strided_slice

Classes

StridedSliceOperator

StridedSliceOperator(ident: int, op: OperatorT, model: ModelT, subgraph: SubGraphT, prefix: str = 'aot', attributes: dict[str, str] = {})

STRIDED_SLICE operator.

This operator performs a strided slice operation on the input tensor according to the specified parameters.

Parameters:

• ident

  (int) –

  Operator identifier.

• op

  (OperatorT) –

  Operator object from LiteRT model.

• model

  (ModelT) –

  LiteRT model object.

• subgraph

  (SubGraphT) –

  Subgraph object from LiteRT model.

• prefix

  (str, default: 'aot' ) –

  Prefix for generated files. Defaults to "aot".

• attributes

  (dict[str, str], default: {} ) –

  Attributes for template values. Defaults to {}.

Attributes

name property

name: str

Return the operator name.

input_indices property

input_indices: list[int]

Return the input tensor indices.

output_indices property

output_indices: list[int]

Return the output tensor indices.

input_tensors property

input_tensors: list[TensorT]

Return the input tensors.

output_tensors property

output_tensors: list[TensorT]

Return the output tensors.

Functions

compute_values

compute_values() -> dict[str, str]

Compute the values for the operator.

Returns:

• dict[str, str] –

  dict[str, str]: Computed values for the operator.

generate_source_code

generate_source_code(save_path: Path)

Generate the source code for the operator.

Parameters:

• save_path

  (Path) –

  Path to save the generated code.

Functions

compute_start_for_dim

compute_start_for_dim(axis: int, axis_size: int, stride: int, begin_mask: int, start: int) -> int

Compute the start index for a given dimension.

Parameters:

• axis

  (int) –

  The axis along which to compute the start.

• axis_size

  (int) –

  The size of the axis.

• stride

  (int) –

  The stride value.

• begin_mask

  (int) –

  The begin mask.

• start

  (int) –

  The initial start index.

Returns:

• int ( int ) –

  The computed start index.

compute_end_for_dim

compute_end_for_dim(axis: int, axis_size: int, stride: int, end_mask: int, start: int, end: int, shrink_axis_mask: int, offset: bool) -> int

Compute the end index for a given dimension.

Parameters:

• axis

  (int) –

  The axis along which to compute the end.

• axis_size

  (int) –

  The size of the axis.

• stride

  (int) –

  The stride value.

• end_mask

  (int) –

  The end mask.

• start

  (int) –

  The initial start index.

• end

  (int) –

  The initial end index.

• shrink_axis_mask

  (int) –

  The shrink axis mask.

• offset

  (bool) –

  Whether to apply an offset to the end index.

Returns:

• int ( int ) –

  The computed end index.