Fix top-down pose postprocessing device

Update PyTorch top-down pose postprocessing to keep tensors on the same device/dtype by using `new_zeros` and `new_tensor` instead of creating CPU tensors. Also replace `torch.cat(poses)` with `torch.stack(..., dim=0)` so batched pose outputs preserve the expected batch dimension.

Author: C-Achard

dlclive/pose_estimation_pytorch/runner.py

@@ -357,21 +357,24 @@ def _postprocess_top_down(
         """Post-processes pose for top-down models."""
         if len(batch_pose) == 0:
             bodyparts, coords = batch_pose.shape[-2:]
-            return torch.zeros((0, bodyparts, coords))
+            return batch_pose.new_zeros((0, bodyparts, coords))
 
         poses = []
+
         for pose, (offset, scale) in zip(batch_pose, offsets_and_scales, strict=False):
-            poses.append(
-                torch.cat(
-                    [
-                        pose[..., :2] * torch.tensor(scale) + torch.tensor(offset),
-                        pose[..., 2:3],
-                    ],
-                    dim=-1,
-                )
+            scale_tensor = pose.new_tensor(scale)
+            offset_tensor = pose.new_tensor(offset)
+
+            transformed_pose = torch.cat(
+                [
+                    pose[..., :2] * scale_tensor + offset_tensor,
+                    pose[..., 2:3],
+                ],
+                dim=-1,
             )
+            poses.append(transformed_pose)
 
-        return torch.cat(poses)
+        return torch.stack(poses, dim=0)
 
 
 def _parse_device(device: str | None) -> str: