BaseConceptualModel

class neuralhydrology.modelzoo.baseconceptualmodel.BaseConceptualModel(cfg: Config)

Bases: Module

Abstract base model class, don’t use this class for model training.

The purpose is to have some common operations that all conceptual models will need. Use subclasses of this class for training/evaluating different conceptual models, e.g. ‘SHM’.

Parameters:

cfg (Config) – The run configuration.

forward(x_conceptual: Tensor, lstm_out: Tensor) → Dict[str, Tensor | Dict[str, Tensor]]

Define the computation performed at every call.

Should be overridden by all subclasses.

Note

Although the recipe for forward pass needs to be defined within this function, one should call the Module instance afterwards instead of this since the former takes care of running the registered hooks while the latter silently ignores them.

property initial_states

property parameter_ranges