diff --git a/test/test_transforms_v2.py b/test/test_transforms_v2.py index b9f440bd545..be82dd4b32f 100644 --- a/test/test_transforms_v2.py +++ b/test/test_transforms_v2.py @@ -5996,7 +5996,19 @@ def test_kernel_image(self, dtype, device): def test_kernel_video(self): check_kernel(F.adjust_sharpness_video, make_video(), sharpness_factor=0.5) - @pytest.mark.parametrize("make_input", [make_image_tensor, make_image, make_image_pil, make_video]) + @pytest.mark.parametrize( + "make_input", + [ + make_image_tensor, + make_image, + make_image_pil, + make_video, + pytest.param( + make_image_cvcuda, + marks=pytest.mark.needs_cvcuda, + ), + ], + ) def test_functional(self, make_input): check_functional(F.adjust_sharpness, make_input(), sharpness_factor=0.5) @@ -6007,12 +6019,31 @@ def test_functional(self, make_input): (F._color._adjust_sharpness_image_pil, PIL.Image.Image), (F.adjust_sharpness_image, tv_tensors.Image), (F.adjust_sharpness_video, tv_tensors.Video), + pytest.param( + F._color._adjust_sharpness_image_cvcuda, + None, + marks=pytest.mark.needs_cvcuda, + ), ], ) def test_functional_signature(self, kernel, input_type): + if kernel is F._color._adjust_sharpness_image_cvcuda: + input_type = _import_cvcuda().Tensor check_functional_kernel_signature_match(F.adjust_sharpness, kernel=kernel, input_type=input_type) - @pytest.mark.parametrize("make_input", [make_image_tensor, make_image_pil, make_image, make_video]) + @pytest.mark.parametrize( + "make_input", + [ + make_image_tensor, + make_image_pil, + make_image, + make_video, + pytest.param( + make_image_cvcuda, + marks=pytest.mark.needs_cvcuda, + ), + ], + ) def test_transform(self, make_input): check_transform(transforms.RandomAdjustSharpness(sharpness_factor=0.5, p=1), make_input()) @@ -6024,13 +6055,28 @@ def test_functional_error(self): F.adjust_sharpness(make_image(), sharpness_factor=-1) @pytest.mark.parametrize("sharpness_factor", [0.1, 0.5, 1.0]) + @pytest.mark.parametrize( + "make_input", + [ + make_image, + pytest.param( + make_image_cvcuda, + marks=pytest.mark.needs_cvcuda, + ), + ], + ) @pytest.mark.parametrize( "fn", [F.adjust_sharpness, transform_cls_to_functional(transforms.RandomAdjustSharpness, p=1)] ) - def test_correctness_image(self, sharpness_factor, fn): - image = make_image(dtype=torch.uint8, device="cpu") + def test_correctness_image(self, sharpness_factor, make_input, fn): + image = make_input(dtype=torch.uint8, device="cpu") actual = fn(image, sharpness_factor=sharpness_factor) + + if make_input == make_image_cvcuda: + actual = F.cvcuda_to_tensor(actual)[0].cpu() + image = F.cvcuda_to_tensor(image)[0].cpu() + expected = F.to_image(F.adjust_sharpness(F.to_pil_image(image), sharpness_factor=sharpness_factor)) assert_equal(actual, expected) diff --git a/torchvision/transforms/v2/_color.py b/torchvision/transforms/v2/_color.py index bf4ae55d232..0c95294c078 100644 --- a/torchvision/transforms/v2/_color.py +++ b/torchvision/transforms/v2/_color.py @@ -5,6 +5,7 @@ import torch from torchvision import transforms as _transforms from torchvision.transforms.v2 import functional as F, Transform +from torchvision.transforms.v2.functional._utils import _is_cvcuda_tensor from ._transform import _RandomApplyTransform from ._utils import query_chw @@ -369,6 +370,8 @@ class RandomAdjustSharpness(_RandomApplyTransform): _v1_transform_cls = _transforms.RandomAdjustSharpness + _transformed_types = _RandomApplyTransform._transformed_types + (_is_cvcuda_tensor,) + def __init__(self, sharpness_factor: float, p: float = 0.5) -> None: super().__init__(p=p) self.sharpness_factor = sharpness_factor diff --git a/torchvision/transforms/v2/_utils.py b/torchvision/transforms/v2/_utils.py index bb6051b4e61..e803aa49c60 100644 --- a/torchvision/transforms/v2/_utils.py +++ b/torchvision/transforms/v2/_utils.py @@ -16,7 +16,7 @@ from torchvision.transforms.transforms import _check_sequence_input, _setup_angle, _setup_size # noqa: F401 from torchvision.transforms.v2.functional import get_dimensions, get_size, is_pure_tensor -from torchvision.transforms.v2.functional._utils import _FillType, _FillTypeJIT +from torchvision.transforms.v2.functional._utils import _FillType, _FillTypeJIT, _is_cvcuda_tensor def _setup_number_or_seq(arg: int | float | Sequence[int | float], name: str) -> Sequence[float]: @@ -182,7 +182,7 @@ def query_chw(flat_inputs: list[Any]) -> tuple[int, int, int]: chws = { tuple(get_dimensions(inpt)) for inpt in flat_inputs - if check_type(inpt, (is_pure_tensor, tv_tensors.Image, PIL.Image.Image, tv_tensors.Video)) + if check_type(inpt, (is_pure_tensor, tv_tensors.Image, PIL.Image.Image, tv_tensors.Video, _is_cvcuda_tensor)) } if