Merge branch 'main' into fix-weights-docs

Author: NicolasHug

test/test_transforms_v2.py

@@ -116,11 +116,9 @@ class TestSmoke:
             (transforms.RandAugment(), auto_augment_adapter),
             (transforms.TrivialAugmentWide(), auto_augment_adapter),
             (transforms.ColorJitter(brightness=0.1, contrast=0.2, saturation=0.3, hue=0.15), None),
-            (transforms.Grayscale(), None),
             (transforms.RandomAdjustSharpness(sharpness_factor=0.5, p=1.0), None),
             (transforms.RandomAutocontrast(p=1.0), None),
             (transforms.RandomEqualize(p=1.0), None),
-            (transforms.RandomGrayscale(p=1.0), None),
             (transforms.RandomInvert(p=1.0), None),
             (transforms.RandomChannelPermutation(), None),
             (transforms.RandomPhotometricDistort(p=1.0), None),
@@ -138,7 +136,6 @@ class TestSmoke:
             (transforms.RandomRotation(degrees=30), None),
             (transforms.RandomShortestSize(min_size=10, antialias=True), None),
             (transforms.RandomVerticalFlip(p=1.0), None),
-            (transforms.RandomZoomOut(p=1.0), None),
             (transforms.Resize([16, 16], antialias=True), None),
             (transforms.ScaleJitter((16, 16), scale_range=(0.8, 1.2), antialias=True), None),
             (transforms.ClampBoundingBoxes(), None),
@@ -390,34 +387,6 @@ def was_applied(output, inpt):
         assert transform.was_applied(output, input)
 
 
-class TestRandomZoomOut:
-    def test_assertions(self):
-        with pytest.raises(TypeError, match="Got inappropriate fill arg"):
-            transforms.RandomZoomOut(fill="abc")
-
-        with pytest.raises(TypeError, match="should be a sequence of length"):
-            transforms.RandomZoomOut(0, side_range=0)
-
-        with pytest.raises(ValueError, match="Invalid canvas side range"):
-            transforms.RandomZoomOut(0, side_range=[4.0, 1.0])
-
-    @pytest.mark.parametrize("fill", [0, [1, 2, 3], (2, 3, 4)])
-    @pytest.mark.parametrize("side_range", [(1.0, 4.0), [2.0, 5.0]])
-    def test__get_params(self, fill, side_range):
-        transform = transforms.RandomZoomOut(fill=fill, side_range=side_range)
-
-        h, w = size = (24, 32)
-        image = make_image(size)
-
-        params = transform._get_params([image])
-
-        assert len(params["padding"]) == 4
-        assert 0 <= params["padding"][0] <= (side_range[1] - 1) * w
-        assert 0 <= params["padding"][1] <= (side_range[1] - 1) * h
-        assert 0 <= params["padding"][2] <= (side_range[1] - 1) * w
-        assert 0 <= params["padding"][3] <= (side_range[1] - 1) * h
-
-
 class TestElasticTransform:
     def test_assertions(self):
 

test/test_transforms_v2_consistency.py

@@ -122,17 +122,6 @@ def __init__(
             (torch.float32, torch.float64),
         ]
     ],
-    ConsistencyConfig(
-        v2_transforms.Grayscale,
-        legacy_transforms.Grayscale,
-        [
-            ArgsKwargs(num_output_channels=1),
-            ArgsKwargs(num_output_channels=3),
-        ],
-        make_images_kwargs=dict(DEFAULT_MAKE_IMAGES_KWARGS, color_spaces=["RGB", "GRAY"]),
-        # Use default tolerances of `torch.testing.assert_close`
-        closeness_kwargs=dict(rtol=None, atol=None),
-    ),
     ConsistencyConfig(
         v2_transforms.ToPILImage,
         legacy_transforms.ToPILImage,
@@ -217,17 +206,6 @@ def __init__(
         ],
         closeness_kwargs={"atol": 1e-6, "rtol": 1e-6},
     ),
-    ConsistencyConfig(
-        v2_transforms.RandomGrayscale,
-        legacy_transforms.RandomGrayscale,
-        [
-            ArgsKwargs(p=0),
-            ArgsKwargs(p=1),
-        ],
-        make_images_kwargs=dict(DEFAULT_MAKE_IMAGES_KWARGS, color_spaces=["RGB", "GRAY"]),
-        # Use default tolerances of `torch.testing.assert_close`
-        closeness_kwargs=dict(rtol=None, atol=None),
-    ),
     ConsistencyConfig(
         v2_transforms.PILToTensor,
         legacy_transforms.PILToTensor,

test/test_transforms_v2_refactored.py

@@ -3945,3 +3945,122 @@ def test_transform_correctness(self, brightness, contrast, saturation, hue):
 
