolationMode.BILINEAR,
-        fill: Optional[List[float]] = None,
+        fill: Optional[Union[int, float, Sequence[int], Sequence[float]]] = None,
     ) -> BoundingBox:
         from torchvision.prototype.transforms import functional as _F
 
diff --git a/torchvision/prototype/features/_feature.py b/torchvision/prototype/features/_feature.py
@@ -122,7 +122,7 @@ def resized_crop(
     def pad(
         self,
         padding: Union[int, Sequence[int]],
-        fill: Union[int, float, Sequence[int], Sequence[float]] = 0,
+        fill: Optional[Union[int, float, Sequence[int], Sequence[float]]] = None,
         padding_mode: str = "constant",
     ) -> Any:
         return self
@@ -132,7 +132,7 @@ def rotate(
         angle: float,
         interpolation: InterpolationMode = InterpolationMode.NEAREST,
         expand: bool = False,
-        fill: Union[int, float, Sequence[int], Sequence[float]] = 0,
+        fill: Optional[Union[int, float, Sequence[int], Sequence[float]]] = None,
         center: Optional[List[float]] = None,
     ) -> Any:
         return self
@@ -144,7 +144,7 @@ def affine(
         scale: float,
         shear: List[float],
         interpolation: InterpolationMode = InterpolationMode.NEAREST,
-        fill: Union[int, float, Sequence[int], Sequence[float]] = 0,
+        fill: Optional[Union[int, float, Sequence[int], Sequence[float]]] = None,
         center: Optional[List[float]] = None,
     ) -> Any:
         return self
@@ -153,7 +153,7 @@ def perspective(
         self,
         perspective_coeffs: List[float],
         interpolation: InterpolationMode = InterpolationMode.BILINEAR,
-        fill: Optional[List[float]] = None,
+        fill: Optional[Union[int, float, Sequence[int], Sequence[float]]] = None,
     ) -> Any:
         return self
 
diff --git a/torchvision/prototype/features/_image.py b/torchvision/prototype/features/_image.py
@@ -166,7 +166,7 @@ def resized_crop(
     def pad(
         self,
         padding: Union[int, Sequence[int]],
-        fill: Union[int, float, Sequence[int], Sequence[float]] = 0,
+        fill: Optional[Union[int, float, Sequence[int], Sequence[float]]] = None,
         padding_mode: str = "constant",
     ) -> Image:
         from torchvision.prototype.transforms import functional as _F
@@ -175,6 +175,9 @@ def pad(
         if not isinstance(padding, int):
             padding = list(padding)
 
+        if fill is None:
+            fill = 0
+
         # PyTorch's pad supports only scalars on fill. So we need to overwrite the colour
         if isinstance(fill, (int, float)):
             output = _F.pad_image_tensor(self, padding, fill=fill, padding_mode=padding_mode)
@@ -190,18 +193,12 @@ def rotate(
         angle: float,
         interpolation: InterpolationMode = InterpolationMode.NEAREST,
         expand: bool = False,
-        fill: Union[int, float, Sequence[int], Sequence[float]] = 0,
+        fill: Optional[Union[int, float, Sequence[int], Sequence[float]]] = None,
         center: Optional[List[float]] = None,
     ) -> Image:
-        from torchvision.prototype.transforms import functional as _F
+        from torchvision.prototype.transforms.functional import _geometry as _F
 
-        # This cast does Sequence -> List[float] to please mypy and torch.jit.script
-        if not isinstance(fill, (int, float)):
-            fill = [float(v) for v in list(fill)]
-
-        if isinstance(fill, (int, float)):
-            # It is OK to cast int to float as later we use inpt.dtype
-            fill = [float(fill)]
+        fill = _F._convert_fill_arg(fill)
 
         output = _F.rotate_image_tensor(
             self, angle, interpolation=interpolation, expand=expand, fill=fill, center=center
@@ -215,18 +212,12 @@ def affine(
         scale: float,
         shear: List[float],
         interpolation: InterpolationMode = InterpolationMode.NEAREST,
-        fill: Union[int, float, Sequence[int], Sequence[float]] = 0,
+        fill: Optional[Union[int, float, Sequence[int], Sequence[float]]] = None,
         center: Optional[List[float]] = None,
     ) -> Image:
-        from torchvision.prototype.transforms import functional as _F
+        from torchvision.prototype.transforms.functional import _geometry as _F
 
