analogvnn.nn.activation.Activation#

Module Contents#

Classes#

InitImplement

Implements the initialisation of parameters using the activation function.

Activation

This class is base class for all activation functions.

class analogvnn.nn.activation.Activation.InitImplement[source]#

Implements the initialisation of parameters using the activation function.

static initialise(tensor: torch.Tensor) torch.Tensor[source]#

Initialisation of tensor using xavier uniform initialisation.

Parameters:

tensor (Tensor) – the tensor to be initialized.

Returns:

the initialized tensor.

Return type:

Tensor

static initialise_(tensor: torch.Tensor) torch.Tensor[source]#

In-place initialisation of tensor using xavier uniform initialisation.

Parameters:

tensor (Tensor) – the tensor to be initialized.

Returns:

the initialized tensor.

Return type:

Tensor

class analogvnn.nn.activation.Activation.Activation[source]#

Bases: analogvnn.nn.module.Layer.Layer, analogvnn.backward.BackwardModule.BackwardModule, InitImplement, abc.ABC

This class is base class for all activation functions.