alpine.models.nonlin package#

Submodules#

alpine.models.nonlin.nonlin module#

class alpine.models.nonlin.nonlin.Gauss#

Bases: Nonlinear

Gaussian nonlinearity proposed by [Ramasinghe and Lucey, 2022].

__init__(scale=1.0, name='gauss')#

Initialize internal Module state, shared by both nn.Module and ScriptModule.

forward(x)#

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.

class alpine.models.nonlin.nonlin.HOSC#

Bases: Nonlinear

HOSC nonlinearity proposed by [Serrano et al., 2024]

__init__(beta, name='hosc')#

Initialize internal Module state, shared by both nn.Module and ScriptModule.

forward(x)#

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.

class alpine.models.nonlin.nonlin.Nonlinear#

Bases: Module

Base class for activation functions that can be tracked using the FeatureExtractor context manager.

__init__(name: str)#

Initialize internal Module state, shared by both nn.Module and ScriptModule.

forward(x)#

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.

class alpine.models.nonlin.nonlin.ReLU#

Bases: Nonlinear

__init__(name='relu')#

Initialize internal Module state, shared by both nn.Module and ScriptModule.

forward(x)#

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.

class alpine.models.nonlin.nonlin.Sinc#

Bases: Nonlinear

Sinc nonlinearity proposed by :cite:``.

__init__(omega=30.0, name='sinc')#

Initialize internal Module state, shared by both nn.Module and ScriptModule.

forward(x)#

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.

class alpine.models.nonlin.nonlin.Sine#

Bases: Nonlinear

Sine nonlinearity proposed by [Sitzmann et al., 2020]

__init__(omega=30.0, name='sine')#

Initialize internal Module state, shared by both nn.Module and ScriptModule.

forward(x)#

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.

class alpine.models.nonlin.nonlin.Wavelet#

Bases: Nonlinear

Wavelet nonlinearty proposed by [Saragadam et al., 2022]

__init__(sigma=1.0, omega=30.0, trainable=False, name='wavelet')#

Initialize internal Module state, shared by both nn.Module and ScriptModule.

forward(x)#

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.

Module contents#