mlcolvar.core.transform.Transform

class mlcolvar.core.transform.Transform(in_features: int, out_features: int)

Bases: Module

Base transform class. To implement a new transform override the forward method. The parameters of the transform should be set either in the initialization or via the setup_from_datamodule function.

__init__(in_features: int, out_features: int)

Transform class options.

Parameters:

• in_features (int) – Number of inputs of the transform

• out_features (int) – Number of outputs of the transform

Methods

__init__(in_features, out_features)	Transform class options.
forward(X)	Define the computation performed at every call.
setup_from_datamodule(datamodule)	Initialize parameters based on pytorch lighting datamodule.
teardown()

forward(X: 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.

setup_from_datamodule(datamodule)

Initialize parameters based on pytorch lighting datamodule.

Attributes

T_destination
call_super_init
dump_patches
training