dair_pll.deep_learnable_model

class dair_pll.deep_learnable_model.DeepLearnableModel(in_size)

Bases: ABC, Module

std_dev: torch.nn.parameter.Parameter

mean: torch.nn.parameter.Parameter

abstract sequential_eval(x, carry)

Return type:

Tensor

set_normalization(x)

Return type:

None

normalize(x)

Return type:

Tensor

class dair_pll.deep_learnable_model.DeepRecurrentModel(in_size, hidden_size, out_size, layers, nonlinearity)

Bases: DeepLearnableModel

forward(x, carry)

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.

Return type:

Tensor

sequential_eval(x, carry)

Return type:

Tensor

class dair_pll.deep_learnable_model.MLP(in_size, hidden_size, out_size, layers, nonlinearity)

Bases: DeepLearnableModel

forward(x, carry)

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.

Return type:

Tensor

sequential_eval(x, carry)

Return type:

Tensor

class dair_pll.deep_learnable_model.ZeroModel(in_size, hidden_size, out_size, layers, nonlinearity)

Bases: DeepLearnableModel

forward(x, carry)

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.

Return type:

Tensor

sequential_eval(x, carry)

Return type:

Tensor