twinlab.BenchmarkParams#

class twinlab.BenchmarkParams(type='quantile')[source]#

Parameter configuration for benchmarking a trained emulator.

Variables:

type (str, optional) –

Specifies the type of emulator benchmark to be performed. Can be either:

  • "quantile": The calibration curve is calculated over Gaussian quantiles.

  • "interval": The calibration curve is calculated over Gaussian confidence intervals.

The default is "quantile".

__init__(type='quantile')[source]#

Methods

__init__([type])

unpack_parameters()