-        # This cast does Sequence -> List[float] to please mypy and torch.jit.script
-        if not isinstance(fill, (int, float)):
-            fill = [float(v) for v in list(fill)]
-
-        if isinstance(fill, (int, float)):
-            # It is OK to cast int to float as later we use inpt.dtype
-            fill = [float(fill)]
+        fill = _F._convert_fill_arg(fill)
 
         output = _F.affine_image_tensor(
             self,
@@ -244,9 +235,11 @@ def perspective(
         self,
         perspective_coeffs: List[float],
         interpolation: InterpolationMode = InterpolationMode.BILINEAR,
-        fill: Optional[List[float]] = None,
+        fill: Optional[Union[int, float, Sequence[int], Sequence[float]]] = None,
     ) -> Image:
-        from torchvision.prototype.transforms import functional as _F
+        from torchvision.prototype.transforms.functional import _geometry as _F
+
+        fill = _F._convert_fill_arg(fill)
 
         output = _F.perspective_image_tensor(self, perspective_coeffs, interpolation=interpolation, fill=fill)
         return Image.new_like(self, output)
diff --git a/torchvision/prototype/features/_segmentation_mask.py b/torchvision/prototype/features/_segmentation_mask.py
@@ -62,7 +62,7 @@ def resized_crop(
     def pad(
         self,
         padding: Union[int, Sequence[int]],
-        fill: Union[int, float, Sequence[int], Sequence[float]] = 0,
+        fill: Optional[Union[int, float, Sequence[int], Sequence[float]]] = None,
         padding_mode: str = "constant",
     ) -> SegmentationMask:
         from torchvision.prototype.transforms import functional as _F
@@ -79,7 +79,7 @@ def rotate(
         angle: float,
         interpolation: InterpolationMode = InterpolationMode.NEAREST,
         expand: bool = False,
-        fill: Union[int, float, Sequence[int], Sequence[float]] = 0,
+        fill: Optional[Union[int, float, Sequence[int], Sequence[float]]] = None,
         center: Optional[List[float]] = None,
     ) -> SegmentationMask:
         from torchvision.prototype.transforms import functional as _F
@@ -94,7 +94,7 @@ def affine(
         scale: float,
         shear: List[float],
         interpolation: InterpolationMode = InterpolationMode.NEAREST,
-        fill: Union[int, float, Sequence[int], Sequence[float]] = 0,
+        fill: Optional[Union[int, float, Sequence[int], Sequence[float]]] = None,
         center: Optional[List[float]] = None,
     ) -> SegmentationMask:
         from torchvision.prototype.transforms import functional as _F
@@ -113,7 +113,7 @@ def perspective(
         self,
         perspective_coeffs: List[float],
         interpolation: InterpolationMode = InterpolationMode.NEAREST,
-        fill: Optional[List[float]] = None,
+        fill: Optional[Union[int, float, Sequence[int], Sequence[float]]] = None,
     ) -> SegmentationMask:
         from torchvision.prototype.transforms import functional as _F
 
diff --git a/torchvision/prototype/transforms/_augment.py b/torchvision/prototype/transforms/_augment.py
@@ -113,13 +113,12 @@ def forward(self, *inpts: Any) -> Any:
             raise TypeError(f"{type(self).__name__}() is only defined for Image's *and* OneHotLabel's.")
         return super().forward(sample)
 
-
-def _mixup_onehotlabel(inpt: features.OneHotLabel, lam: float) -> features.OneHotLabel:
-    if inpt.ndim < 2:
-        raise ValueError("Need a batch of one hot labels")
-    output = inpt.clone()
-    output = output.roll(1, -2).mul_(1 - lam).add_(output.mul_(lam))
-    return features.OneHotLabel.new_like(inpt, output)
+    def _mixup_onehotlabel(self, inpt: features.OneHotLabel, lam: float) -> features.OneHotLabel:
+        if inpt.ndim < 2:
+            raise ValueError("Need a batch of one hot labels")
+        output = inpt.clone()
+        output = output.roll(1, -2).mul_(1 - lam).add_(output.mul_(lam))
+        return features.OneHotLabel.new_like(inpt, output)
 
