supaernova.configs.steps.nflow.tf

source module supaernova.configs.steps.nflow.tf

Classes

• TFNFlowModelConfig — Create a new model by parsing and validating input data from keyword arguments.

Functions

• validate_activation

• validate_scheduler

• validate_optimiser

• validate_loss

• get_loss

source validate_activation(activation: ConfigInputObject[ActivationObject])

source validate_scheduler(scheduler: ConfigInputObject[SchedulerObject]) → SchedulerObject

source validate_optimiser(optimiser: ConfigInputObject[OptimiserObject])

source validate_loss(loss: ConfigInputObject[LossObject])

Raises

• ValueError

source get_loss(loss_fn: Callable[[tf.Tensor, tf.Tensor], tf.Tensor]) → type[ks.losses.Loss]

source class TFNFlowModelConfig(**data: Any)

Bases : NFlowModelConfig

Create a new model by parsing and validating input data from keyword arguments.

Raises [ValidationError][pydantic_core.ValidationError] if the input data cannot be validated to form a valid model.

self is explicitly positional-only to allow self as a field name.

Attributes

• model_extra : dict[str, Any] | None — Get extra fields set during validation.

• model_fields_set : set[str] — Returns the set of fields that have been explicitly set on this model instance.

source property TFNFlowModelConfig.activation_fn: ActivationObject

source property TFNFlowModelConfig.optimiser_cls: type[ks.optimizers.Optimizer]

source property TFNFlowModelConfig.scheduler_cls: type[ks.optimizers.schedules.LearningRateSchedule]

source property TFNFlowModelConfig.loss_cls: type[ks.losses.Loss] | None