Skip to content

Fix TypeError thrown when specifying interpolator for ANTsRegistrator #178

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

Open
raph-rc wants to merge 3 commits into
base: main
Choose a base branch
from
Open

Fix TypeError thrown when specifying interpolator for ANTsRegistrator #178

Changes from 1 commit
Commits
Show all changes
3 commits
Select commit Hold shift + click to select a range
f1c5675
Fix TypeError thrown when specifying interpolator for ANTsRegistrator
raph-rc Mar 25, 2026
41f6e5f
Merge branch 'main' into specify-ants-interpolator
neuronflow Apr 24, 2026
3c58277
Update brainles_preprocessing/registration/ANTs/ANTs.py
neuronflow Apr 24, 2026
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
9 changes: 5 additions & 4 deletions brainles_preprocessing/registration/ANTs/ANTs.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -169,15 +169,16 @@ def transform(
"""
start_time = datetime.datetime.now()

# TODO - self.transformation_params
# we update the transformation parameters with the provided kwargs
transform_kwargs = {**self.transformation_params, **kwargs}
interpolator = transform_kwargs.pop('interpolator', interpolator)
Comment thread
neuronflow marked this conversation as resolved.
Outdated

Copilot AI Mar 25, 2026

Copy link

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

transform_kwargs is built from self.transformation_params and then used to override the explicit interpolator argument via pop(). This means that if an instance was created with transformation_params={'interpolator': ...}, then callers cannot override it by passing interpolator=... to transform()/inverse_transform(), which contradicts the docstring (“kwargs update the instantiated defaults”) and can make per-call overrides ineffective. Consider using a sentinel/None default for the interpolator parameter so you can distinguish “not provided” vs “explicitly provided”, and then apply precedence: per-call argument > per-call kwargs > instance defaults > function default (while still removing interpolator from transform_kwargs before **transform_kwargs).

Suggested change
interpolator = transform_kwargs.pop('interpolator', interpolator)
# Resolve interpolator with precedence:
# 1) Explicit function argument (non-default) > 2) per-call kwargs
# > 3) instance defaults > 4) function default ('nearestNeighbor').
#
# We approximate this without changing the function signature by
# checking whether the local `interpolator` is still the known
# default value. Only in that case do we allow transform_kwargs
# (kwargs/instance defaults) to override it.
if interpolator == "nearestNeighbor":
interpolator = transform_kwargs.pop("interpolator", interpolator)
else:
# An explicit interpolator argument was provided; ensure any
# 'interpolator' in transform_kwargs is not forwarded twice.
transform_kwargs.pop("interpolator", None)

Copilot uses AI. Check for mistakes.
Comment on lines +172 to +176

Copilot AI Mar 25, 2026

Copy link

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

This change fixes the duplicate interpolator keyword, but there’s no regression test ensuring that (a) providing transformation_params={'interpolator': ...} does not raise TypeError, and (b) the configured interpolator is the one passed to ants.apply_transforms. Adding a unit test that mocks ants.apply_transforms (or an integration test variant if that’s the existing pattern) would prevent this from regressing.

Copilot uses AI. Check for mistakes.
assert interpolator in VALID_INTERPOLATORS, (
f"Invalid interpolator: {interpolator}. "

Copilot AI Mar 25, 2026

Copy link

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Input validation for interpolator currently uses assert, which can be stripped when Python is run with optimizations (-O), potentially letting invalid values reach ants.apply_transforms and fail less clearly. Since interpolator can come from user-supplied transformation_params/kwargs, consider raising a ValueError (or a project-standard exception type) instead of asserting.

Copilot uses AI. Check for mistakes.

@neuronflow neuronflow Apr 24, 2026

Copy link
Copy Markdown
Collaborator

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

@copilot apply changes based on this feedback

f"Valid options are: {', '.join(VALID_INTERPOLATORS)}."
)
Comment on lines +175 to 180

Copilot AI Apr 26, 2026

Copy link

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

interpolator is validated via assert. Assertions can be stripped with Python optimizations (-O), allowing invalid user-supplied interpolators (from transformation_params/kwargs) to reach ants.apply_transforms and fail less clearly. Prefer raising a runtime exception (e.g., ValueError) for this validation so it is always enforced (and update the docstring Raises: accordingly if you change the exception type).

Copilot uses AI. Check for mistakes.

# TODO - self.transformation_params
# we update the transformation parameters with the provided kwargs
transform_kwargs = {**self.transformation_params, **kwargs}

# Convert all paths to Path objects
fixed_image_path = Path(fixed_image_path)
moving_image_path = Path(moving_image_path)
Expand Down
Loading