mgplvm.lpriors.torus module

class mgplvm.lpriors.torus.IARP(p, manif, mu=None, phi=None, concentration=None, fixed_mu=False, fixed_concentration=False, link='logits')

Bases: mgplvm.lpriors.torus.LpriorTorus

forward(g, batch_idxs=None)

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.

property msg

name = 'IARP'

property prms

training: bool

class mgplvm.lpriors.torus.LARP(p, manif, mu=None, phi=None, eta=None, fixed_mu=False, fixed_eta=False, link='logits')

Bases: mgplvm.lpriors.torus.LpriorTorus

forward(g, batch_idxs=None)

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.

property msg

name = 'LinkedARP'

property prms

training: bool

class mgplvm.lpriors.torus.LpriorTorus(manif)

Bases: mgplvm.lpriors.common.Lprior

training: bool

class mgplvm.lpriors.torus.VonMises(manif, concentration=None, fixed_concentration=False)

Bases: mgplvm.lpriors.torus.LpriorTorus

forward(g, batch_idxs=None)

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.

property msg

name = 'VonMises'

property prms

training: bool