jactorch.quickstart.models#

Classes

LinearClassificationModel

LinearRegressionModel

MLPClassificationModel

MLPModel

MLPRegressionModel

ModelIOKeysMixin

Class LinearClassificationModel

class LinearClassificationModel[source]#

Bases: MLPClassificationModel

__init__(input_dim, nr_classes)[source]#

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

forward(feed_dict)#

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.

reset_parameters()#

Class LinearRegressionModel

class LinearRegressionModel[source]#

Bases: MLPRegressionModel

__init__(input_dim, output_dim)[source]#

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

forward(feed_dict)#

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.

reset_parameters()#

Class MLPClassificationModel

class MLPClassificationModel[source]#

Bases: MLPModel, ModelIOKeysMixin

__init__(input_dim, nr_classes, hidden_dims, batch_norm=None, dropout=None, activation='relu')[source]#

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

forward(feed_dict)[source]#

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.

reset_parameters()#

Class MLPModel

class MLPModel[source]#

Bases: MLPLayer

__init__(input_dim, output_dim, hidden_dims, batch_norm=None, dropout=None, activation='relu', flatten=True, last_activation=False)#

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

forward(input)#

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.

reset_parameters()#

Class MLPRegressionModel

class MLPRegressionModel[source]#

Bases: MLPModel, ModelIOKeysMixin

__init__(input_dim, output_dim, hidden_dims, batch_norm=None, dropout=None, activation='relu')[source]#

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

forward(feed_dict)[source]#

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.

reset_parameters()#

Class ModelIOKeysMixin

class ModelIOKeysMixin[source]#

Bases: object

__init__()#
__new__(**kwargs)#
On this page