Switch pose aggregation from stack to cat

In `PyTorchRunner`, transformed pose tensors are now merged with `torch.cat(..., dim=0)` instead of `torch.stack`. This aligns aggregation with tensors that already carry a leading batch dimension and avoids introducing an extra axis.

Author: C-Achard

dlclive/pose_estimation_pytorch/runner.py

@@ -409,7 +409,10 @@ def _postprocess_top_down(
             )
             poses.append(transformed_pose)
 
-        return torch.stack(poses, dim=0)
+        result = torch.cat(poses, dim=0)
+
+        if result.ndim != 3:
+            raise ValueError(f"Expected result of shape (detections, bodyparts, coords), got {tuple(result.shape)}")
 
 
 def _parse_device(device: str | None) -> str: