SegmentedOperand#

class cuequivariance.SegmentedOperand( segments: list[tuple[int, ...]] | None = None, *, ndim: int | None = None, _dims: dict[int, set[int]] | None = None, )#

A segmented operand is a list of segment’s shapes.

classmethod empty_segments( num_segments: int, ) → SegmentedOperand#: Create an operand with ndim=0

classmethod stack( operands: list[SegmentedOperand], ) → SegmentedOperand#: Stack a list of operands together.

copy() → SegmentedOperand#: Copy the operand.

assert_valid()#: Assert that the operand is valid.

insert_segment(index: int, segment: tuple[int, ...])#: Insert a segment at a given index.

add_segment(segment: tuple[int, ...]) → int#: Add a segment to the operand.

property num_segments: int#: The number of segments in the operand.

property size: int#: The total size of the operand.

segment_slices() → list[slice]#: Return slice object for each segment.

get_dimensions_dict() → dict[int, set[int]]#: Return a dictionary of dimensions for each channel.

get_dims(i: int) → set[int]#: Return the dimensions for a given channel.

all_same_segment_shape() → bool#: Check if all segments have the same shape. Returns False if there are no segments.

property segment_shape: tuple[int, ...]#: The shape of the segments if they are all the same.

property segment_size: int#: The size of the segments if they are all the same.