add stanardized setup to main for easier updating of PRs and branches

Author: justincdavis

test/common_utils.py

@@ -20,13 +20,15 @@
 from torch.testing._comparison import BooleanPair, NonePair, not_close_error_metas, NumberPair, TensorLikePair
 from torchvision import io, tv_tensors
 from torchvision.transforms._functional_tensor import _max_value as get_max_value
-from torchvision.transforms.v2.functional import to_cvcuda_tensor, to_image, to_pil_image
+from torchvision.transforms.v2.functional import cvcuda_to_tensor, to_cvcuda_tensor, to_image, to_pil_image
+from torchvision.transforms.v2.functional._utils import _import_cvcuda, _is_cvcuda_available
 from torchvision.utils import _Image_fromarray
 
 
 IN_OSS_CI = any(os.getenv(var) == "true" for var in ["CIRCLECI", "GITHUB_ACTIONS"])
 IN_RE_WORKER = os.environ.get("INSIDE_RE_WORKER") is not None
 IN_FBCODE = os.environ.get("IN_FBCODE_TORCHVISION") == "1"
+CVCUDA_AVAILABLE = _is_cvcuda_available()
 CUDA_NOT_AVAILABLE_MSG = "CUDA device not available"
 MPS_NOT_AVAILABLE_MSG = "MPS device not available"
 OSS_CI_GPU_NO_CUDA_MSG = "We're in an OSS GPU machine, and this test doesn't need cuda."
@@ -275,6 +277,17 @@ def combinations_grid(**kwargs):
     return [dict(zip(kwargs.keys(), values)) for values in itertools.product(*kwargs.values())]
 
 
+def cvcuda_to_pil_compatible_tensor(tensor: "cvcuda.Tensor") -> torch.Tensor:
+    tensor = cvcuda_to_tensor(tensor)
+    if tensor.ndim != 4:
+        raise ValueError(f"CV-CUDA Tensor should be 4 dimensional. Got {tensor.ndim} dimensions.")
+    if tensor.shape[0] != 1:
+        raise ValueError(
+            f"CV-CUDA Tensor should have batch dimension 1 for comparison with PIL.Image.Image. Got {tensor.shape[0]}."
+        )
+    return tensor.squeeze(0).cpu()
+
+
 class ImagePair(TensorLikePair):
     def __init__(
         self,
@@ -287,6 +300,11 @@ def __init__(
         if all(isinstance(input, PIL.Image.Image) for input in [actual, expected]):
             actual, expected = (to_image(input) for input in [actual, expected])
 
+        # handle check for CV-CUDA Tensors
+        if CVCUDA_AVAILABLE and isinstance(actual, _import_cvcuda().Tensor):
+            # Use the PIL compatible tensor, so we can always compare with PIL.Image.Image
+            actual = cvcuda_to_pil_compatible_tensor(actual)
+
         super().__init__(actual, expected, **other_parameters)
         self.mae = mae
 
@@ -401,7 +419,6 @@ def make_image_pil(*args, **kwargs):
 
 
 def make_image_cvcuda(*args, batch_dims=(1,), **kwargs):
-    # explicitly default batch_dims to (1,) since to_cvcuda_tensor requires a batch dimension (ndims == 4)
     return to_cvcuda_tensor(make_image(*args, batch_dims=batch_dims, **kwargs))
 
 

test/test_transforms_v2.py

@@ -21,6 +21,7 @@
 import torchvision.transforms.v2 as transforms
 
 from common_utils import (
+    assert_close,
     assert_equal,
     cache,
     cpu_and_cuda,
@@ -41,7 +42,6 @@
 )
 
 from torch import nn
-from torch.testing import assert_close
 from torch.utils._pytree import tree_flatten, tree_map
 from torch.utils.data import DataLoader, default_collate
 from torchvision import tv_tensors

torchvision/transforms/v2/_utils.py

@@ -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")

torchvision/transforms/v2/functional/_meta.py

@@ -51,6 +51,16 @@ def get_dimensions_video(video: torch.Tensor) -> list[int]:
     return get_dimensions_image(video)
 
 
+def _get_dimensions_cvcuda(image: "cvcuda.Tensor") -> list[int]:
+    # CV-CUDA tensor is always in NHWC layout
+    # get_dimensions is CHW
+    return [image.shape[3], image.shape[1], image.shape[2]]
+
+
+if CVCUDA_AVAILABLE:
+    _register_kernel_internal(get_dimensions, cvcuda.Tensor)(_get_dimensions_cvcuda)
+
+
 def get_num_channels(inpt: torch.Tensor) -> int:
     if torch.jit.is_scripting():
         return get_num_channels_image(inpt)
@@ -87,6 +97,16 @@ def get_num_channels_video(video: torch.Tensor) -> int:
 get_image_num_channels = get_num_channels
 
 
+def _get_num_channels_cvcuda(image: "cvcuda.Tensor") -> int:
+    # CV-CUDA tensor is always in NHWC layout
+    # get_num_channels is C
+    return image.shape[3]
+
+
+if CVCUDA_AVAILABLE:
+    _register_kernel_internal(get_num_channels, cvcuda.Tensor)(_get_num_channels_cvcuda)
+
+
 def get_size(inpt: torch.Tensor) -> list[int]:
     if torch.jit.is_scripting():
         return get_size_image(inpt)
@@ -114,7 +134,7 @@ def _get_size_image_pil(image: PIL.Image.Image) -> list[int]:
     return [height, width]
 
 
-def get_size_image_cvcuda(image: "cvcuda.Tensor") -> list[int]:
+def _get_size_cvcuda(image: "cvcuda.Tensor") -> list[int]:
     """Get size of `cvcuda.Tensor` with NHWC layout."""
     hw = list(image.shape[-3:-1])
     ndims = len(hw)
@@ -125,7 +145,7 @@ def get_size_image_cvcuda(image: "cvcuda.Tensor") -> list[int]:
 
 
 if CVCUDA_AVAILABLE:
-    _get_size_image_cvcuda = _register_kernel_internal(get_size, cvcuda.Tensor)(get_size_image_cvcuda)
+    _register_kernel_internal(get_size, cvcuda.Tensor)(_get_size_cvcuda)
 
 
 @_register_kernel_internal(get_size, tv_tensors.Video, tv_tensor_wrapper=False)