tanh

Classes

TanhOperator

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

TANH operator.

This operator computes the tanh activation function on the input tensor.

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

make_tanh_lut

make_tanh_lut(input_scale: float, input_zero_point: int, output_scale: float, output_zero_point: int) -> np.ndarray

Build a 256-entry int8 → int8 LUT for quantized Tanh, iterating over q in [-128..127].

compute_params_s16

compute_params_s16(input_tensor: AirTensor, output_tensor: AirTensor) -> AirFixedPointScale

Compute the input_multiplier and input_left_shift parameters for int16 Tanh.

Parameters:

• input_tensor

  (AirTensor) –

  The input tensor.

• output_tensor

  (AirTensor) –

  The output tensor.

Returns:

• AirFixedPointScale ( AirFixedPointScale ) –

  The input_multiplier and input_left_shift parameters.