quaterion_models.modules.simple module

class ActivationFromFnName(activation_fn: str)

Bases: Module

Simple module constructed from function name to be used in nn.Sequential

Construct a nn.Module that applies the specified activation function to inputs

Parameters:

activation_fn – Name of the activation function to apply to input. Must be an attribute of torch.nn.functional.

forward(inputs: Tensor) → Tensor

Defines 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.

training: bool