FakeQuantMAOutputScaleLayer

class paddle.nn.quant.quant_layers. FakeQuantMAOutputScaleLayer ( layer: Layer, weight_bits: int = 8, activation_bits: int = 8, moving_rate: float = 0.9, name: str | None = None, reduce_type: Literal[max] | None = None, *args: Never, **kwargs: Never ) [source]

Add FakeQuantMovingAverageAbsMax layer to the behind of the input layer.

forward ( *inputs: Any, **kwargs: Any ) Tensor

forward

Defines the computation performed at every call. Should be overridden by all subclasses.

Parameters
  • *inputs (tuple) – unpacked tuple arguments

  • **kwargs (dict) – unpacked dict arguments