[fbsync] Change torch.arange dtype from torch.float32 to torch.int32 …

…in anchor_utils.py (#4395) (#4409)

Summary:

Reviewed By: datumbox

Differential Revision: D31268024

fbshipit-source-id: 0294ad05fc94bdf5a6d3eba50d85813d568e8fbe

Co-authored-by: Julien RIPOCHE <ripoche@magic-lemp.com>
Co-authored-by: Vasilis Vryniotis <datumbox@users.noreply.github.com>

torchvision/models/detection/anchor_utils.py

@@ -97,10 +97,10 @@ def grid_anchors(self, grid_sizes: List[List[int]], strides: List[List[Tensor]])
 
             # For output anchor, compute [x_center, y_center, x_center, y_center]
             shifts_x = torch.arange(
-                0, grid_width, dtype=torch.float32, device=device
+                0, grid_width, dtype=torch.int32, device=device
             ) * stride_width
             shifts_y = torch.arange(
-                0, grid_height, dtype=torch.float32, device=device
+                0, grid_height, dtype=torch.int32, device=device
             ) * stride_height
             shift_y, shift_x = torch.meshgrid(shifts_y, shifts_x)
             shift_x = shift_x.reshape(-1)