diff --git a/torchvision/transforms/functional.py b/torchvision/transforms/functional.py
index 7bd15dde4c2..d36e68c2b6f 100644
--- a/torchvision/transforms/functional.py
+++ b/torchvision/transforms/functional.py
@@ -346,6 +346,12 @@ def resize(img: Tensor, size: List[int], interpolation: InterpolationMode = Inte
     If the image is torch Tensor, it is expected
     to have [..., H, W] shape, where ... means an arbitrary number of leading dimensions
 
+    .. warning::
+        The output image might be different depending on its type: when downsampling, the interpolation of PIL images
+        and tensors is slightly different, because PIL applies antialiasing. This may lead to significant differences
+        in the performance of a network. Therefore, it is preferable to train and serve a model with the same input
+        types.
+
     Args:
         img (PIL Image or Tensor): Image to be resized.
         size (sequence or int): Desired output size. If size is a sequence like
diff --git a/torchvision/transforms/transforms.py b/torchvision/transforms/transforms.py
index 2c4a10598b4..7c25b000ce8 100644
--- a/torchvision/transforms/transforms.py
+++ b/torchvision/transforms/transforms.py
@@ -229,6 +229,12 @@ class Resize(torch.nn.Module):
     If the image is torch Tensor, it is expected
     to have [..., H, W] shape, where ... means an arbitrary number of leading dimensions
 
+    .. warning::
+        The output image might be different depending on its type: when downsampling, the interpolation of PIL images
+        and tensors is slightly different, because PIL applies antialiasing. This may lead to significant differences
+        in the performance of a network. Therefore, it is preferable to train and serve a model with the same input
+        types.
+
     Args:
         size (sequence or int): Desired output size. If size is a sequence like
             (h, w), output size will be matched to this. If size is an int,