Fix #8775: handle torch.Tensor input in compute_shape_offset (#8812)

## Description

`compute_shape_offset` in `monai/data/utils.py` passes `spatial_shape`
directly to `np.array()`. When `spatial_shape` is a `torch.Tensor`, this
relies on the non-tuple sequence indexing protocol, which PyTorch
removed in version 2.9. The call raises a hard error on PyTorch ≥ 2.9.

The fix is to wrap `spatial_shape` in `tuple()` before passing it to
`np.array()`. This routes through `__iter__`, which is stable across all
PyTorch versions, and produces 0-d scalar tensors that NumPy consumes
correctly.

## Root cause

The direct caller in `monai/transforms/spatial/functional.py` (line 115)
constructs an `in_spatial_size` as a `torch.Tensor` and passes it
straight to `compute_shape_offset`. This path has been broken since
PyTorch 2.9.

## Changes

- `monai/data/utils.py` — one-character change: `np.array(spatial_shape,
...)` → `np.array(tuple(spatial_shape), ...)`
- `tests/data/utils/test_compute_shape_offset.py`: new unit tests
covering `torch.Tensor`, `np.ndarray`, and plain list inputs

Fixes #8775

---------

Signed-off-by: UGBOMEH OGOCHUKWU WILLIAMS <williamsugbomeh@gmail.com>
Signed-off-by: Eric Kerfoot <17726042+ericspod@users.noreply.github.com>
Co-authored-by: Eric Kerfoot <17726042+ericspod@users.noreply.github.com>
Co-authored-by: pre-commit-ci[bot] <66853113+pre-commit-ci[bot]@users.noreply.github.com>

Author: 3 people

tests/data/utils/test_compute_shape_offset.py

@@ -19,8 +19,8 @@
 from monai.data.utils import compute_shape_offset
 
 
-class TestComputeShapeOffsetRegression(unittest.TestCase):
-    """Regression tests for `compute_shape_offset` input-shape handling."""
+class TestComputeShapeOffset(unittest.TestCase):
+    """Unit tests for :func:`monai.data.utils.compute_shape_offset`."""
 
     def test_pytorch_size_input(self):
         """Validate `torch.Size` input produces expected shape and offset.
@@ -42,6 +42,39 @@ def test_pytorch_size_input(self):
         # 3. Prove it successfully processed the shape by checking its length
         self.assertEqual(len(shape), 3)
 
+    def setUp(self):
+        """Set up a 4x4 identity affine used across all test cases."""
+        self.affine = np.eye(4)
+
+    def test_numpy_array_input(self):
+        """Verify compute_shape_offset accepts a numpy array as spatial_shape."""
+        shape = np.array([64, 64, 64])
+        out_shape, _ = compute_shape_offset(shape, self.affine, self.affine)
+        self.assertEqual(len(out_shape), 3)
+
+    def test_list_input(self):
+        """Verify compute_shape_offset accepts a plain list as spatial_shape."""
+        shape = [64, 64, 64]
+        out_shape, _ = compute_shape_offset(shape, self.affine, self.affine)
+        self.assertEqual(len(out_shape), 3)
+
+    def test_torch_tensor_input(self):
+        """Verify compute_shape_offset accepts a torch.Tensor as spatial_shape.
+
+        This path broke in PyTorch >= 2.9 because np.array() relied on the
+        non-tuple sequence indexing protocol that PyTorch removed. Wrapping with
+        tuple() fixes it.
+        """
+        shape = torch.tensor([64, 64, 64])
+        out_shape, _ = compute_shape_offset(shape, self.affine, self.affine)
+        self.assertEqual(len(out_shape), 3)
+
+    def test_identity_affines_preserve_shape(self):
+        """Verify that identity in/out affines produce an output shape matching the input."""
+        shape = torch.tensor([32, 48, 16])
+        out_shape, _ = compute_shape_offset(shape, self.affine, self.affine)
+        np.testing.assert_allclose(np.array(out_shape, dtype=float), shape.numpy().astype(float), atol=1e-5)
+
 
 if __name__ == "__main__":
     unittest.main()