 
 class RandomMixup(_BaseMixupCutmix):
@@ -135,7 +134,7 @@ def _transform(self, inpt: Any, params: Dict[str, Any]) -> Any:
             output = output.roll(1, -4).mul_(1 - lam).add_(output.mul_(lam))
             return features.Image.new_like(inpt, output)
         if isinstance(inpt, features.OneHotLabel):
-            return _mixup_onehotlabel(inpt, lam)
+            return self._mixup_onehotlabel(inpt, lam)
 
         raise TypeError(
             "RandomMixup transformation does not support bounding boxes, segmentation masks and plain labels"
@@ -178,7 +177,7 @@ def _transform(self, inpt: Any, params: Dict[str, Any]) -> Any:
             return features.Image.new_like(inpt, output)
         if isinstance(inpt, features.OneHotLabel):
             lam_adjusted = params["lam_adjusted"]
-            return _mixup_onehotlabel(inpt, lam_adjusted)
+            return self._mixup_onehotlabel(inpt, lam_adjusted)
 
         raise TypeError(
             "RandomCutmix transformation does not support bounding boxes, segmentation masks and plain labels"
diff --git a/torchvision/prototype/transforms/_color.py b/torchvision/prototype/transforms/_color.py
@@ -1,5 +1,5 @@
 import collections.abc
-from typing import Any, Dict, Union, Tuple, Optional, Sequence, Callable, TypeVar
+from typing import Any, Dict, Union, Tuple, Optional, Sequence, TypeVar
 
 import PIL.Image
 import torch
@@ -52,24 +52,6 @@ def _check_input(
 
         return None if value[0] == value[1] == center else (float(value[0]), float(value[1]))
 
-    def _image_transform(
-        self,
-        inpt: T,
-        *,
-        kernel_tensor: Callable[..., torch.Tensor],
-        kernel_pil: Callable[..., PIL.Image.Image],
-        **kwargs: Any,
-    ) -> T:
-        if isinstance(inpt, features.Image):
-            output = kernel_tensor(inpt, **kwargs)
-            return features.Image.new_like(inpt, output)
-        elif is_simple_tensor(inpt):
-            return kernel_tensor(inpt, **kwargs)
-        elif isinstance(inpt, PIL.Image.Image):
-            return kernel_pil(inpt, **kwargs)  # type: ignore[no-any-return]
-        else:
-            raise RuntimeError
-
     @staticmethod
     def _generate_value(left: float, right: float) -> float:
         return float(torch.distributions.Uniform(left, right).sample())
diff --git a/torchvision/prototype/transforms/_geometry.py b/torchvision/prototype/transforms/_geometry.py
@@ -270,8 +270,6 @@ def __init__(
         if side_range[0] < 1.0 or side_range[0] > side_range[1]:
             raise ValueError(f"Invalid canvas side range provided {side_range}.")
 
-        self._pad_op = Pad(0, padding_mode="constant")
-
     def _get_params(self, sample: Any) -> Dict[str, Any]:
         image = query_image(sample)
         orig_c, orig_h, orig_w = get_image_dimensions(image)
@@ -293,11 +291,8 @@ def _get_params(self, sample: Any) -> Dict[str, Any]:
 
         return dict(padding=padding, fill=fill)
 
-    def forward(self, *inputs: Any) -> Any:
-        params = self._get_params(inputs)
-        self._pad_op.padding = params["padding"]
-        self._pad_op.fill = params["fill"]
-        return self._pad_op(*inputs)
+    def _transform(self, inpt: Any, params: Dict[str, Any]) -> Any:
+        return F.pad(inpt, **params)
 
 
 class RandomRotation(Transform):
diff --git a/torchvision/prototype/transforms/functional/_geometry.py b/torchvision/prototype/transforms/functional/_geometry.py
diff --git a/torchvision/transforms/functional_pil.py b/torchvision/transforms/functional_pil.py

Original file line number	Diff line number	Diff line change
`@@ -72,6 +72,7 @@ class TestSmoke:`
`72`	`72`	`transforms.ConvertImageDtype(),`
`73`	`73`	`transforms.RandomHorizontalFlip(),`
`74`	`74`	`transforms.Pad(5),`
	`75`	`+ transforms.RandomZoomOut(),`
`75`	`76`	`)`
`76`	`77`	`def test_common(self, transform, input):`
`77`	`78`	`transform(input)`