         mae = (actual.float() - expected.float()).abs().mean()
         assert mae < 2
+
+
+class TestRgbToGrayscale:
+    @pytest.mark.parametrize("dtype", [torch.uint8, torch.float32])
+    @pytest.mark.parametrize("device", cpu_and_cuda())
+    def test_kernel_image(self, dtype, device):
+        check_kernel(F.rgb_to_grayscale_image, make_image(dtype=dtype, device=device))
+
+    @pytest.mark.parametrize("make_input", [make_image_tensor, make_image_pil, make_image])
+    def test_functional(self, make_input):
+        check_functional(F.rgb_to_grayscale, make_input())
+
+    @pytest.mark.parametrize(
+        ("kernel", "input_type"),
+        [
+            (F.rgb_to_grayscale_image, torch.Tensor),
+            (F._rgb_to_grayscale_image_pil, PIL.Image.Image),
+            (F.rgb_to_grayscale_image, tv_tensors.Image),
+        ],
+    )
+    def test_functional_signature(self, kernel, input_type):
+        check_functional_kernel_signature_match(F.rgb_to_grayscale, kernel=kernel, input_type=input_type)
+
+    @pytest.mark.parametrize("transform", [transforms.Grayscale(), transforms.RandomGrayscale(p=1)])
+    @pytest.mark.parametrize("make_input", [make_image_tensor, make_image_pil, make_image])
+    def test_transform(self, transform, make_input):
+        check_transform(transform, make_input())
+
+    @pytest.mark.parametrize("num_output_channels", [1, 3])
+    @pytest.mark.parametrize("fn", [F.rgb_to_grayscale, transform_cls_to_functional(transforms.Grayscale)])
+    def test_image_correctness(self, num_output_channels, fn):
+        image = make_image(dtype=torch.uint8, device="cpu")
+
+        actual = fn(image, num_output_channels=num_output_channels)
+        expected = F.to_image(F.rgb_to_grayscale(F.to_pil_image(image), num_output_channels=num_output_channels))
+
+        assert_equal(actual, expected, rtol=0, atol=1)
+
+    @pytest.mark.parametrize("num_input_channels", [1, 3])
+    def test_random_transform_correctness(self, num_input_channels):
+        image = make_image(
+            color_space={
+                1: "GRAY",
+                3: "RGB",
+            }[num_input_channels],
+            dtype=torch.uint8,
+            device="cpu",
+        )
+
+        transform = transforms.RandomGrayscale(p=1)
+
+        actual = transform(image)
+        expected = F.to_image(F.rgb_to_grayscale(F.to_pil_image(image), num_output_channels=num_input_channels))
+
+        assert_equal(actual, expected, rtol=0, atol=1)
+
+
+class TestRandomZoomOut:
+    # Tests are light because this largely relies on the already tested `pad` kernels.
+
+    @pytest.mark.parametrize(
+        "make_input",
+        [
+            make_image_tensor,
+            make_image_pil,
+            make_image,
+            make_bounding_boxes,
+            make_segmentation_mask,
+            make_detection_mask,
+            make_video,
+        ],
+    )
+    def test_transform(self, make_input):
+        check_transform(transforms.RandomZoomOut(p=1), make_input())
+
+    def test_transform_error(self):
+        for side_range in [None, 1, [1, 2, 3]]:
+            with pytest.raises(
+                ValueError if isinstance(side_range, list) else TypeError, match="should be a sequence of length 2"
+            ):
+                transforms.RandomZoomOut(side_range=side_range)
+
+        for side_range in [[0.5, 1.5], [2.0, 1.0]]:
+            with pytest.raises(ValueError, match="Invalid side range"):
+                transforms.RandomZoomOut(side_range=side_range)
+
+    @pytest.mark.parametrize("side_range", [(1.0, 4.0), [2.0, 5.0]])
+    @pytest.mark.parametrize(
+        "make_input",
+        [
+            make_image_tensor,
+            make_image_pil,
+            make_image,
+            make_bounding_boxes,
+            make_segmentation_mask,
+            make_detection_mask,
+            make_video,
+        ],
+    )
+    @pytest.mark.parametrize("device", cpu_and_cuda())
+    def test_transform_params_correctness(self, side_range, make_input, device):
+        if make_input is make_image_pil and device != "cpu":
+            pytest.skip("PIL image tests with parametrization device!='cpu' will degenerate to that anyway.")
+
+        transform = transforms.RandomZoomOut(side_range=side_range)
+
+        input = make_input()
+        height, width = F.get_size(input)
+
+        params = transform._get_params([input])
+        assert "padding" in params
+
+        padding = params["padding"]
+        assert len(padding) == 4
+
+        assert 0 <= padding[0] <= (side_range[1] - 1) * width
+        assert 0 <= padding[1] <= (side_range[1] - 1) * height
+        assert 0 <= padding[2] <= (side_range[1] - 1) * width
+        assert 0 <= padding[3] <= (side_range[1] - 1) * height

torchvision/transforms/v2/_geometry.py

@@ -546,7 +546,7 @@ def __init__(
 
         self.side_range = side_range
         if side_range[0] < 1.0 or side_range[0] > side_range[1]:
-            raise ValueError(f"Invalid canvas side range provided {side_range}.")
+            raise ValueError(f"Invalid side range provided {side_range}.")
 
     def _get_params(self, flat_inputs: List[Any]) -> Dict[str, Any]:
         orig_h, orig_w = query_size(flat_inputs)