Skip to content

Bug fix: max_pool2d default stride value #36

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
TobyRoseman merged 1 commit into from
Jul 13, 2026
+4 −2
Merged

Bug fix: max_pool2d default stride value #36

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
4 changes: 2 additions & 2 deletions coreai_torch/_aten_to_core.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -2227,11 +2227,11 @@ def replace_maxpool2d_with_indices(
x = _get_operand(values_map, node, 0)
args = node.args
kernel_size = args[1]
if isinstance(args[2], fx.Node):
if len(args) > 2 and isinstance(args[2], fx.Node):
raise ValueError(
f"Encountered dynamic stride at maxpool2d: node: {node}, name: {node.name}"
)
stride = args[2]
stride = args[2] if len(args) >= 3 else kernel_size
padding = args[3] if len(args) >= 4 else [0, 0]
dilation = args[4] if len(args) >= 5 else [1, 1]
ceil_mode = args[5] if len(args) >= 6 else False
Expand Down
2 changes: 2 additions & 0 deletions tests/ops/test_ops.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -2686,6 +2686,8 @@ def forward(self, x: Tensor, y: Tensor) -> Tensor:
@pytest.mark.parametrize(
"input_shape, dtype, kernel_size, stride, padding, dilation, ceil_mode, dynamic_dims",
[
# Default parameters
((2, 4, 16, 16), torch.float32, 3, None, 0, 1, False, tuple()),
# Static — all pool configs, multiple shapes and dtypes
((2, 4, 16, 16), torch.float32, 3, 2, 1, 1, False, tuple()),
((2, 4, 16, 16), torch.float32, 3, 2, 0, 1, True, tuple()),
Expand Down