dmx.compressor.advanced_recipe.DmxQuantizerCalibrationHyperparams

class dmx.compressor.advanced_recipe.DmxQuantizerCalibrationHyperparams(observer_cls: ObserverBase = <class 'dmx.compressor.numerical.observer.HistogramObserver'>, qscheme_to_overload: qscheme = torch.per_tensor_symmetric, group_size: int | None = None, ch_axis: int | None = None)

Fake quantizer (i.e. CastTo) calibration hyperparameters with default values

__init__(observer_cls: ObserverBase = <class 'dmx.compressor.numerical.observer.HistogramObserver'>, qscheme_to_overload: qscheme = torch.per_tensor_symmetric, group_size: int | None = None, ch_axis: int | None = None) → None

Methods

__init__(observer_cls, qscheme_to_overload, ...)

Attributes

`ch_axis`
`group_size`
`qscheme_to_overload`