asterism.nets#

Module contents#

class asterism.nets.Encoder(*channels, bias=True, norm='batch', act='relu', drop=0.5, seed=None, **kwargs)#

Bases: Module

forward(x, return_kld=False)#

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 asterism.nets.MLP(*channels, bias=True, norm=None, act=None, drop=0.0, final_bias=True, final_norm=None, final_act=None, final_drop=0.0, **kwargs)#

Bases: Sequential

static layer(in_channels, out_channels=None, bias=True, norm=None, act=None, drop=0.0, **kwargs)#

class asterism.nets.RNN(channels, bias=True, norm=None, act='tanh', drop=0.0, seed=None, init_zero=False, **kwargs)#

Bases: MLP

forward(x=None, n_layers=1)#: Runs the forward pass.

class asterism.nets.VAE(*channels, bias=True, norm='batch', act='relu', drop=0.5, kld_scale=0.1, optim='adam', desc='VAE', seed=None, **kwargs)#

Bases: BaseEstimator, TransformerMixin, Module

fit(x, n_steps=None, learn_rate=0.01, batch_size=None, shuffle=True, verbosity=1, display_rate=10, **kwargs)#

Configure whether metadata should be requested to be passed to the fit method.

Note that this method is only relevant when this estimator is used as a sub-estimator within a meta-estimator and metadata routing is enabled with enable_metadata_routing=True (see sklearn.set_config()). Please check the User Guide on how the routing mechanism works.

The options for each parameter are:

True: metadata is requested, and passed to fit if provided. The request is ignored if metadata is not provided.
False: metadata is not requested and the meta-estimator will not pass it to fit.
None: metadata is not requested, and the meta-estimator will raise an error if the user provides it.
str: metadata should be passed to the meta-estimator with this given alias instead of the original name.

The default (sklearn.utils.metadata_routing.UNCHANGED) retains the existing request. This allows you to change the request for some parameters and not others.

Added in version 1.3.

Parameters#

batch_sizestr, True, False, or None, default=sklearn.utils.metadata_routing.UNCHANGED: Metadata routing for batch_size parameter in fit.
display_ratestr, True, False, or None, default=sklearn.utils.metadata_routing.UNCHANGED: Metadata routing for display_rate parameter in fit.
learn_ratestr, True, False, or None, default=sklearn.utils.metadata_routing.UNCHANGED: Metadata routing for learn_rate parameter in fit.
n_stepsstr, True, False, or None, default=sklearn.utils.metadata_routing.UNCHANGED: Metadata routing for n_steps parameter in fit.
shufflestr, True, False, or None, default=sklearn.utils.metadata_routing.UNCHANGED: Metadata routing for shuffle parameter in fit.
verbositystr, True, False, or None, default=sklearn.utils.metadata_routing.UNCHANGED: Metadata routing for verbosity parameter in fit.
xstr, True, False, or None, default=sklearn.utils.metadata_routing.UNCHANGED: Metadata routing for x parameter in fit.

Returns#

selfobject: The updated object.

set_transform_request(*, train: bool | None | str = '$UNCHANGED$', x: bool | None | str = '$UNCHANGED$') → VAE#

Configure whether metadata should be requested to be passed to the transform method.