diff --git a/test/test_transforms.py b/test/test_transforms.py
index 214f2963bfe..cef8d183938 100644
--- a/test/test_transforms.py
+++ b/test/test_transforms.py
@@ -2217,10 +2217,6 @@ def test_elastic_transformation():
     with pytest.raises(ValueError, match=r"sigma is a sequence its length should be 2"):
         transforms.ElasticTransform(alpha=2.0, sigma=[1.0, 0.0, 1.0])
 
-    with pytest.warns(UserWarning, match=r"Argument interpolation should be of type InterpolationMode"):
-        t = transforms.transforms.ElasticTransform(alpha=2.0, sigma=2.0, interpolation=2)
-        assert t.interpolation == transforms.InterpolationMode.BILINEAR
-
     with pytest.raises(TypeError, match=r"fill should be int or float"):
         transforms.ElasticTransform(alpha=1.0, sigma=1.0, fill={})
 
diff --git a/torchvision/transforms/functional.py b/torchvision/transforms/functional.py
index abf827a08c7..ae76d4fa47f 100644
--- a/torchvision/transforms/functional.py
+++ b/torchvision/transforms/functional.py
@@ -34,20 +34,6 @@ class InterpolationMode(Enum):
     LANCZOS = "lanczos"
 
 
-# TODO: Once torchscript supports Enums with staticmethod
-# this can be put into InterpolationMode as staticmethod
-def _interpolation_modes_from_int(i: int) -> InterpolationMode:
-    inverse_modes_mapping = {
-        0: InterpolationMode.NEAREST,
-        2: InterpolationMode.BILINEAR,
-        3: InterpolationMode.BICUBIC,
-        4: InterpolationMode.BOX,
-        5: InterpolationMode.HAMMING,
-        1: InterpolationMode.LANCZOS,
-    }
-    return inverse_modes_mapping[i]
-
-
 pil_modes_mapping = {
     InterpolationMode.NEAREST: 0,
     InterpolationMode.BILINEAR: 2,
@@ -1501,13 +1487,6 @@ def elastic_transform(
     """
     if not torch.jit.is_scripting() and not torch.jit.is_tracing():
         _log_api_usage_once(elastic_transform)
-    # Backward compatibility with integer value
-    if isinstance(interpolation, int):
-        warnings.warn(
-            "Argument interpolation should be of type InterpolationMode instead of int. "
-            "Please, use InterpolationMode enum."
-        )
-        interpolation = _interpolation_modes_from_int(interpolation)
 
     if not isinstance(displacement, torch.Tensor):
         raise TypeError("Argument displacement should be a Tensor")
diff --git a/torchvision/transforms/transforms.py b/torchvision/transforms/transforms.py
index 9395ca674f4..bf9f52cf536 100644
--- a/torchvision/transforms/transforms.py
+++ b/torchvision/transforms/transforms.py
@@ -15,7 +15,7 @@
 
 from ..utils import _log_api_usage_once
 from . import functional as F
-from .functional import _interpolation_modes_from_int, InterpolationMode
+from .functional import InterpolationMode
 
 __all__ = [
     "Compose",
@@ -2044,14 +2044,6 @@ def __init__(self, alpha=50.0, sigma=5.0, interpolation=InterpolationMode.BILINE
             sigma = [sigma[0], sigma[0]]
 
         self.sigma = sigma
-
-        # Backward compatibility with integer value
-        if isinstance(interpolation, int):
-            warnings.warn(
-                "Argument interpolation should be of type InterpolationMode instead of int. "
-                "Please, use InterpolationMode enum."
-            )
-            interpolation = _interpolation_modes_from_int(interpolation)
         self.interpolation = interpolation
 
         if isinstance(fill, (int, float)):