not chws: raise TypeError("No image or video was found in the sample") @@ -207,6 +207,7 @@ def query_size(flat_inputs: list[Any]) -> tuple[int, int]: tv_tensors.Mask, tv_tensors.BoundingBoxes, tv_tensors.KeyPoints, + _is_cvcuda_tensor, ), ) } diff --git a/torchvision/transforms/v2/functional/_color.py b/torchvision/transforms/v2/functional/_color.py index be254c0d63a..495a963553c 100644 --- a/torchvision/transforms/v2/functional/_color.py +++ b/torchvision/transforms/v2/functional/_color.py @@ -1,3 +1,5 @@ +from typing import TYPE_CHECKING + import PIL.Image import torch from torch.nn.functional import conv2d @@ -9,7 +11,13 @@ from ._misc import _num_value_bits, to_dtype_image from ._type_conversion import pil_to_tensor, to_pil_image -from ._utils import _get_kernel, _register_kernel_internal +from ._utils import _get_kernel, _import_cvcuda, _is_cvcuda_available, _register_kernel_internal + + +CVCUDA_AVAILABLE = _is_cvcuda_available() + +if TYPE_CHECKING: + import cvcuda # type: ignore[import-not-found] def rgb_to_grayscale(inpt: torch.Tensor, num_output_channels: int = 1) -> torch.Tensor: @@ -286,6 +294,88 @@ def adjust_sharpness_video(video: torch.Tensor, sharpness_factor: float) -> torc return adjust_sharpness_image(video, sharpness_factor=sharpness_factor) +_max_value_map: dict["cvcuda.Type", float | int] = {} +_dtype_to_format: dict[tuple["cvcuda.Type", int], "cvcuda.Format"] = {} + + +def _adjust_sharpness_image_cvcuda( + image: "cvcuda.Tensor", + sharpness_factor: float, +) -> "cvcuda.Tensor": + cvcuda = _import_cvcuda() + + if len(_max_value_map) == 0: + _max_value_map[cvcuda.Type.U8] = 255 + _max_value_map[cvcuda.Type.F32] = 1.0 + if len(_dtype_to_format) == 0: + _dtype_to_format[(cvcuda.Type.U8, 1)] = cvcuda.Format.U8 + _dtype_to_format[(cvcuda.Type.U8, 3)] = cvcuda.Format.RGB8 + _dtype_to_format[(cvcuda.Type.F32, 1)] = cvcuda.Format.F32 + _dtype_to_format[(cvcuda.Type.F32, 3)] = cvcuda.Format.RGBf32 + + if sharpness_factor < 0: + raise ValueError(f"sharpness_factor ({sharpness_factor}) is not non-negative.") + + n, h, w, c = image.shape + if c not in (1, 3): + raise TypeError(f"Input image tensor can have 1 or 3 channels, but found {c}") + + if h <= 2 or w <= 2: + return image + + # grab the constants like in the torchvision + bound = _max_value_map[image.dtype] + fp = image.dtype == cvcuda.Type.F32 + img_format = _dtype_to_format.get((image.dtype, c)) + if img_format is None: + raise TypeError(f"Unsupported dtype/channel combination: {image.dtype}, {c} channels") + + # conv2d requires ImageBatchVarShape, so we split the batch into individual images + # CV-CUDA has no split, so use zero-copy and torch + batch = cvcuda.ImageBatchVarShape(capacity=n) + for tensor in torch.as_tensor(image.cuda()).split(1, dim=0): + cv_image = cvcuda.as_image(tensor, format=img_format) + batch.pushback(cv_image) + + # create kernel same as adjust_sharpness_image + a, b = 1.0 / 13.0, 5.0 / 13.0 + torch_kernel = torch.tensor([[a, a, a], [a, b, a], [a, a, a]], dtype=torch.float32, device="cuda") + kernel_batch = cvcuda.ImageBatchVarShape(capacity=n) + for _ in range(n): + kernel_batch.pushback(cvcuda.as_image(torch_kernel, format=cvcuda.Format.F32)) + + # anchors of kernel for cvcuda, [-1, -1] means center of kernel + anchor_data = torch.tensor([[-1, -1]] * n, dtype=torch.int32, device="cuda") + anchor = cvcuda.as_tensor(anchor_data, "NC") + + # run the sharpen operator using cvcuda.conv2d + sharpened_batch = cvcuda.conv2d(batch, kernel=kernel_batch, kernel_anchor=anchor, border=cvcuda.Border.REPLICATE) + sharpened_list = [] + for sharpened_img in sharpened_batch: + tensor = cvcuda.as_tensor(sharpened_img.cuda(), cvcuda.TensorLayout.HWC) + sharpened_list.append(tensor) + sharpened = cvcuda.stack(sharpened_list) + + # handle the final blend operations using zero-copy from the adjust_sharpness_image + blurred_degenerate = torch.as_tensor(sharpened.cuda()) + output = torch.as_tensor(image.cuda()).to(dtype=torch.float32, copy=True) + if not fp: + blurred_degenerate = blurred_degenerate.round() + view = output[:, 1:-1, 1:-1, :] + blurred_inner = blurred_degenerate[:, 1:-1, 1:-1, :] + view.add_(blurred_inner.sub(view), alpha=(1.0 - sharpness_factor)) + output = output.clamp_(0, bound) + if not fp: + output = output.to(torch.uint8) + + # convert back to cvcuda.Tensor + return cvcuda.as_tensor(output.contiguous(), cvcuda.TensorLayout.NHWC) + + +if CVCUDA_AVAILABLE: + _register_kernel_internal(adjust_sharpness, _import_cvcuda().Tensor)(_adjust_sharpness_image_cvcuda) + + def adjust_hue(inpt: torch.Tensor, hue_factor: float) -> torch.Tensor: """Adjust hue""" if torch.jit.is_scripting():