SNAS Profile

class confopt.profile.SNASProfile(searchspace_type: str | SearchSpaceType, epochs: int, temp_init: float = 1.0, temp_min: float = 0.03, temp_annealing: bool = True, **kwargs: Any)

Bases: BaseProfile, ABC

Train Profile class for SNAS (Stochastic Neural Architecture Search).. It inherits from the BaseProfile class and sets the sampler config for SNAS sampler.

Variables:

  • temp_init (float) – Initial temperature for sampling.

  • temp_min (float) – Minimum temperature for sampling.

  • temp_annealing (bool) – Flag to use temperature annealing.

  • total_epochs (int) – Total number of epochs for training.

configure_sampler(**kwargs) → None

Configures the sampler settings based on provided keyword arguments.

The configuration options are passed as keyword arguments.

Parameters:

**kwargs –

Arbitrary keyword arguments. Possible keys include:

sample_frequency (str): The rate at which samples should be taken.

arch_combine_fn (str): The function used to combine architectures (str). when FairDARTS is used, this should be ‘sigmoid’. Default value is ‘default’.

temp_init (float): Initial temperature for sampling.

temp_min (float): Minimum temperature for sampling.

temp_annealing (bool): Flag to use temperature annealing.

total_epochs (int): Total number of epochs for training.

The accepted keyword arguments should align with the sampler’s configuration and the attributes can be configured dynamically.

Raises:

ValueError – If an unrecognized keyword is passed in kwargs.

Returns:

None