Hi @Nic-Ma, this is the first version of incorporating the SliceInferer into monai.inferers.

What do you think of the implementation? For now, it is the same as what was in the tutorials with better documentation. I'm trying to think of how to make it more readable and concise. Any inputs would be appreciated.

Hi @Nic-Ma

Incorporated all the changes you suggested and added a unit test. Let me know if something is missing.

I also changed the logic a bit to make the purpose of the SliceInferer more clear. The old version would fallback and run the SlidingWindowInferer if the roi_size was not provided according to the SliceInferer requirements - this might be confusing to the user, therefore I've changed it to throw a RuntimeError in case the roi_size is not as expected. Added a note to describe what roi_size expects too.

Hi @surajpaib ,

There is some format error in the code according to CI tests:

monai/inferers/inferer.py:262:16: error: Argument 1 to "len" has incompatible type "Union[Sequence[int], int]"; expected "Sized"  [arg-type]
monai/inferers/inferer.py:263:34: error: Argument 1 to "list" has incompatible type "Union[Sequence[int], int]"; expected "Iterable[int]"  [arg-type]
monai/inferers/inferer.py:268:41: error: Argument 2 to "__call__" of "SlidingWindowInferer" has incompatible type "Callable[[Any], Callable[..., Tensor]]"; expected "Callable[..., Tensor]"  [arg-type]
monai/inferers/inferer.py:268:51: error: Incompatible return value type (got "Callable[..., Tensor]", expected "Tensor")  [return-value]
monai/inferers/inferer.py:281:16: error: Incompatible return value type (got "Tensor", expected "Callable[..., Tensor]")  [return-value]

Thanks.