diff --git a/pytorch3d/renderer/cameras.py b/pytorch3d/renderer/cameras.py
index 4f5f1615..ed1d4371 100644
--- a/pytorch3d/renderer/cameras.py
+++ b/pytorch3d/renderer/cameras.py
@@ -905,7 +905,7 @@ def get_world_to_view_transform(R=r, T=t) -> Transform3d:
         raise ValueError(msg % repr(T.shape))
     if R.dim() != 3 or R.shape[1:] != (3, 3):
         msg = "Expected R to have shape (N, 3, 3); got %r"
-        raise ValueError(msg % R.shape)
+        raise ValueError(msg % repr(R.shape))
 
     # Create a Transform3d object
     T = Translate(T, device=T.device)
diff --git a/pytorch3d/renderer/mesh/utils.py b/pytorch3d/renderer/mesh/utils.py
index a82f10ca..2179b2ec 100644
--- a/pytorch3d/renderer/mesh/utils.py
+++ b/pytorch3d/renderer/mesh/utils.py
@@ -19,7 +19,7 @@ def _clip_barycentric_coordinates(bary) -> torch.Tensor:
     """
     if bary.shape[-1] != 3:
         msg = "Expected barycentric coords to have last dim = 3; got %r"
-        raise ValueError(msg % bary.shape)
+        raise ValueError(msg % (bary.shape,))
     clipped = bary.clamp(min=0.0)
     clipped_sum = torch.clamp(clipped.sum(dim=-1, keepdim=True), min=1e-5)
     clipped = clipped / clipped_sum
@@ -57,7 +57,7 @@ def interpolate_face_attributes(
     N, H, W, K, _ = barycentric_coords.shape
     if pix_to_face.shape != (N, H, W, K):
         msg = "pix_to_face must have shape (batch_size, H, W, K); got %r"
-        raise ValueError(msg % pix_to_face.shape)
+        raise ValueError(msg % (pix_to_face.shape,))
 
     # Replace empty pixels in pix_to_face with 0 in order to interpolate.
     mask = pix_to_face == -1
diff --git a/pytorch3d/structures/textures.py b/pytorch3d/structures/textures.py
index 0f30f0aa..eb057ba2 100644
--- a/pytorch3d/structures/textures.py
+++ b/pytorch3d/structures/textures.py
@@ -103,7 +103,7 @@ class Textures(object):
             raise ValueError(msg % repr(faces_uvs.shape))
         if verts_rgb is not None and verts_rgb.ndim != 3:
             msg = "Expected verts_rgb to be of shape (N, V, 3); got %r"
-            raise ValueError(msg % verts_rgb.shape)
+            raise ValueError(msg % repr(verts_rgb.shape))
         if maps is not None:
             if torch.is_tensor(maps) and maps.ndim != 4:
                 msg = "Expected maps to be of shape (N, H, W, 3); got %r"
diff --git a/pytorch3d/transforms/transform3d.py b/pytorch3d/transforms/transform3d.py
index cd901f98..34cfd395 100644
--- a/pytorch3d/transforms/transform3d.py
+++ b/pytorch3d/transforms/transform3d.py
@@ -275,7 +275,7 @@ class Transform3d:
             points_batch = points_batch[None]  # (P, 3) -> (1, P, 3)
         if points_batch.dim() != 3:
             msg = "Expected points to have dim = 2 or dim = 3: got shape %r"
-            raise ValueError(msg % points.shape)
+            raise ValueError(msg % repr(points.shape))
 
         N, P, _3 = points_batch.shape
         ones = torch.ones(N, P, 1, dtype=points.dtype, device=points.device)
@@ -309,7 +309,7 @@ class Transform3d:
         """
         if normals.dim() not in [2, 3]:
             msg = "Expected normals to have dim = 2 or dim = 3: got shape %r"
-            raise ValueError(msg % normals.shape)
+            raise ValueError(msg % (normals.shape,))
         composed_matrix = self.get_matrix()
 
         # TODO: inverse is bad! Solve a linear system instead