Fix RoIAlign/RoIPool output_size to always be a tuple

The downstream code accesses output_size[0] and output_size[1],
so normalize int inputs to (int, int) tuples.

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>

setup_mmcv_shim.py

@@ -61,6 +61,8 @@ def roi_align(input, rois, output_size, spatial_scale=1.0, sampling_ratio=-1, po
 class RoIAlign(torch.nn.Module):
     def __init__(self, output_size, spatial_scale=1.0, sampling_ratio=-1, pool_mode="avg", aligned=True, use_torchvision=False):
         super().__init__()
+        if isinstance(output_size, int):
+            output_size = (output_size, output_size)
         self.output_size = output_size
         self.spatial_scale = spatial_scale
         self.sampling_ratio = sampling_ratio
@@ -71,6 +73,8 @@ class RoIAlign(torch.nn.Module):
 class RoIPool(torch.nn.Module):
     def __init__(self, output_size, spatial_scale=1.0):
         super().__init__()
+        if isinstance(output_size, int):
+            output_size = (output_size, output_size)
         self.output_size = output_size
         self.spatial_scale = spatial_scale
     def forward(self, input, rois):