mean

Classes

MeanOperator

MeanOperator(op: AirOperator, model: AirModel, platform: SocPlatform, prefix: str = 'aot', attributes: dict[str, str] = {})

MEAN operator.

This operator computes the mean of the input tensor along specified axes.

Parameters:

• op

  (AirOperator) –

  The AIR operator to wrap.

• model

  (AirModel) –

  The AIR model.

• platform

  (SocPlatform) –

  The target platform for code generation.

• prefix

  (str, default: 'aot' ) –

  Prefix for generated code files. Defaults to "aot".

• attributes

  (dict[str, str], default: {} ) –

  Attributes for template values. Defaults to {}.

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.

emit

emit(save_path: Path)

Generate the source code for the operator.

Parameters:

• save_path

  (Path) –

  Path to save the generated code.

Functions

fold_mean_multiplier

fold_mean_multiplier(base_fp: AirFixedPointScale, count) -> AirFixedPointScale

Fold 1 / count into base_multiplier and shift, such that the result is compatible with arm_nn_requantize().

Ensures shift is in [0, 31] and multiplier fits in Q31.

Parameters:

• base_fp

  (AirFixedPointScale) –

  Base fixed-point scale.

• count

  (int) –

  Count to fold into the multiplier.