Merge branch 'main' into patch-1

Author: NicolasHug

test/test_datasets_download.py

@@ -368,6 +368,7 @@ def url_parametrization(*dataset_urls_and_ids_fns):
     kinetics,
     kitti,
     places365,
+    sbu,
 )
 def test_url_is_accessible(url):
     """
@@ -379,7 +380,6 @@ def test_url_is_accessible(url):
 
 @url_parametrization(
     stanford_cars,  # https://github.com/pytorch/vision/issues/7545
-    sbu,  # https://github.com/pytorch/vision/issues/7964
 )
 @pytest.mark.xfail
 def test_url_is_not_accessible(url):

test/test_onnx.py

@@ -79,7 +79,7 @@ def to_numpy(tensor):
         inputs = list(map(to_numpy, inputs))
         outputs = list(map(to_numpy, outputs))
 
-        ort_session = onnxruntime.InferenceSession(onnx_io.getvalue())
+        ort_session = onnxruntime.InferenceSession(onnx_io.getvalue(), providers=onnxruntime.get_available_providers())
         # compute onnxruntime output prediction
         ort_inputs = {ort_session.get_inputs()[i].name: inpt for i, inpt in enumerate(inputs)}
         ort_outs = ort_session.run(None, ort_inputs)

torchvision/transforms/functional.py

@@ -1326,7 +1326,7 @@ def erase(img: Tensor, i: int, j: int, h: int, w: int, v: Tensor, inplace: bool
 def gaussian_blur(img: Tensor, kernel_size: List[int], sigma: Optional[List[float]] = None) -> Tensor:
     """Performs Gaussian blurring on the image by given kernel.
     If the image is torch Tensor, it is expected
-    to have [..., H, W] shape, where ... means an arbitrary number of leading dimensions.
+    to have [..., H, W] shape, where ... means at most one leading dimension.
 
     Args:
         img (PIL Image or Tensor): Image to be blurred

torchvision/transforms/transforms.py

@@ -1760,7 +1760,7 @@ def __repr__(self) -> str:
 class GaussianBlur(torch.nn.Module):
     """Blurs image with randomly chosen Gaussian blur.
     If the image is torch Tensor, it is expected
-    to have [..., C, H, W] shape, where ... means an arbitrary number of leading dimensions.
+    to have [..., C, H, W] shape, where ... means at most one leading dimension.
 
     Args:
         kernel_size (int or sequence): Size of the Gaussian kernel.